Initial commit

skills/translation-reframing-audience-shift/SKILL.md

@@ -0,0 +1,290 @@
+---
+name: translation-reframing-audience-shift
+description: Use when content must be translated between audiences with different expertise, context, or goals while preserving accuracy but adapting presentation. Invoke when technical content needs business framing (engineering decisions → executive summary), strategic vision needs tactical translation (board presentation → team OKRs), expert knowledge needs simplification (academic paper → blog post, medical diagnosis → patient explanation), formal content needs casual tone (annual report → social media post), long-form needs summarization (50-page doc → 1-page brief), internal content needs external framing (roadmap → public updates, bug tracking → known issues), cross-cultural adaptation (US idioms → international clarity, Gen Z → Boomer messaging), medium shifts (written report → presentation script, detailed spec → action checklist), or when user mentions "explain to", "reframe for", "translate this for [audience]", "make this more [accessible/formal/technical]", "adapt for [executives/engineers/customers]", "simplify without losing accuracy", or "same content, different audience". Apply to technical communication (code → business value), organizational translation (strategy → execution), education (expert → novice), customer communication (internal → external), cross-cultural messaging, and anywhere same core message needs different presentation for different stakeholders while maintaining correctness.
+---
+# Translation, Reframing & Audience Shift
+
+## Purpose
+
+Adapt content for different audiences while preserving core accuracy—changing tone, depth, emphasis, and framing to match audience expertise, goals, and context.
+
+## When to Use
+
+**Invoke this skill when:**
+- Same information needs to reach audiences with different expertise (technical → business, expert → novice)
+- Content tone/formality needs changing (formal report → casual email, academic → conversational)
+- Strategic content needs tactical translation (vision → action items, why → how)
+- Internal content goes external (company docs → customer-facing, jargon → plain language)
+- Long-form needs compression without losing key points (detailed → summary, comprehensive → highlights)
+- Medium changes (written → spoken, document → presentation, email → social media)
+- Cross-cultural or demographic shifts (US → international, industry → industry, generation → generation)
+- Emphasis needs shifting (highlight different aspects for different stakeholders)
+
+**Don't use when:**
+- Content is already appropriate for target audience (no translation needed)
+- Creating entirely new content (not adapting existing)
+- Simple copy-editing (grammar, spelling) without audience shift
+- Translating between human languages (use language translation, not this skill)
+
+## What Is It?
+
+**Translation/reframing** adapts content between audiences by preserving semantic accuracy (what is true) while changing presentation (how it's communicated). **Four fidelity types:**
+
+**1. Semantic fidelity (MUST preserve):** Core facts, relationships, constraints, implications remain accurate
+**2. Tonal fidelity (adapt):** Formality, emotion, register change to match audience expectations
+**3. Emphasis fidelity (adapt):** What's highlighted vs. backgrounded shifts based on audience priorities
+**4. Medium fidelity (adapt):** Structure, length, format change for different channels/contexts
+
+**Example:** Technical incident postmortem → Customer status update
+
+**Original (Engineers):** "Root cause: race condition in distributed lock manager under high concurrency (>5000 req/s). Null pointer dereference when lock timeout occurred before callback registration. Fix: added CAS operation with retry logic, deployed canary to 5% traffic, monitored for 2 hours before full rollout."
+
+**Translated (Customers):** "What happened: Service slowdown on Jan 15, 2-3pm affecting checkout for some users. Root cause: Timing issue in our system under high traffic. Status: Fixed, monitored, and fully deployed. Prevention: Added safeguards to prevent similar timing issues."
+
+**What changed:** Technical detail reduced, jargon removed, impact/status emphasized, customer concerns prioritized (what happened, is it fixed, will it happen again). **What preserved:** Timing, affected functionality, root cause category, resolution status.
+
+## Workflow
+
+Copy this checklist and track your progress:
+
+```
+Translation & Reframing Progress:
+- [ ] Step 1: Analyze source and target audiences
+- [ ] Step 2: Identify translation type and constraints
+- [ ] Step 3: Apply translation strategy
+- [ ] Step 4: Validate fidelity and appropriateness
+- [ ] Step 5: Refine and deliver
+```
+
+**Step 1: Analyze source and target audiences**
+
+Characterize both audiences using [Audience Analysis](#audience-analysis) framework (expertise, goals, context, constraints). Identify gap between source and target.
+
+**Step 2: Identify translation type and constraints**
+
+Classify as: technical↔business, strategic↔tactical, expert↔novice, formal↔informal, long↔short, internal↔external, or cross-cultural. See [Common Translation Types](#common-translation-types) for patterns.
+
+**Step 3: Apply translation strategy**
+
+For simple cases → Use [resources/template.md](resources/template.md) for structured translation. For complex cases (multiple audiences, high stakes, nuanced reframing) → Study [resources/methodology.md](resources/methodology.md) for advanced techniques.
+
+**Step 4: Validate fidelity and appropriateness**
+
+Self-assess using [resources/evaluators/rubric_translation_reframing_audience_shift.json](resources/evaluators/rubric_translation_reframing_audience_shift.json). Check: semantic accuracy preserved? tone appropriate? emphasis aligned with audience priorities? See [Validation](#validation) section.
+
+**Step 5: Refine and deliver**
+
+Create `translation-reframing-audience-shift.md` with source, target audience, translated content, and translation rationale. See [Delivery Format](#delivery-format).
+
+---
+
+## Audience Analysis
+
+Before translating, characterize source and target:
+
+**1. Expertise Level**
+- **Expert**: Domain fluent, comfortable with jargon, wants depth and nuance
+- **Intermediate**: Familiar with basics, needs some context, appreciates balance
+- **Novice**: No background assumed, needs analogies and plain language, wants practical takeaways
+
+**2. Primary Goals**
+- **Decision-makers**: Want options, trade-offs, recommendations, risks, timelines
+- **Implementers**: Want specifics, how-to, constraints, success criteria
+- **Learners**: Want understanding, context, mental models, examples
+- **Stakeholders**: Want impact, status, next steps, how it affects them
+
+**3. Context & Constraints**
+- **Time**: Busy executives (1-page), deep dives (comprehensive), quick updates (bullets)
+- **Medium**: Email (skimmable), presentation (visual + verbal), document (reference)
+- **Familiarity**: Internal (shared context) vs. external (assume nothing)
+- **Sensitivity**: Public (carefully worded) vs. private (candid)
+
+**4. Cultural/Demographic**
+- **Language**: Native vs. non-native speakers (idiomatic vs. literal)
+- **Generation**: Communication norms (emoji use, formality expectations)
+- **Industry**: Tech vs. traditional (pacing, references, assumptions)
+- **Geography**: US vs. international (date formats, measurement units, cultural references)
+
+**Mapping exercise:** Source audience is [expertise/goals/context] → Target audience is [expertise/goals/context] → Gap requires [translation strategy].
+
+---
+
+## Common Translation Types
+
+### Technical ↔ Business
+
+**Technical → Business:**
+- **Remove**: Implementation details, jargon, code, algorithms
+- **Add**: Business value, customer impact, cost/benefit, competitive advantage
+- **Shift emphasis**: How it works → Why it matters, Metrics → Outcomes
+- **Example**: "Reduced p95 latency from 450ms to 120ms via query optimization" → "Pages load 3x faster, improving customer satisfaction and conversion"
+
+**Business → Technical:**
+- **Remove**: Marketing language, vague goals, buzzwords
+- **Add**: Requirements, constraints, acceptance criteria, technical implications
+- **Shift emphasis**: Vision → Implementation details, Outcomes → Metrics
+- **Example**: "Delight customers with seamless experience" → "Reduce checkout flow to 2 steps, target 95% completion rate, maintain PCI compliance"
+
+### Strategic ↔ Tactical
+
+**Strategic → Tactical:**
+- **Remove**: High-level vision, market trends, abstract goals
+- **Add**: Specific actions, timelines, owners, dependencies, success metrics
+- **Shift emphasis**: Why → What and how, 3-year vision → This quarter's plan
+- **Example**: "Become data-driven organization" → "Q1: Instrument 10 key user flows. Q2: Train PMs on analytics. Q3: Establish weekly metrics review."
+
+**Tactical → Strategic:**
+- **Remove**: Granular tasks, individual tickets, daily activities
+- **Add**: Themes, rationale, business alignment, cumulative impact
+- **Shift emphasis**: Individual work → Portfolio narrative, Tasks → Outcomes
+- **Example**: "Fixed 47 bugs, added 12 features, refactored auth" → "Improved product stability and security foundation to support enterprise customers"
+
+### Expert ↔ Novice
+
+**Expert → Novice:**
+- **Remove**: Jargon, assumptions of prior knowledge, complex terminology
+- **Add**: Analogies, definitions, examples, "why this matters"
+- **Shift emphasis**: Nuance → Core concepts, Edge cases → Happy path
+- **Example (Medical)**: "Idiopathic hypertension, prescribe ACE inhibitor, monitor renal function" → "High blood pressure without clear cause. Medication helps blood vessels relax. Regular kidney checks needed."
+
+**Novice → Expert:**
+- **Remove**: Over-explanations, analogies, hand-holding
+- **Add**: Precision, technical terms, caveats, edge cases
+- **Shift emphasis**: Simplified model → Accurate complexity
+- **Example**: "Make the button easier to click" → "Increase touch target to 44×44pt per iOS HIG, add 8pt padding, ensure 3:1 contrast ratio"
+
+### Formal ↔ Informal
+
+**Formal → Informal:**
+- **Tone**: Third person → First person, Passive → Active, Complex → Simple
+- **Structure**: Rigid sections → Conversational flow, Citations → Casual mentions
+- **Language**: "Furthermore, it is evident" → "Also, you can see"
+- **Example**: "The organization has determined that remote work arrangements shall be permitted" → "We're allowing remote work"
+
+**Informal → Formal:**
+- **Tone**: Contractions → Full words ("we're" → "we are"), Casual → Professional
+- **Structure**: Loose → Structured sections with clear headers
+- **Language**: "Stuff's broken" → "System experiencing degradation"
+- **Example**: "Just shipped this cool feature!" → "Released enhanced functionality for improved user experience"
+
+### Long-form ↔ Summary
+
+**Long → Summary:**
+- **Structure**: Inverted pyramid (most important first), bullet points, highlight key decisions/actions
+- **Remove**: Supporting details, full context, exhaustive examples
+- **Preserve**: Core findings, recommendations, next steps, critical caveats
+- **Ratios**: 50 pages → 1 page (50:1), 1 hour → 5 min (12:1), Comprehensive → Highlights
+
+**Summary → Long-form:**
+- **Add**: Context, methodology, supporting evidence, alternative perspectives
+- **Structure**: Introduction → Body → Conclusion, Multiple sections with subheadings
+- **Preserve**: Original key points as outline, Expand each with detail
+
+---
+
+## Validation
+
+Before finalizing, check:
+
+**Semantic Fidelity (CRITICAL):**
+- [ ] Core facts accurate? (No distortions or omissions that change meaning)
+- [ ] Relationships preserved? (Cause-effect, dependencies, constraints intact)
+- [ ] Caveats included? (Limitations, uncertainties, edge cases mentioned when relevant)
+- [ ] Implications correct? (What this means for audience is accurate)
+- [ ] Verifiable? (Expert in source domain would confirm translation is accurate)
+
+**Audience Appropriateness:**
+- [ ] Expertise match? (Not too technical or too dumbed-down for target)
+- [ ] Jargon level right? (Explained when needed, used when understood)
+- [ ] Goals addressed? (Decision-makers get options, implementers get how-to, learners get why)
+- [ ] Tone appropriate? (Formality, emotion, register match audience expectations)
+- [ ] Length appropriate? (Respects audience time constraints)
+
+**Emphasis Alignment:**
+- [ ] Priorities match audience? (Highlight what they care about)
+- [ ] Details at right level? (Enough for understanding, not overwhelming)
+- [ ] Actionability? (If audience needs to act, next steps are clear)
+- [ ] Framing effective? (Positive/negative/neutral matches context and goal)
+
+**Medium & Format:**
+- [ ] Structure fits medium? (Email = skimmable, presentation = visual, document = reference)
+- [ ] Formatting helps comprehension? (Headers, bullets, bold for key points)
+- [ ] Accessibility? (Clear for non-native speakers if needed, links/references provided)
+
+**Cultural/Demographic:**
+- [ ] Idioms/references work? (Avoided US-centric idioms if international audience)
+- [ ] Examples relatable? (Audience can connect to scenarios)
+- [ ] Assumptions explicit? (Don't rely on shared context that target lacks)
+
+**Minimum Standard:** Use rubric (resources/evaluators/rubric_translation_reframing_audience_shift.json). Average score ≥ 3.5/5 before delivering.
+
+---
+
+## Delivery Format
+
+Create `translation-reframing-audience-shift.md` with:
+
+**1. Source Analysis**
+- Original audience: [Expertise, goals, context]
+- Original content: [Brief excerpt or summary]
+- Original tone/emphasis: [What was highlighted, how it was framed]
+
+**2. Target Analysis**
+- Target audience: [Expertise, goals, context]
+- Translation type: [Technical→Business, Strategic→Tactical, etc.]
+- Key constraints: [Length, medium, sensitivity]
+
+**3. Translated Content**
+- [Full translated version]
+- [Formatted for target medium—bullets for emails, sections for docs, etc.]
+
+**4. Translation Rationale**
+- **What changed:** [Jargon removed, emphasis shifted to X, details reduced, analogies added]
+- **What preserved:** [Core facts, key implications, critical caveats]
+- **Why:** [Audience expertise gap, time constraints, medium requirements, cultural adaptation]
+
+**5. Validation Notes**
+- Semantic fidelity: ✓ Core facts accurate
+- Audience match: ✓ Tone and depth appropriate for [target]
+- Emphasis: ✓ Highlights [audience priorities]
+- Limitations: [Any unavoidable compromises, e.g., "Some nuance lost for brevity"]
+
+---
+
+## Common Translation Patterns
+
+**"So What?" Test (Technical → Business):** Every technical detail answers "so what?" - "Migrated to Kubernetes" → "Auto-scale during traffic spikes, 30% cost reduction" | "OAuth 2.0" → "Enterprise SSO, removes adoption barrier"
+
+**"How?" Test (Strategic → Tactical):** Every goal answers "how?" - "Improve satisfaction" → "Response <2hr, add help center, NPS survey" | "AI-first company" → "Train PMs (Q1), hire 3 ML engineers (Q2), pilot feature (Q3)"
+
+**Analogy Bridge (Expert → Novice):** Familiar → Unfamiliar - "Git branching" = essay draft versions | "Microservices" = food trucks not one restaurant | "API rate limiting" = nightclub capacity
+
+**Inverted Pyramid (Long → Summary):** Most important first - Lede (1-2 sentences) → Key details (2-3 bullets) → Supporting (optional depth)
+
+**Code-Switching (Cross-Cultural):** Replace cultural references - "Home run" (US) → "Big success" (neutral) | "Fire hose" idiom → "Overwhelming info" (literal) | MM/DD/YYYY → YYYY-MM-DD (ISO)
+
+---
+
+## Quick Reference
+
+**Resources:**
+- [resources/template.md](resources/template.md) - Structured translation workflow
+- [resources/methodology.md](resources/methodology.md) - Advanced techniques for complex/nuanced translation
+- [resources/evaluators/rubric_translation_reframing_audience_shift.json](resources/evaluators/rubric_translation_reframing_audience_shift.json) - Quality criteria
+
+**Key Principles:**
+- **Preserve semantic accuracy** - Facts, relationships, implications must remain true
+- **Adapt presentation** - Tone, depth, emphasis change for audience
+- **Match audience needs** - Expertise level, goals, context, constraints
+- **Test with "would expert confirm?"** - Source domain expert validates translation accuracy
+- **Test with "can target act on it?"** - Target audience can understand and use it
+
+**Red Flags:**
+- Semantic drift (facts become inaccurate through simplification)
+- Talking down (condescending tone to novices)
+- Jargon mismatch (too technical or too vague for audience)
+- Missing "so what?" (technical details without business impact)
+- Missing "how?" (strategic vision without tactical translation)
+- Lost nuance (critical caveats omitted for brevity)
+- Cultural assumptions (idioms, references that exclude target)
+- Wrong emphasis (highlighting what you find interesting vs. what audience needs)

skills/translation-reframing-audience-shift/resources/evaluators/rubric_translation_reframing_audience_shift.json

@@ -0,0 +1,167 @@
+{
+  "criteria": [
+    {
+      "name": "Semantic Fidelity",
+      "weight": 1.5,
+      "description": "Are core facts, relationships, and implications preserved accurately?",
+      "levels": {
+        "5": "Perfect accuracy: all facts, cause-effect relationships, and implications preserved. Source domain expert would confirm translation is correct. Critical caveats included. Quantification retained (exact or within stated range). No semantic drift from simplification. Verifiable against original.",
+        "4": "Strong accuracy: key facts and relationships preserved, minor details simplified appropriately. Expert would mostly confirm. Important caveats included. Some quantification rounded but within reasonable range (30.2% → 'about 30%'). Minimal semantic drift, documented.",
+        "3": "Acceptable accuracy: core facts correct but some relationships simplified. Expert would note minor issues but agree on main points. Key caveats present, some edge cases omitted. Quantification less precise ('significantly' instead of '30%') but directionally correct. Some semantic drift, still usable.",
+        "2": "Questionable accuracy: facts oversimplified leading to potential misunderstanding. Expert would disagree with some translations. Missing important caveats. Quantification vague or misleading. Semantic drift changes meaning in places. Needs revision.",
+        "1": "Inaccurate: facts distorted, relationships wrong, or implications incorrect. Expert would reject translation. Critical caveats missing. False precision or gross exaggeration. Semantic drift makes it unreliable or misleading."
+      }
+    },
+    {
+      "name": "Audience Expertise Match",
+      "weight": 1.4,
+      "description": "Is content appropriate for target audience's expertise level (not too technical or too simple)?",
+      "levels": {
+        "5": "Perfect calibration: jargon level exactly right for target (explained when unknown, used when understood). Depth matches expertise (novice gets analogies, expert gets precision). Not condescending or confusing. Target would understand without frustration or boredom.",
+        "4": "Good calibration: mostly appropriate depth, minor mismatches (1-2 unexplained terms or slight over-simplification). Target would understand with minimal effort. Slightly too technical or too simple in places but not problematic.",
+        "3": "Acceptable calibration: notable mismatches (several unexplained terms OR talking down). Target would struggle in parts or feel patronized. Expertise assumption off by 1 level (treating intermediate as novice, or novice as intermediate). Still usable with effort.",
+        "2": "Poor calibration: frequently too technical (jargon unexplained, target confused) OR too simple (obvious to target, wastes time). Expertise assumption off by 2 levels. Target likely gives up or feels insulted. Major revision needed.",
+        "1": "Complete mismatch: written for wrong audience entirely. Expert-level content for novice (incomprehensible) OR novice-level for expert (insultingly simple). Target cannot use this."
+      }
+    },
+    {
+      "name": "Goal Alignment",
+      "weight": 1.3,
+      "description": "Does translation address target audience's primary goals and use case?",
+      "levels": {
+        "5": "Perfectly aligned: addresses target's core questions (decision-makers get options/recommendations, implementers get how-to, learners get why/context, stakeholders get impact). Actionable for intended use. Emphasis on what target needs to know, not what source wants to tell.",
+        "4": "Well aligned: addresses primary goals, minor gaps (e.g., action is mostly clear but could be more specific). Target can accomplish their goal with minimal additional work. Emphasis mostly on target's priorities.",
+        "3": "Partially aligned: addresses some goals but misses key aspects (e.g., decision-makers get information but not clear recommendation, implementers get what but not how). Target needs supplemental information. Emphasis mixed between target's and source's priorities.",
+        "2": "Poorly aligned: answers different questions than target needs (e.g., gives background when target needs decision, or gives vision when target needs tactics). Target struggles to extract what they need. Emphasis on source's interests.",
+        "1": "Misaligned: doesn't address target's goals at all. Target cannot accomplish intended purpose with this translation. Completely wrong emphasis or missing critical information for their use case."
+      }
+    },
+    {
+      "name": "Tone & Formality Appropriateness",
+      "weight": 1.2,
+      "description": "Does tone match audience expectations and context (formal/informal, encouraging/neutral, etc.)?",
+      "levels": {
+        "5": "Perfect tone: formality level exactly right for audience and context (professional for executives, casual for internal team, encouraging for learners). Emotional register appropriate (neutral for facts, reassuring for concerns). Perspective (first/second/third person) matches norms. Target would feel tone is respectful and appropriate.",
+        "4": "Good tone: mostly appropriate, minor mismatches (slightly too formal or casual but not jarring). Emotional register mostly right. Target would accept without issue.",
+        "3": "Acceptable tone: noticeable mismatches (e.g., casual when formal expected, or stiff when conversational appropriate). Doesn't offend but feels off. Target would note but overlook.",
+        "2": "Inappropriate tone: clearly wrong (e.g., flippant for serious topic, condescending to audience, overly bureaucratic for friendly context). Target would be put off or annoyed. Detracts from message.",
+        "1": "Offensive tone: disrespectful, condescending, or wildly inappropriate for context. Target would reject message due to tone alone."
+      }
+    },
+    {
+      "name": "Emphasis & Prioritization",
+      "weight": 1.4,
+      "description": "Does translation lead with target's priorities and emphasize what they care about?",
+      "levels": {
+        "5": "Perfect emphasis: leads with target's top priorities in first sentence/paragraph. Key information highlighted (bullets, bold, prominent placement). Secondary details backgrounded. Target can quickly find what matters to them. 'Inverted pyramid' or 'BLUF' structure for busy audiences.",
+        "4": "Good emphasis: priorities mostly correct, minor issues (target's #1 priority in paragraph 2 instead of paragraph 1). Key information emphasized. Some extraneous detail upfront but doesn't obscure main points.",
+        "3": "Acceptable emphasis: priorities somewhat misaligned (target's top concern buried mid-document). Some key information highlighted but inconsistently. Requires skimming to find important parts. Structure makes work for target.",
+        "2": "Poor emphasis: source's priorities dominate (what source finds interesting vs. what target needs). Key information not highlighted or buried. Target must read entire thing to find relevant parts. Wrong structure for audience (exhaustive when summary needed).",
+        "1": "Wrong emphasis: completely backwards priorities (leads with trivia, buries critical information). Target would miss key points. Structure fights against target's goals."
+      }
+    },
+    {
+      "name": "Length & Concision",
+      "weight": 1.1,
+      "description": "Is length appropriate for target's time constraints and medium?",
+      "levels": {
+        "5": "Perfect length: respects target's time (exec summary 1 page, status update 3 bullets, detailed analysis comprehensive). No unnecessary verbosity. Could not be shorter without losing essential content. Medium-appropriate (email skimmable, doc reference-quality, presentation slide-friendly).",
+        "4": "Good length: mostly appropriate, could trim 10-20% without losing value. Fits time constraints. Minor verbosity or could add slight detail. Medium mostly appropriate.",
+        "3": "Acceptable length: noticeable issues (too long for time constraint, or too brief missing key info). 20-30% too verbose or 10-20% too sparse. Medium somewhat mismatched (dense paragraphs in email that should have bullets).",
+        "2": "Poor length: way too long (exec gets 10 pages when they have 5 minutes) or way too brief (implementer gets vague bullets when they need specifics). 50%+ too verbose or 30%+ missing needed content. Medium inappropriate.",
+        "1": "Unusable length: massively too long (target gives up) or far too brief (target cannot act). Completely ignores time constraints or medium norms."
+      }
+    },
+    {
+      "name": "Cultural & Demographic Sensitivity",
+      "weight": 1.2,
+      "description": "Does translation work for target's cultural/demographic context (idioms, references, examples)?",
+      "levels": {
+        "5": "Culturally appropriate: no culture-specific idioms if international audience (or replaced with target-culture equivalents). Examples relatable to target industry/geography/generation. Date formats, units, references fit target norms. Assumptions explicit, not relying on shared context source has but target lacks.",
+        "4": "Mostly appropriate: 1-2 minor cultural references that don't exclude target (e.g., common idiom that's widely understood). Examples mostly relatable. Assumptions mostly explicit.",
+        "3": "Some issues: several culture-specific elements (idioms, references, examples) that may confuse or exclude target. Some unstated assumptions. Target can still use with effort. N/A if source and target are same culture.",
+        "2": "Inappropriate: many culturally specific elements (sports references unknown to target, generation-specific slang, industry jargon from different industry). Heavy unstated assumptions. Target struggles to connect.",
+        "1": "Culturally tone-deaf: riddled with exclusionary references. Assumes target shares source's culture. Target feels excluded or cannot understand due to cultural gap. N/A if source/target same culture."
+      }
+    },
+    {
+      "name": "Structural & Format Quality",
+      "weight": 1.1,
+      "description": "Is structure optimized for target medium and comprehension?",
+      "levels": {
+        "5": "Excellent structure: optimized for medium (email = skimmable with bullets/bold, doc = sections with ToC, presentation = slide-friendly bullets, conversation = natural flow). Headers guide reader. Formatting (bullets, emphasis, white space) aids comprehension. Accessible (clear for non-native speakers if needed).",
+        "4": "Good structure: appropriate for medium, minor improvements possible. Headers present. Formatting mostly helpful. Accessible.",
+        "3": "Acceptable structure: somewhat optimized but issues (email with dense paragraphs, doc without clear sections, presentation with walls of text). Formatting inconsistent. Moderate accessibility issues.",
+        "2": "Poor structure: wrong for medium (presentation that reads like essay, email that requires printing to parse). Headers missing or unhelpful. Formatting hinders (no emphasis, poor spacing). Accessibility problems.",
+        "1": "No structure: wall of text regardless of medium. No headers, bullets, or formatting. Incomprehensible structure. Inaccessible."
+      }
+    },
+    {
+      "name": "Actionability (if applicable)",
+      "weight": 1.3,
+      "description": "If target must act, are next steps clear (who, what, when, how)?",
+      "levels": {
+        "5": "Completely actionable: next steps explicit (what to do, who does it, when/deadline, how/method). Success criteria clear. Resources/links provided. Target can immediately act without follow-up questions. N/A if target doesn't need to act (FYI only).",
+        "4": "Mostly actionable: next steps clear, minor gaps (e.g., 'who' implicit from context, or 'how' partly specified). Target can act with minimal clarification.",
+        "3": "Partially actionable: next steps vague (what is stated but who/when/how unclear). Target needs follow-up to act. Success criteria ambiguous.",
+        "2": "Barely actionable: next steps very vague ('improve X'without specifics). Target unsure what to do. Would need significant clarification.",
+        "1": "Not actionable: no clear next steps despite target needing to act. Target blocked. N/A if this is informational only and no action expected."
+      }
+    },
+    {
+      "name": "Overall Translation Quality",
+      "weight": 1.2,
+      "description": "Holistic assessment: would translation successfully serve its purpose?",
+      "levels": {
+        "5": "Excellent: target would fully understand, find it useful, and accomplish their goal. Source expert confirms accuracy. No significant weaknesses. Sets gold standard.",
+        "4": "Good: target would understand and use successfully with minor issues. Source expert mostly confirms. Small improvements possible but not critical. Solid work.",
+        "3": "Acceptable: target would understand enough to act, but gaps or awkwardness. Source expert has reservations. Notable improvements needed but usable. Passes minimum bar.",
+        "2": "Problematic: target struggles to understand or use effectively. Source expert disagrees with translation choices. Major issues across multiple criteria. Needs significant revision.",
+        "1": "Failed: target cannot understand or use. Source expert rejects as inaccurate. Does not serve purpose. Complete rework needed."
+      }
+    }
+  ],
+  "guidance": {
+    "translation_type": {
+      "technical_to_business": "Prioritize Semantic Fidelity (1.5x), Goal Alignment (1.3x, focus on business value), Emphasis (1.4x, lead with 'so what?'). Expertise Match critical (business audience doesn't know technical terms). Actionability important if seeking approval/decision.",
+      "strategic_to_tactical": "Prioritize Goal Alignment (1.3x, concrete actions), Actionability (1.3x, who/what/when), Emphasis (1.4x, lead with tasks not vision). Length moderate (tactical needs specifics). Semantic Fidelity ensures strategic intent preserved in tactics.",
+      "expert_to_novice": "Prioritize Expertise Match (1.4x, simplify without condescension), Semantic Fidelity (1.5x, accuracy despite simplification), Tone (1.2x, respectful explanation). Use analogies, avoid jargon, test for 'talking down' feel.",
+      "formal_to_informal": "Prioritize Tone (1.2x, casual but not flippant), Structural Quality (1.1x, conversational flow). Semantic Fidelity and Expertise Match still matter. Cultural sensitivity for emoji/slang use.",
+      "long_to_summary": "Prioritize Length (1.1x, ruthless concision), Emphasis (1.4x, inverted pyramid), Semantic Fidelity (1.5x, preserve core despite compression). BLUF structure critical. Test: 'Can target get main point in 30 seconds?'",
+      "internal_to_external": "Prioritize Cultural Sensitivity (1.2x, no company jargon), Tone (1.2x, professional), Semantic Fidelity (1.5x, no leaked confidential info). Remove insider references, explain context.",
+      "cross_cultural": "Prioritize Cultural Sensitivity (1.2x, avoid idioms), Examples relatable to target culture. Tone may need adjustment (direct vs indirect cultures). Date formats, units, references adapted.",
+      "multi_audience": "Create separate translations if goals/expertise differ significantly. Use layered approach if one document must serve all. Ensure no contradictions between versions (semantic fidelity across all)."
+    },
+    "minimum_thresholds": {
+      "critical_criteria": "Semantic Fidelity ≥3 (must be accurate), Expertise Match ≥3 (must be comprehensible), Goal Alignment ≥3 (must be useful). If any <3, translation fundamentally flawed.",
+      "overall_average": "Must be ≥3.5 across applicable criteria before delivering. Higher threshold (≥4.0) for high-stakes translations (safety-critical, legal, financial, executive decisions)."
+    },
+    "weight_interpretation": "Semantic Fidelity (1.5x) and Emphasis (1.4x) are most critical—must be accurate and prioritize target's needs. Expertise Match (1.4x), Goal Alignment (1.3x), Actionability (1.3x), Tone (1.2x), Cultural Sensitivity (1.2x), Overall (1.2x) are highly important. Length (1.1x) and Structure (1.1x) are important but less central."
+  },
+  "common_failure_modes": {
+    "semantic_drift": "Semantic Fidelity: 1-2. Facts become inaccurate through simplification ('reduces risk by 30% if applied within 24 hours' → 'helps reduce risk'). Fix: After each simplification, check against original. Preserve quantification and critical constraints.",
+    "jargon_mismatch": "Expertise Match: 1-2. Too technical (undefined jargon confuses target) or too simple (obvious to target, wastes time). Fix: Profile target expertise (1-5 scale). Define terms at level 1-2, use terms at level 4-5.",
+    "wrong_emphasis": "Emphasis: 1-2. Leads with source's interests not target's needs (engineer excited about algorithm elegance, exec needs ROI). Fix: List target's top 3 priorities BEFORE translating. Lead with those.",
+    "missing_so_what": "Goal Alignment: 2-3. Technical details without business impact ('migrated to Kubernetes' without 'enables auto-scaling, reduces costs 30%'). Fix: Every technical detail must answer 'so what?' from target perspective.",
+    "missing_how": "Goal Alignment + Actionability: 2-3. Strategic vision without tactical translation ('become data-driven' without 'Q1: instrument 10 flows, Q2: train PMs, Q3: weekly metrics review'). Fix: Every goal must specify concrete actions.",
+    "lost_nuance": "Semantic Fidelity: 2-3. Critical caveats omitted for brevity ('works' without 'only under condition X'). Fix: Preserve important qualifications even in summaries. Add 'generally' or 'in most cases' if caveat too detailed for length.",
+    "talking_down": "Tone: 1-2. Condescending to novices ('even you can understand'). Fix: Respectful explanation. Test: 'Would I be insulted if someone explained this to me this way?'",
+    "cultural_assumptions": "Cultural Sensitivity: 1-2. Idioms or references that exclude target (baseball idioms for international, Gen Z slang for Boomers). Fix: Replace with universal equivalents ('home run' → 'big success').",
+    "unverified_accuracy": "Semantic Fidelity: 2-3. Assumes translation is correct without checking. Fix: Test with 'would source domain expert confirm this is accurate?' If uncertain, get expert review or err on side of preserving detail."
+  },
+  "self_check_questions": [
+    "Semantic Fidelity: Would source domain expert confirm this translation is accurate?",
+    "Expertise Match: Is jargon level right for target (explained when unknown, used when understood)?",
+    "Goal Alignment: Does this answer target's core questions (decide/implement/learn)?",
+    "Tone: Is formality and emotional register appropriate for audience and context?",
+    "Emphasis: Do I lead with target's priorities (not source's)?",
+    "Length: Does length respect target's time constraints?",
+    "Cultural: Do idioms/references work for target's culture/generation?",
+    "Structure: Is structure optimized for medium (email/doc/presentation/conversation)?",
+    "Actionability: If target must act, are next steps clear (who/what/when/how)?",
+    "Fidelity Trade-offs: Any simplifications that risk accuracy? Are they justified and documented?",
+    "Back-Translation Test: If I translate this back to source level, does it match original semantics?",
+    "Overall: Would target find this clear, useful, and accurate enough to act on?"
+  ],
+  "evaluation_notes": "Translation quality assessed across 10 weighted criteria. Critical: Semantic Fidelity (1.5x, accuracy preserved), Emphasis (1.4x, leads with target priorities), Expertise Match (1.4x, appropriate depth). Highly important: Goal Alignment (1.3x, addresses target's use case), Actionability (1.3x, clear next steps if needed), Tone (1.2x, matches audience), Cultural Sensitivity (1.2x, works for target's context), Overall (1.2x, holistic success). Important: Length (1.1x, respects time), Structure (1.1x, optimized for medium). Minimum thresholds: Semantic Fidelity ≥3, Expertise Match ≥3, Goal Alignment ≥3 (if any <3, fundamentally flawed). Overall average ≥3.5 for standard work, ≥4.0 for high-stakes. Common failures: semantic drift (facts distorted through simplification), jargon mismatch (too technical or too simple), wrong emphasis (source's priorities not target's), missing 'so what?' (technical without business impact), missing 'how?' (vision without tactics), lost nuance (critical caveats omitted), talking down, cultural assumptions, unverified accuracy. Quality translation preserves semantic accuracy while adapting presentation (tone, depth, emphasis, length, structure) to match target audience expertise, goals, context, and constraints."
+}

skills/translation-reframing-audience-shift/resources/methodology.md

@@ -0,0 +1,423 @@
+# Advanced Translation & Reframing Methodology
+
+## Overview
+
+Advanced techniques for complex translation scenarios: multi-audience translation, layered complexity, fidelity trade-offs, and validation strategies.
+
+---
+
+## 1. Multi-Audience Translation
+
+**Challenge:** One source must serve multiple audiences simultaneously or sequentially.
+
+**Strategies:**
+
+### Parallel Translation (One → Many)
+
+Create separate versions for each audience from single source.
+
+**Process:**
+1. **Audience clustering:** Group audiences by expertise (expert/intermediate/novice), goals (decide/implement/learn), or context (internal/external)
+2. **Core extraction:** Identify semantic core that ALL audiences need (facts, key relationships, critical caveats)
+3. **Divergent framing:** For each audience, adapt presentation while preserving core
+4. **Validation:** Ensure no contradictions between versions (all say same truth, differently framed)
+
+**Example - Product launch announcement:**
+- **Customers:** Focus on benefits, ease of use, availability (novice, learning)
+- **Partners:** Focus on integration APIs, revenue share, timeline (intermediate, implementing)
+- **Investors:** Focus on market TAM, competitive advantage, financials (expert in business, deciding)
+- **Core preserved:** Product name, launch date, key capability, availability
+
+**Efficiency tip:** Create most comprehensive version first (expert), then simplify for others. Easier than elaborating from simple version.
+
+### Layered Translation (Progressive Depth)
+
+Single document with increasing complexity levels—readers consume what they need.
+
+**Structure:**
+1. **Executive summary** (1 paragraph): Core message for busy decision-makers
+2. **Key findings** (3-5 bullets): Main takeaways for stakeholders
+3. **Analysis** (2-3 pages): Moderate detail for implementers
+4. **Appendices** (unlimited): Full technical depth for experts
+5. **Cross-references:** "For technical details, see Appendix A" links throughout
+
+**Advantage:** One artifact serves all, reader self-selects depth.
+
+**Example - Technical architecture decision:**
+- Summary: "Chose microservices for scalability, adds deployment complexity"
+- Key findings: Benefits (independent scaling, tech diversity), Costs (coordination overhead, infra complexity), Timeline (6-month migration)
+- Analysis: Service boundaries, inter-service communication patterns, deployment architecture
+- Appendices: Detailed service specs, API schemas, deployment diagrams, performance benchmarks
+
+### Modular Translation (Mix-and-Match)
+
+Create content modules that combine for different audiences.
+
+**Modules:**
+- **Core narrative:** Same for all (facts, timeline, implications)
+- **Technical deep-dive:** For engineers
+- **Business case:** For executives
+- **Implementation guide:** For operators
+- **Customer impact:** For support/sales
+
+**Assembly:** Core + [Technical] for engineers, Core + [Business case] for executives, Core + [Customer impact] for support.
+
+**Benefit:** Maintain consistency (core is identical across all), efficiency (write modules once, reuse).
+
+---
+
+## 2. Fidelity Trade-off Framework
+
+**Tension:** Simplification risks inaccuracy. Preservation risks confusion. How to decide?
+
+### Trade-off Decision Matrix
+
+| Scenario | Semantic Fidelity Priority | Presentation Priority | Resolution |
+|----------|---------------------------|----------------------|------------|
+| **Safety-critical** (medical, legal, financial) | CRITICAL - must be accurate | Secondary | Preserve accuracy, add explanations. If too complex for target, escalate or refuse to translate. |
+| **High-stakes decision** (executive, investment) | Very high - decisions depend on it | High - must be understood | Preserve key caveats, simplify mechanisms. Test: "Would decision change if they knew technical details?" If yes, include them. |
+| **Educational** (onboarding, training) | High - building mental models | Very high - must be clear | Simplify with caveat "This is simplified model; reality has nuance." Progressive layers: simple → accurate. |
+| **Informational** (status update, FYI) | Moderate - directionally correct | Very high - quick consumption | Round numbers, omit edge cases. Test: "Does rounding change conclusion?" If no, round. |
+| **Persuasive** (sales, marketing) | Moderate - highlights truth, omits downsides | Critical - must resonate | Emphasize benefits, acknowledge limits. Test: "Is this misleading?" If feels misleading, add balance. |
+
+### Fidelity Preservation Checklist
+
+When simplifying, ask:
+
+- [ ] **Does simplification change conclusion?** If yes, don't simplify that element.
+- [ ] **Would expert in source domain disagree?** If yes, revise.
+- [ ] **Are caveats critical for target's use case?** If yes, preserve them.
+- [ ] **Can I add qualifying language?** "Generally...", "In most cases...", "Simplified view: ..."
+- [ ] **Can I link to detail?** "See technical doc for full analysis"
+
+**Acceptable simplifications:**
+- Rounding numbers (32.7% → "about 30%") if conclusion unchanged
+- Omitting edge cases if target won't encounter them
+- Using analogy if disclaimer added ("Like X, but not perfect analogy")
+- Skipping methodology if outcome is what matters
+
+**Unacceptable simplifications:**
+- Stating correlation as causation
+- Omitting critical limitations ("only works under X condition")
+- Exaggerating certainty ("will happen" when "likely to happen")
+- Cherry-picking favorable facts while hiding unfavorable
+
+---
+
+## 3. Advanced Audience Profiling
+
+### Expertise Calibration
+
+Don't assume binary (expert/novice). Use spectrum with markers.
+
+**Technical expertise scale (example):**
+1. **Novice:** Never heard term, needs analogy
+2. **Aware:** Heard term, vague idea, needs definition
+3. **Familiar:** Uses term, understands concept, needs context for depth
+4. **Proficient:** Applies concept, understands nuance, needs edge cases
+5. **Expert:** Teaches concept, wants precision and caveats
+
+**Calibration technique:**
+- Identify 3-5 key terms/concepts in source
+- For each, estimate target's level (1-5)
+- Average gives overall expertise level
+- Translate accordingly: define at level 1-2, use at level 4-5
+
+### Goal Profiling
+
+Understand not just role but specific goal for this content.
+
+**Questions:**
+- **What decision does this inform?** (Approve budget? Choose approach? Understand impact?)
+- **What action follows?** (Implement? Communicate to others? Monitor?)
+- **What's the risk of misunderstanding?** (Costly mistake? Minor inefficiency?)
+- **What's already known?** (Baseline context? Prior decisions?)
+
+**Example:**
+- **Executive reading technical postmortem:** Decision = Approve prevention work? Risk = Under-invest or over-react. Needs: Severity, root cause category, cost to prevent, confidence it's fixed.
+- **Engineer reading same postmortem:** Action = Implement prevention. Risk = Repeat incident. Needs: Technical details, reproduction steps, code changes, testing approach.
+
+**Same source, different translations because goals differ.**
+
+### Contextual Constraints
+
+**Time constraint types:**
+- **Hard deadline:** Must fit in 5-minute meeting slot → Ruthless prioritization, BLUF structure
+- **Attention limit:** Will skim email → Bullets, bold, scannable
+- **Processing capacity:** Cognitively taxed (end of day, stressful period) → Simpler language, less demanding
+
+**Cultural context:**
+- **High-context culture:** (Japan, China) Implicit communication, read between lines → More context, softer framing
+- **Low-context culture:** (US, Germany) Explicit communication, direct → Clear statements, explicit asks
+
+---
+
+## 4. Translation Validation Techniques
+
+### Expert Review
+
+**Best practice:** Have source domain expert review translation for accuracy.
+
+**Process:**
+1. Provide expert with: (a) Original source, (b) Translated version, (c) Target audience description
+2. Ask: "Is the translation accurate for this audience? What's missing or wrong?"
+3. Note: Experts often over-include detail. Push back: "Does target need this for their goal?"
+
+**If no expert available:** Self-review by reading translation and asking "would I stake my reputation on this being accurate?"
+
+### Target Audience Testing
+
+**Best practice:** Show translation to representative of target audience.
+
+**Process:**
+1. Find someone matching target profile (expertise, role, context)
+2. Give them translated version (NOT original)
+3. Ask: "What's the main message? What should you do? Any confusion?"
+4. If misunderstood: Identify where and revise
+
+**Red flags:**
+- Target misses key point → Not emphasized enough
+- Target asks "what does X mean?" → Jargon not explained
+- Target takes wrong action → Implications unclear
+- Target seems talked down to → Tone too simple
+
+### Back-Translation Test
+
+**Technique:** Translate back to source audience level. Does it match original semantics?
+
+**Process:**
+1. Translate expert → novice
+2. Now translate novice version → expert (what would expert infer?)
+3. Compare re-expert-ified version to original
+4. Gaps = semantic loss in simplification
+
+**Example:**
+- Original (expert): "p95 latency reduced from 450ms to 120ms via query optimization"
+- Translated (novice): "Pages load 3x faster after improving database"
+- Back-translated (expert): "Response time improved ~3x via database optimization"
+- **Lost:** Specific metric (p95), exact numbers (450→120), method (query optimization)
+- **Preserved:** Magnitude (3x), category (database)
+- **Decision:** Acceptable loss for novice? If they need to reproduce work, NO. If they just need to know it's fixed, YES.
+
+---
+
+## 5. Common Failure Modes & Recovery
+
+### Semantic Drift
+
+**Symptom:** Translation becomes inaccurate through cumulative simplifications.
+
+**Example:**
+- Fact: "Reduces risk by 30% if applied within 24 hours"
+- Simplification 1: "Reduces risk by 30%"
+- Simplification 2: "Reduces risk significantly"
+- Simplification 3: "Helps reduce risk"
+- **Drift:** Lost quantification (30%) and time constraint (24 hours). Now sounds like "maybe helps a bit."
+
+**Prevention:**
+- After each simplification, check against original
+- Preserve one level of quantification ("significant" = at least 20-40% range)
+- Preserve critical constraints (time, conditions, scope)
+
+**Recovery:** If drift detected, re-anchor to source and re-translate with tighter constraints.
+
+### Audience Mismatch
+
+**Symptom:** Translation too technical or too simple for actual target.
+
+**Diagnosis:**
+- Too technical: Target asks "what does X mean?" frequently, gives up reading
+- Too simple: Target feels patronized, says "I know this, get to the point"
+
+**Recovery:**
+1. Re-profile audience (was assumption wrong?)
+2. Adjust one level up/down on expertise scale
+3. Test with different target representative
+
+### Emphasis Inversion
+
+**Symptom:** Translation emphasizes what source cares about, not what target needs.
+
+**Example:**
+- Source (engineer): Excited about elegant algorithm
+- Translation for business: Leads with algorithm elegance
+- Target (exec): Doesn't care about elegance, cares about ROI
+- **Fix:** Lead with business impact, mention elegance as side note if at all
+
+**Prevention:** Before translating, list target's top 3 priorities. Ensure translation leads with those, not source's priorities.
+
+### False Simplification
+
+**Symptom:** Simplification introduces error, not just loss of detail.
+
+**Example:**
+- Fact: "Correlation between X and Y (r=0.6, p<0.05)"
+- Bad simplification: "X causes Y"
+- **Error:** Correlation ≠ Causation
+
+**Prevention:** Distinguish:
+- **Loss of precision** (OK if within acceptable range): "30.2%" → "about 30%"
+- **Loss of nuance** (OK if caveat added): "Usually works" + footnote "except cases A, B"
+- **Introduction of error** (NOT OK): Changing meaning, implying false causation, stating certainty when uncertain
+
+**Recovery:** If false simplification detected, revise to either: (a) Preserve accuracy with explanation, or (b) Escalate to source expert for help simplifying correctly.
+
+---
+
+## 6. Domain-Specific Translation Patterns
+
+### Technical → Business
+
+**Pattern:**
+- Remove: Implementation details, code, algorithms, technical metrics
+- Add: Business outcomes, customer impact, competitive advantage, ROI
+- Reframe: "How" → "Why" and "So what?"
+
+**Translation table:**
+
+| Technical Term | Business Translation | Rationale |
+|----------------|---------------------|-----------|
+| "Migrated to microservices" | "Can now scale components independently, reducing infrastructure costs 30%" | Outcome + quantified benefit |
+| "Implemented CI/CD pipeline" | "Faster feature delivery: releases went from monthly to daily" | Customer-visible outcome |
+| "Reduced technical debt" | "Improved developer productivity 25%, enabling faster roadmap execution" | Business productivity + enablement |
+| "OAuth 2.0 authentication" | "Enterprise-grade security enabling Fortune 500 customers" | Customer segment + enablement |
+
+### Strategic → Tactical
+
+**Pattern:**
+- Remove: Vision statements, market trends, abstract goals
+- Add: Concrete actions, owners, timelines, success metrics
+- Reframe: "What" and "Why" → "How" and "Who"
+
+**Translation table:**
+
+| Strategic Statement | Tactical Translation | Specificity Added |
+|---------------------|---------------------|-------------------|
+| "Become customer-obsessed" | "Eng: Implement NPS survey (Q1). PM: Weekly customer calls (start Feb). Support: <2hr response SLA (Apr)." | Actions, owners, deadlines |
+| "Lead in AI innovation" | "Hire 3 ML engineers (Q1), train PMs on ML basics (Q2), ship AI feature in product X (Q3)" | Team changes, timeline, deliverable |
+| "Expand market presence" | "Enter 3 new regions (EMEA Q2, APAC Q3, LATAM Q4). Localize product for each. 2 sales hires per region." | Regions, timeline, resources |
+
+### Formal → Informal
+
+**Pattern:**
+- Voice: Passive → Active, Third person → First/Second person
+- Structure: Rigid → Conversational flow
+- Language: Complex → Simple, Remove jargon → Use plain terms
+- Tone: Distant → Approachable
+
+**Examples:**
+
+| Formal | Informal | Change |
+|--------|----------|--------|
+| "It has been determined that the aforementioned policy shall be revised" | "We're updating the policy" | Passive → Active, complex → simple |
+| "Stakeholders are advised to review the documentation" | "Please check out the docs" | Third person → Second person, formal → casual |
+| "The organization will implement remote work arrangements" | "We're allowing remote work" | Bureaucratic → Direct |
+
+### Long → Summary (Compression)
+
+**Invert pyramid:**
+1. **Lede** (1-2 sentences): Core finding/decision/recommendation
+2. **Key details** (3-5 bullets): Essential context
+3. **Optional depth:** "For more, see full doc"
+
+**Compression ratios:**
+- 50:1 (50 pages → 1 page): Abstract for research papers
+- 10:1 (10 pages → 1 page): Executive summary
+- 3:1 (3 paragraphs → 1 paragraph): Email summary of meeting
+
+**What to preserve in compression:**
+- Decisions made
+- Key numbers (magnitudes, not precision)
+- Critical caveats ("only works if...")
+- Next steps and owners
+
+**What to cut:**
+- Background context (assume known)
+- Alternatives considered but rejected
+- Detailed methodology
+- Supporting examples beyond first one
+
+---
+
+## 7. Advanced Techniques
+
+### Analogical Translation
+
+**Use:** Explain unfamiliar domain by mapping to familiar domain.
+
+**Process:**
+1. **Identify unfamiliar concept:** e.g., "Distributed consensus algorithm"
+2. **Find familiar analogy:** e.g., "Group of friends deciding where to eat"
+3. **Map structure:** Agreement protocol → Discussion and voting
+4. **State limits:** "Like friends voting, but must tolerate some being slow to respond"
+
+**Quality checks:**
+- Structural similarity (not just surface): Both involve coordination, conflicting preferences, eventual agreement
+- Limits acknowledged: Unlike friends, algorithms can't negotiate creatively
+- Productive: Analogy helps target understand novel concept
+
+### Progressive Disclosure Translation
+
+**Use:** Multi-level document where depth increases incrementally.
+
+**Structure:**
+1. **Level 0 - Headline:** 10-word summary
+2. **Level 1 - Summary:** 3 sentences
+3. **Level 2 - Findings:** 1 paragraph
+4. **Level 3 - Analysis:** 1 page
+5. **Level 4 - Full detail:** Multiple pages
+
+**Reader flow:** Busy exec reads Level 0-1, implementer reads Level 2-3, expert reads all.
+
+**Example - Incident report:**
+- **L0:** Database outage 2-3pm, fixed, prevented
+- **L1:** Race condition under high load caused 1hr outage. Root cause fixed, monitoring added, no data loss.
+- **L2:** [Paragraph with symptom timeline, customer impact, immediate mitigation]
+- **L3:** [Page with technical root cause, fix implementation, prevention measures]
+- **L4:** [Full postmortem with code changes, testing, related incidents]
+
+### Cultural Code-Switching
+
+**Use:** Adapt content for different cultural norms.
+
+**Dimensions:**
+- **Directness:** US (direct) vs Japan (indirect) → Frame feedback as suggestion vs directive
+- **Hierarchy:** Flat (US startups) vs Hierarchical (traditional corps) → "We decided" vs "Leadership decided"
+- **Time orientation:** Monochronic (Germany, deadlines sacred) vs Polychronic (Latin America, deadlines flexible) → Emphasize punctuality or relationships
+- **Communication style:** Low-context (explicit, literal) vs High-context (implicit, read between lines)
+
+**Example - Requesting deadline extension:**
+- **US (direct, low-context):** "We need 2 more weeks due to scope increase. Can extend deadline to March 15?"
+- **Japan (indirect, high-context):** "Considering recent scope adjustments, we're evaluating timeline. Perhaps discussion of March 15 target would be beneficial?"
+
+**Both convey same request, framed for cultural norms.**
+
+---
+
+## 8. Validation Checklist
+
+Before finalizing ANY translation:
+
+**Semantic Accuracy:**
+- [ ] Source domain expert would confirm accuracy
+- [ ] No facts changed through simplification
+- [ ] Critical caveats preserved
+- [ ] Quantification retained (at least order of magnitude)
+
+**Audience Fit:**
+- [ ] Expertise level matched (not too technical or simple)
+- [ ] Addresses target's primary goals
+- [ ] Tone appropriate for relationship and context
+- [ ] Length fits time/attention constraints
+
+**Emphasis:**
+- [ ] Leads with target's priorities, not source's
+- [ ] Key information highlighted (bullets, bold, first position)
+- [ ] Actionable if target needs to act
+
+**Quality:**
+- [ ] "Would target find this clear and useful?" - Yes
+- [ ] "Would I stake my reputation on accuracy?" - Yes
+- [ ] Any trade-offs (accuracy vs clarity) justified and documented
+
+If any check fails, revise before delivering.

skills/translation-reframing-audience-shift/resources/template.md

@@ -0,0 +1,349 @@
+# Translation, Reframing & Audience Shift Template
+
+## Workflow
+
+Copy this checklist and track your progress:
+
+```
+Translation Template Progress:
+- [ ] Step 1: Characterize source and target audiences
+- [ ] Step 2: Map translation requirements
+- [ ] Step 3: Execute translation
+- [ ] Step 4: Validate fidelity
+- [ ] Step 5: Finalize and deliver
+```
+
+**Step 1**: Complete [Section 1: Audience Characterization](#1-audience-characterization) for both source and target.
+
+**Step 2**: Fill out [Section 2: Translation Mapping](#2-translation-mapping) to identify gaps and strategy.
+
+**Step 3**: Use [Section 3: Translated Content](#3-translated-content) to perform the translation.
+
+**Step 4**: Apply [Section 4: Fidelity Validation](#4-fidelity-validation) to verify semantic accuracy and audience fit.
+
+**Step 5**: Complete [Section 5: Delivery Package](#5-delivery-package) with final content and rationale.
+
+---
+
+## 1. Audience Characterization
+
+### Source Audience
+
+**Expertise Level:**
+- [ ] Expert (domain fluent, comfortable with jargon, wants depth)
+- [ ] Intermediate (familiar with basics, needs some context)
+- [ ] Novice (no background assumed, needs plain language)
+
+**Primary Goals:**
+- [ ] Decision-makers (want options, trade-offs, recommendations)
+- [ ] Implementers (want specifics, how-to, constraints)
+- [ ] Learners (want understanding, context, mental models)
+- [ ] Stakeholders (want impact, status, next steps)
+
+**Context:**
+- **Time available**: [e.g., 5 minutes, 30 minutes, unlimited for reference]
+- **Medium**: [Email, document, presentation, conversation, etc.]
+- **Familiarity with topic**: [Deep context, some awareness, completely new]
+- **Sensitivity**: [Public/external, internal/private, confidential]
+
+**Cultural/Demographic:**
+- **Language comfort**: [Native English, non-native, specific terminology expected]
+- **Generation/age**: [Gen Z, Millennial, Gen X, Boomer - affects tone/references]
+- **Industry background**: [Tech, healthcare, finance, manufacturing, government, etc.]
+- **Geography**: [US, Europe, Asia, global - affects idioms, examples, formats]
+
+**Tone & Style of Source:**
+- **Formality**: [Formal, semi-formal, casual, conversational]
+- **Emotion**: [Neutral, enthusiastic, concerned, celebratory]
+- **Perspective**: [First person, third person, passive voice]
+- **Length/depth**: [Brief, moderate, comprehensive, exhaustive]
+
+### Target Audience
+
+**Expertise Level:**
+- [ ] Expert (domain fluent, comfortable with jargon, wants depth)
+- [ ] Intermediate (familiar with basics, needs some context)
+- [ ] Novice (no background assumed, needs plain language)
+
+**Primary Goals:**
+- [ ] Decision-makers (want options, trade-offs, recommendations)
+- [ ] Implementers (want specifics, how-to, constraints)
+- [ ] Learners (want understanding, context, mental models)
+- [ ] Stakeholders (want impact, status, next steps)
+
+**Context:**
+- **Time available**: [e.g., 1 minute, 10 minutes, will read thoroughly]
+- **Medium**: [Email, document, presentation, conversation, etc.]
+- **Familiarity with topic**: [None, minimal, some background]
+- **Sensitivity**: [Public/external, internal/private, confidential]
+
+**Cultural/Demographic:**
+- **Language comfort**: [Native English, non-native, avoid jargon]
+- **Generation/age**: [Affects communication style, references, emoji use]
+- **Industry background**: [Different from source? Requires analogy bridge?]
+- **Geography**: [Same or different from source? Affects examples, units, dates]
+
+**Desired Tone & Style:**
+- **Formality**: [Formal, semi-formal, casual, conversational]
+- **Emotion**: [Neutral, encouraging, urgent, reassuring]
+- **Perspective**: [First person (we/I), second person (you), third person]
+- **Length/depth**: [TL;DR, brief summary, moderate detail, comprehensive]
+
+### Audience Gap Analysis
+
+**Expertise gap:** Source is [expert/intermediate/novice] → Target is [expert/intermediate/novice]
+
+**Gap size:** [Small (1 level) / Moderate (2 levels) / Large (expert ↔ novice)]
+
+**Implication:** [If large gap: Requires significant simplification/elaboration and bridging analogies]
+
+**Goal misalignment:** Source focused on [decision/implementation/learning] → Target needs [decision/implementation/learning]
+
+**Implication:** [Requires emphasis shift - highlight different aspects of same information]
+
+**Context difference:** Source has [time/medium/familiarity] → Target has [time/medium/familiarity]
+
+**Implication:** [Requires length/format/explanation level adjustment]
+
+**Cultural/Demographic difference:** Source is [demographic] → Target is [demographic]
+
+**Implication:** [Requires idiom replacement, reference changes, example adaptation]
+
+---
+
+## 2. Translation Mapping
+
+### Translation Type Classification
+
+Select primary translation type(s):
+
+- [ ] **Technical ↔ Business** (engineering details ↔ business value)
+- [ ] **Strategic ↔ Tactical** (vision/goals ↔ actions/tasks)
+- [ ] **Expert ↔ Novice** (domain jargon ↔ plain language)
+- [ ] **Formal ↔ Informal** (professional report ↔ casual communication)
+- [ ] **Long-form ↔ Summary** (comprehensive ↔ highlights)
+- [ ] **Internal ↔ External** (company context ↔ customer-facing)
+- [ ] **Cross-Cultural** (one culture/generation/industry → another)
+- [ ] **Medium Shift** (written ↔ spoken, document ↔ presentation)
+
+### Translation Strategy
+
+Based on audience gap, select strategy:
+
+**If simplifying (expert → novice, technical → business):**
+- **Remove**: [Jargon, technical details, implementation specifics, edge cases, nuance]
+- **Add**: [Definitions, analogies, "why this matters", examples, context]
+- **Shift emphasis**: [How it works → Why it matters | Metrics → Outcomes | Process → Impact]
+- **Bridge technique**: [Use familiar domain to explain unfamiliar - analogies, metaphors]
+
+**If elaborating (novice → expert, business → technical):**
+- **Remove**: [Over-explanations, basic definitions, hand-holding]
+- **Add**: [Precision, technical terms, caveats, edge cases, constraints, methodology]
+- **Shift emphasis**: [Simplified model → Accurate complexity | Outcomes → Metrics | Impact → Process]
+- **Depth technique**: [Add layers of detail, specify units/quantification, cite sources]
+
+**If changing tone (formal ↔ informal):**
+- **Formal → Informal**: Active voice, contractions, first/second person, simple language, conversational flow
+- **Informal → Formal**: Remove contractions, third person, passive where appropriate, professional terminology, structured sections
+
+**If compressing (long → summary):**
+- **Structure**: Inverted pyramid (most important first)
+- **Preserve**: Core findings, key recommendations, critical caveats, next steps
+- **Remove**: Supporting details, full context, exhaustive examples, tangents
+- **Ratio target**: [e.g., 50:1, 10:1, 3:1 depending on need]
+
+**If cross-cultural/demographic:**
+- **Replace**: Culture-specific idioms, references, examples with universal or target-culture equivalents
+- **Adapt**: Date formats, measurement units, communication norms
+- **Clarify**: Assumptions that source culture takes for granted
+
+### What Must Change
+
+| Element | Source | Target | Reason |
+|---------|--------|--------|--------|
+| **Jargon/terminology** | [Technical terms used] | [Plain language equivalent] | [Target expertise level lower] |
+| **Tone/formality** | [Current tone] | [Desired tone] | [Target audience expects X] |
+| **Emphasis** | [What's highlighted now] | [What should be highlighted] | [Target cares about Y not Z] |
+| **Length** | [Current length] | [Target length] | [Time constraints] |
+| **Structure** | [Current organization] | [Target organization] | [Medium change] |
+| **Examples/analogies** | [Current examples] | [Relatable examples for target] | [Cultural/domain difference] |
+| **Details level** | [Current depth] | [Target depth] | [Expertise gap] |
+
+### What Must Preserve (Semantic Fidelity)
+
+**Critical to maintain accuracy:**
+- Core facts: [List key facts that must remain true]
+- Relationships: [Cause-effect, dependencies, constraints that must be preserved]
+- Limitations/caveats: [Important qualifications that can't be dropped]
+- Implications: [What this means for the audience - must remain accurate]
+- Quantification: [Numbers, timelines, magnitudes - can round but not distort]
+
+**Verification test:** "Would an expert in the source domain confirm this translation is accurate?"
+
+---
+
+## 3. Translated Content
+
+### Original Content (Brief Excerpt)
+
+[Paste relevant excerpt from original, or summarize if very long]
+
+**Key points in original:**
+1. [Point 1]
+2. [Point 2]
+3. [Point 3]
+4. [Point 4]
+5. [Point 5]
+
+### Translated Version
+
+[Write full translated version here, formatted for target medium]
+
+**If target medium is email:** Use short paragraphs, bullets, bold for key points, skimmable structure.
+
+**If target medium is presentation:** Slide-friendly bullets, one main idea per slide/section, visual cues.
+
+**If target medium is document:** Clear headers, sections, reference format, comprehensive.
+
+**If target medium is conversation:** Conversational language, questions to check understanding, interactive.
+
+**Example structure for executive summary:**
+
+---
+
+**[Title - Clear, jargon-free]**
+
+**Bottom line up front (BLUF):** [1-2 sentence core message - what they need to know]
+
+**Key findings/decisions:**
+- [Point 1 - phrased for target audience with their priorities]
+- [Point 2]
+- [Point 3]
+
+**Recommendation:** [Clear action with rationale]
+
+**Next steps:** [What happens now, timeline, who's responsible]
+
+**Context (if needed):** [Brief background only if target needs it]
+
+---
+
+### Translation Diff
+
+**What changed from original:**
+
+| Aspect | Change Made | Rationale |
+|--------|-------------|-----------|
+| Jargon | [Replaced "X" with "Y"] | [Target doesn't know X, Y is familiar equivalent] |
+| Details | [Removed implementation specifics] | [Target is decision-maker, not implementer] |
+| Emphasis | [Highlighted business value over technical approach] | [Target cares about ROI, not how it works] |
+| Tone | [Changed from formal report to conversational email] | [Target prefers approachable communication] |
+| Length | [Reduced from 5 pages to 1 page] | [Target has 5 minutes, not 30 minutes] |
+| Structure | [Inverted pyramid - key finding first] | [Target may not read to end, need headline first] |
+| Examples | [Replaced code snippet with business analogy] | [Target doesn't read code, needs business framing] |
+| Cultural | [Replaced "home run" with "big win"] | [International audience, baseball reference excludes them] |
+
+**What preserved:**
+
+| Aspect | How Preserved | Verification |
+|--------|---------------|--------------|
+| Core facts | [Still states X happened on Y date with Z impact] | [Accuracy check: yes] |
+| Relationships | [Still shows A caused B, which enabled C] | [Cause-effect intact: yes] |
+| Caveats | [Still notes limitation that it only works under condition X] | [Qualification preserved: yes] |
+| Implications | [Still conveys that this means we can now do Y] | [Meaning intact: yes] |
+| Numbers | [Still cites 30% improvement, rounded from 32.7%] | [Within acceptable range: yes] |
+
+---
+
+## 4. Fidelity Validation
+
+### Validation Checks
+
+**CRITICAL - Semantic Fidelity:** "Would source domain expert confirm this is accurate?"
+- [ ] Core facts accurate (no distortions from simplification)
+- [ ] Cause-effect relationships preserved
+- [ ] Critical caveats included when relevant
+- [ ] Implications correct for target
+- [ ] No semantic drift (facts still true, just rephrased)
+
+**Audience Appropriateness:** "Would target find this clear and useful?"
+- [ ] Expertise level matched (not too technical or too simple)
+- [ ] Jargon explained when needed, avoided when unknown
+- [ ] Addresses target's primary goals (decide/implement/learn)
+- [ ] Tone appropriate for audience and context
+- [ ] Length respects time constraints
+
+**Emphasis & Medium:**
+- [ ] Leads with target's priorities (not source's)
+- [ ] Detail level right (enough to understand, not overwhelming)
+- [ ] Structure fits medium (email skimmable, doc structured, presentation visual)
+- [ ] Actionable if needed (clear next steps)
+
+**Cultural/Demographic (if applicable):**
+- [ ] Idioms/references work for target culture/generation
+- [ ] Examples relatable to target's context
+- [ ] No unstated cultural assumptions
+
+**If semantic fidelity fails:** STOP. Revise to restore accuracy before proceeding.
+
+---
+
+## 5. Delivery Package
+
+### Final Translated Content
+
+[Paste polished final version here, ready for delivery to target audience]
+
+### Translation Metadata
+
+**Translation performed:**
+- Date: [Date]
+- Source audience: [Brief characterization]
+- Target audience: [Brief characterization]
+- Translation type: [e.g., Technical → Business, Expert → Novice]
+- Primary changes: [e.g., Removed jargon, added business framing, compressed 10:1]
+
+### Translation Rationale
+
+**Why this translation approach:**
+
+[Explain the key decisions made and why - helps stakeholders understand the translation choices]
+
+**Example:**
+"Original was written for engineering team (expert audience) with deep technical detail. Translated for executive stakeholders (decision-makers) who need business implications, not implementation details. Removed technical jargon (distributed lock manager → timing issue), shifted emphasis from how it was fixed to customer impact and prevention, compressed from 3 pages to 3 paragraphs. Preserved: timeline, affected systems, root cause category, resolution confidence. Business value: Executives can quickly understand incident impact, assess risk, and approve resources for prevention—without needing to understand technical implementation."
+
+### Validation Summary
+
+**Semantic fidelity:** ✓ Core facts verified accurate by [source domain expert / self-check against rubric]
+
+**Audience match:** ✓ Tone, depth, and emphasis appropriate for [target audience characterization]
+
+**Emphasis aligned:** ✓ Highlights [key priorities for target audience]
+
+**Medium optimized:** ✓ Formatted as [target medium] with appropriate structure
+
+**Limitations/compromises:** [Note any unavoidable trade-offs, e.g., "Some technical nuance lost for brevity, but core accuracy preserved" or "Simplified causal chain for accessibility, details available in appendix"]
+
+**Minimum Standard:** Use rubric (evaluators/rubric_translation_reframing_audience_shift.json). Average score ≥ 3.5/5.
+
+---
+
+## Common Pitfalls to Avoid
+
+**Semantic drift** - Facts become inaccurate through simplification. Fix: Verify each simplification preserves truth.
+
+**Talking down** - Condescending tone to novices ("even you can understand this"). Fix: Respectful explanations.
+
+**Jargon mismatch** - Too technical for target or too vague. Fix: Define or avoid per target knowledge.
+
+**Missing "so what?"** - Technical details without business impact. Fix: Every technical detail answers "why does target care?"
+
+**Missing "how?"** - Strategic vision without tactical translation. Fix: Every goal specifies concrete actions.
+
+**Lost nuance** - Critical caveats omitted for brevity. Fix: Preserve important qualifications even in summaries.
+
+**Cultural assumptions** - Idioms or references that exclude target. Fix: Replace with universal or target-culture equivalents.
+
+**Wrong emphasis** - Highlighting what you find interesting vs. what target needs. Fix: Lead with target's priorities.
+
+**Unverified accuracy** - Assuming translation is correct without checking. Fix: Test with "would source expert confirm this?"