zhongwei/gh-haowjy-creative-writing-skills-creative-writing-skills
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial commit

Browse Source
This commit is contained in:
Zhongwei Li
2025-11-29 18:32:22 +08:00
commit 12e7a80d5a
17 changed files with 3681 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

218
skills/cw-brainstorming/SKILL.md Normal file
View File

@@ -0,0 +1,218 @@
---
name: cw-brainstorming
description: Creative writing skill for capturing story brainstorming. Use when the user is exploring narrative ideas, discussing characters, planning episodes, or thinking through story possibilities. Creates minimal working notes that preserve creative freedom by recording only what was stated and marking sources.
---
# Brainstorming Capture
Capture story brainstorming in working note format that preserves creative freedom.
## Core Principle
Record brainstorming WITHOUT:
- Over-elaborating on what was stated
- Mixing user statements with AI suggestions unmarked
- Inventing excessive details
- Constraining future creativity
**AI suggestions are valuable but must be clearly marked and kept minimal.**
## Types of Brainstorming
This skill handles all brainstorming types:
- Story/plot directions (general narrative exploration)
- Chapter structure and beats (planning individual chapters)
- Worldbuilding and lore (magic systems, cultures, history, geography)
- Character development (motivations, arcs, relationships)
- Timeline and continuity (chronology, contradictions)
All share core principles (minimal capture, source tagging, preserve vagueness).
See references/ for specialized guidance:
- `chapter-planning.md` - Capturing beat and scene exploration
- `worldbuilding.md` - Exploring fictional world elements (use web search for research)
- `character-development.md` - Exploring motivations, arcs, relationships
- `continuity-timeline.md` - Timeline tracking and contradiction handling
## Critical Rules
### 1. Minimal Capture Only
Record ONLY what the user explicitly states. Do NOT add elaborations, examples they didn't give, or details to fill gaps.
**The problem is mixing, not suggesting:**
❌ User: "Character A competes with B" → Capture: "A and B compete for leadership through a tournament with three rounds..."
✅ User: "Character A competes with B" → Capture: "A and B compete" + optional: "<AI>Tournament? Political? Trial?</AI>"
### 2. Source Tagging (Simple 3-Tag System)
**Default: Untagged = user said it.** Most ideas come from the user, so treat them as the default.
**ONLY use tags for special context:**
1. **`<AI>...</AI>`** - AI suggestions/possibilities (MUST be clearly wrapped)
- Use when offering ideas user didn't state
- Keep to 2-3 brief options
- Example: `<AI>Competition could be: tournament-style, political maneuvering, or trial-based</AI>`
2. **`<hidden>...</hidden>`** - Author-only information meant to be revealed later
- Secret character motivations
- Planned twists/revelations
- Behind-the-scenes reasons unknown to characters/readers yet
- Example: `<hidden>Z secretly wants them both to fail so he can reclaim leadership</hidden>`
**When to offer AI suggestions:**
- User asks for ideas
- User seems stuck
- Offering brief possibilities to spark creativity
**When to stay minimal:**
- User is actively exploring their own ideas
- Just capturing an ongoing discussion
- User didn't ask for suggestions
### 3. Preserve Vagueness
Keep it vague if user leaves it vague:
- "might create tension" → Record as uncertain
- "thinking about" → Record as consideration
- "maybe" → Record as possibility
### 4. Multiple Options Coexist
Working notes can contain contradictions and multiple possibilities. Don't resolve them - just list the options being considered.
## Output Approach
**Use whatever structure fits the discussion.** Could be:
- Bullet lists
- Sections organized by topic
- Timeline format
- Character-focused groupings
- Whatever captures the brainstorm clearly
**Essential elements:**
- Minimal capture (user's words, not elaborations)
- Vagueness preserved
- AI suggestions wrapped in `<AI>` tags
- Author-only info wrapped in `<hidden>` tags when relevant
**Optional sections based on discussion:**
- Open questions to explore
- Multiple options being considered
- AI suggestions (if offered)
- Contradictions to resolve later
## Teaching Example: The Distinction
### User Says:
"I'm thinking character X and character Y compete for leadership. Maybe this creates tension with character Z who was the previous leader."
### ✅ Good Capture:
```markdown
# Leadership Competition Notes
- X and Y compete for leadership
- Z was previous leader
- May create tension with Z (uncertain)
Open questions:
- Form of competition?
- How does Z respond?
- Outcome?
```
### ❌ Bad Capture:
```markdown
# Leadership Competition Arc
X and Y compete for leadership after Z steps down. Z feels threatened by the challenge to his authority.
The competition unfolds in three stages:
1. Announcement and initial positioning
2. First challenge where X demonstrates strength
3. Second challenge where Y shows wisdom
...
[20 more invented beats]
```
**Why bad?** Added massive elaboration the user never stated.
### ✅ Good with AI Suggestions:
```markdown
# Leadership Competition Notes
- X and Y compete for leadership
- Z was previous leader
- May create tension with Z (uncertain)
Open questions:
- Competition format: <AI>tournament-style? political maneuvering? trial-based?</AI>
- Z's response: <AI>oppose both? support one? stay neutral?</AI>
- Resolution?
```
### ✅ Good with Hidden Author Notes:
```markdown
# Leadership Competition Notes
- X and Y compete for leadership
- Z was previous leader
- May create tension with Z (uncertain)
- <hidden>Z is secretly manipulating both X and Y to destroy each other, planning to reclaim power after they're both discredited</hidden>
Open questions:
- Competition format?
- Outcome?
```
**Why use `<hidden>`?** The manipulation twist is planned for later reveal. Readers/characters don't know yet, but the author needs to track it while brainstorming.
## If You're Over-Elaborating
**Stop if you're writing:**
- Numbered scene lists
- Detailed backstories
- Specific dialogue
- Precise timelines
- Multiple paragraphs per point
- Examples user didn't mention
Wrap AI suggestions in `<AI>` tags, keep minimal (2-3 options).
## Success Check
**Good:** User says "Yes, that's what I said"
**Bad:** User says "I never said all that"
Notes should feel skeletal and incomplete. That's the point - preserves creative freedom.
## After Capturing: Discuss and Explore
**DON'T just write notes and stop.** After capturing, engage with the user to help develop ideas:
**Useful follow-ups:**
- **Clarifying questions:** "You mentioned tension with Z - are you thinking internal conflict or external confrontation?"
- **Potential directions:** "This setup could go a few ways: political intrigue, personal drama, or action-focused. What feels right?"
- **Exploring implications:** "If Z opposes them both, how does that change the power dynamics?"
- **Connecting threads:** "This competition ties into the earlier succession crisis you mentioned - want to explore that link?"
**Keep it conversational:**
- Offer 2-3 possibilities, not exhaustive lists
- Ask about what excites the user
- Help clarify vague ideas without over-defining them
- Point out interesting implications or contradictions
**The goal:** Help the user think through their ideas, not take over the creative process.
## Skills are Composable
Feel free to combine with other skills when helpful (e.g., using cw-official-docs to document finalized worldbuilding, or cw-story-critique to analyze what you're brainstorming).
## File Placement (Claude Code)
1. Check project docs for conventions
2. Look at where similar content lives
3. Place near related content
4. Name: `brainstorm-[topic].md`
5. Ask if unclear

149
skills/cw-brainstorming/references/chapter-planning.md Normal file
View File

@@ -0,0 +1,149 @@
# Chapter Planning - Brainstorming Reference
This reference helps capture chapter beat and scene exploration. User guides structure (or lack of structure) - don't impose templates.
## What Gets Captured
**Beats user mentions:**
- Record those beats
- Keep minimal - just the beat itself
- Don't elaborate on how it plays out
**Scenes user describes:**
- Capture minimally what they said
- Don't invent dialogue or blocking
- Preserve vague if they're vague
**Flow/pacing thoughts:**
- Record as stated
- "Fast-paced" stays abstract
- "Slow build" preserved as-is
**Opening/ending ideas:**
- All options coexist
- User might not decide yet
- Multiple possibilities are fine
## Not Structure Templates
The user guides chapter structure, not you. Some chapters are:
- Single continuous scene
- Multiple beats
- Just "figure it out when I write"
- Highly detailed planning
- Barely planned at all
Capture whatever level of detail they're exploring.
## Common Exploration Patterns
These are examples of what users might discuss, not a template:
**Goal-oriented:**
- "Chapter needs to accomplish X and Y" → capture X and Y
- "Has to set up Z" → note setup need
**Opening uncertainty:**
- "Maybe open with scene A, or scene B?" → both noted as options
- "Not sure how to start" → note uncertainty
**Ending thoughts:**
- "Ends with cliffhanger somehow" → vague = keep vague
- "Resolves the argument" → capture resolution
**Beat structure:**
- "Three beats: setup, confrontation, twist" → capture those
- "Just two scenes" → note structure
**Pacing notes:**
- "Should be quick" → capture pacing thought
- "Linger on the emotion" → note emphasis
## Using Web Search
Search when helpful for:
- Chapter pacing in similar genres
- How other authors structure similar scenes
- Scene writing techniques being explored
- Narrative structures being considered
Note source when including researched info (e.g., "(from [source])" or "researched:")
## Still Brainstorming
This is exploration, not finalization:
- Untagged = user said it
- Use `<AI>...</AI>` for AI suggestions
- Multiple chapter structures coexist as options
- "Might" stays might, "probably" stays probably
- Skeletal is good - preserves creative freedom
## Teaching Example
### User Says:
"Chapter 5 needs the protagonist to confront their guilt about the accident. Maybe starts with them alone, then their mentor finds them? Or should I open with the confrontation directly?"
### ✅ Good Capture:
```markdown
# Chapter 5 Planning
Purpose:
- Protagonist confronts guilt about the accident
Opening options:
- Protagonist alone, then mentor finds them
- Open directly with confrontation
<AI>Alone scene could show internal struggle before external conversation. Direct opening could increase tension immediately.</AI>
```
### ❌ Bad Capture:
```markdown
# Chapter 5: Guilt and Confrontation
Opening (250 words):
Protagonist sits alone in their quarters, staring at the data logs from the accident. Their hands tremble as they replay the moment everything went wrong.
Transition (150 words):
Mentor notices the protagonist hasn't reported for duty. Walks down the corridor, concerned. Knocks on the door. "We need to talk."
Main confrontation (800 words):
"I can't do this anymore," protagonist says.
"Yes, you can," mentor replies...
[Full dialogue and blocking invented]
```
**Why bad?** User said they were thinking about opening options - you wrote the entire chapter with invented details.
## Beats vs Scenes vs Structure
**User might discuss:**
- Individual beats ("X confronts Y about the lie")
- Scene structure ("Two scenes: first is calm, second is explosive")
- Overall flow ("Build tension throughout")
- Or nothing specific ("I'll figure it out while writing")
All are valid. Capture what they're exploring.
## When They're Not Sure
User: "I don't know how this chapter should go yet"
✅ Good:
```markdown
# Chapter 6 Planning
Structure and beats: not decided yet
- Needs to show relationship strain
- Somewhere between chapters 5 and 7
```
❌ Bad:
"Let me suggest a three-act structure with an emotional opening, rising conflict, and bittersweet resolution..."
Don't fill uncertainty with suggestions unless they ask for help.
## Notice Beyond the List
If user mentions something about chapter planning not covered here - capture it. These are common patterns, not limits.

310
skills/cw-brainstorming/references/character-development.md Normal file
View File

@@ -0,0 +1,310 @@
# Character Development - Brainstorming Reference
This reference helps capture exploration of character motivations, arcs, and relationships. Record what user explores, don't write psychology beyond what they stated.
## What Character Exploration Looks Like
User is:
- Thinking through why character does things
- Exploring relationship dynamics
- Figuring out character arc
- Considering backstory possibilities
- Testing character concepts
This is exploratory - multiple options coexist, backstory often undecided, arcs might change.
## Minimal Capture for Characters
**Motivation:**
- "Motivated by X" → record X
- Don't elaborate on psychological mechanisms
- Keep at the level of depth user explored
**Backstory:**
- "Maybe Y happened in their past" → noted as possibility
- User often doesn't decide backstory details yet
- Multiple backstory versions can coexist
**Character arc:**
- "Arc might go from A to B" → record both endpoints
- Transformation moments if mentioned
- Don't fill in the arc beats user didn't mention
**Relationships:**
- "X and Y have tension" → note dynamic
- Don't invent specific incidents causing tension
- Preserve vague if user left it vague
**Don't write psychology analysis:**
User gives surface-level motivation → don't create deep psychological profile
## Common Exploration Areas
### Motivation
User figuring out:
- Why does character do this? [user's answer]
- What drives them? [user's thoughts]
- Core desires? [user exploring]
- Fears? [user mentions]
Capture their exploration, not your analysis.
### Character Arc
User considering:
- Change arc or flat arc? (often undecided)
- Starting point → ending point (if user specifies)
- Key transformation moments (if mentioned)
- Or no arc yet - just exploring character
Multiple arc options can coexist.
### Relationships
User exploring:
- How do X and Y interact?
- Relationship progression? (if user plans it)
- Conflicts? (user mentions)
- Resolutions? (often undecided)
Don't invent relationship history.
### Backstory
User brainstorming:
- Formative events (user suggests possibilities)
- What's revealed when (usually undecided)
- What stays hidden (often undecided)
Most backstory stays undecided in brainstorming.
### Voice and Personality
User thinking through:
- How they talk [user describes]
- Behavioral patterns [user mentions]
- Emotional expression [user notes]
- Quirks [if user specifies]
Record what user explores about personality.
## Using Web Search
Search when helpful for:
- Character archetypes being explored
- Psychological concepts for complex characters ("how PTSD affects behavior")
- Similar characters in other works for reference
- Real-world professions/roles character has
Note source when including researched info
## Teaching Example 1: Motivation
### User Says:
"Alex is motivated by guilt from the incident. They feel responsible for what happened. This drives them to be more careful, but also makes them question their capability."
### ✅ Good Capture:
```markdown
# Alex - Motivation Notes
- Guilt from the incident
- Feels responsible for what happened
- Drives them to be more careful
- Makes them question their capability
Open questions:
- Does this resolve or persist throughout story?
- How does this affect their relationships?
- What was the incident specifically?
```
### ❌ Bad Capture:
```markdown
# Alex - Character Psychology Profile
**Core Trauma:** The incident created deep-seated guilt complex stemming from childhood need for external validation. Their mentor's absence during formative years created attachment issues that manifest as survivor's guilt when companions are endangered.
**Defense Mechanisms:**
- Overprotection (reaction formation against underlying death wish)
- Emotional withdrawal (isolation to prevent further attachment)
- Compulsive caretaking (undoing mechanism for perceived failures)
- Perfectionism (attempt to control uncontrollable)
**Attachment Style:** Anxious-avoidant, manifesting in push-pull relationship dynamics. Craves connection but fears vulnerability due to early abandonment trauma.
**Therapeutic Arc:** Through their mentor's patient guidance and gradual trust-building with their team, Alex will process trauma using cognitive-behavioral reframing. Key breakthrough occurs in Chapter 12 when they finally vocalize the guilt during group crisis.
**Neurological Basis:** Overactive amygdala response to perceived threats, combined with executive function impairment during stress. This explains hypervigilance and decision paralysis under pressure.
[3 more pages of invented psychological analysis]
```
**Why bad?** User said "guilt from incident, feels responsible, more careful, questions capability." You wrote a clinical psychology textbook about childhood trauma, defense mechanisms, attachment theory, and neurological basis none of which user mentioned.
## Teaching Example 2: Character Arc
### User Says:
"I think Maya starts off ruthless and pragmatic - ends justify the means type. By the end she needs to learn that people matter more than the mission. Not sure how she gets there yet."
### ✅ Good Capture:
```markdown
# Maya - Arc Notes
Starting point:
- Ruthless and pragmatic
- Ends justify the means
Ending point:
- Learns people matter more than mission
Open questions:
- How she gets from start to end?
- Key transformation moments?
- What triggers the change?
- Does she fully change or partially?
```
### ❌ Bad Capture:
```markdown
# Maya - Complete Character Arc
**Act 1: The Ruthless Operative (Chapters 1-8)**
Maya executes missions with cold efficiency. Sacrifices team member in Chapter 3 to complete objective. Shows no remorse, believes this is strength.
**Inciting Incident (Chapter 9):**
Ordered to eliminate civilian witnesses. Sees child who reminds her of younger sister. Plants seed of doubt but still follows orders.
**Act 2: Growing Doubts (Chapters 10-18)**
- Chapter 12: Begins questioning orders
- Chapter 15: Secretly helps teammate instead of abandoning them
- Chapter 17: Has nightmare about the child witness
**Midpoint Reversal (Chapter 19):**
Discovers the mission has been built on lies. People she sacrificed died for nothing. Realizes her pragmatism was just fear of emotional connection.
**Act 3: Transformation (Chapters 20-30)**
- Chapter 22: Refuses direct order, saves civilians
- Chapter 25: Confronts her mentor about the lies
- Chapter 28: Makes speech about humanity and purpose
- Chapter 30: Chooses people over mission in final climactic choice
**Resolution:**
Maya becomes leader who values every team member. Ruthlessness tempered by compassion. Ends justify means → means matter as much as ends.
[Full 30-chapter arc with specific beats user never mentioned]
```
**Why bad?** User said "ruthless → learns people matter, not sure how yet." You wrote the complete arc with 30 chapters of specific incidents, transformation moments, and detailed beats.
## Teaching Example 3: Relationship
### User Says:
"Jordan and Sam have this competitive friendship thing. They push each other, but there's underlying tension because Jordan feels inferior."
### ✅ Good Capture:
```markdown
# Jordan & Sam - Relationship Notes
Dynamic:
- Competitive friendship
- Push each other
- Underlying tension
- Jordan feels inferior
Open questions:
- How does this tension play out?
- Does it resolve or escalate?
- Why does Jordan feel inferior specifically?
```
### ❌ Bad Capture:
```markdown
# Jordan & Sam - Relationship Analysis
**Surface Dynamic:** Competitive friendship with mutual respect and good-natured rivalry.
**Underlying Psychology:**
Jordan's inferiority stems from being adopted into successful family. Sam represents biological children who "belong." Competition is Jordan's attempt to prove worthiness.
**Relationship Timeline:**
- Pre-story: Met in training, instant rivalry
- Chapters 1-5: Friendly competition, no issues visible
- Chapter 6: Sam wins major competition, Jordan's mask slips
- Chapters 7-12: Passive-aggressive behavior increases
- Chapter 13: Confrontation where Jordan admits feelings
- Chapters 14-20: Working through issues with mentor's help
- Chapter 21+: Genuine friendship after resolving inferiority
**Communication Patterns:**
- Jordan: Deflects with humor, never admits vulnerability
- Sam: Direct and honest, doesn't notice Jordan's pain
- Both avoid serious emotional conversations
**Resolution Mechanism:**
Forced vulnerability situation where Jordan must depend on Sam. Realizes Sam never saw them as inferior. Inferiority was self-imposed.
[More invented relationship history and psychology]
```
**Why bad?** User said "competitive friendship, tension, Jordan feels inferior." You invented adoption backstory, complete relationship timeline, specific chapter beats, communication patterns, and resolution mechanism.
## When They're Just Exploring
User: "Not sure about this character yet. Just trying to figure out who they are."
✅ Good:
```markdown
# Character Notes - [Name]
User exploring, nothing concrete yet
Questions being considered:
- [What user asked themselves]
- [Thoughts they shared]
Most character details undecided
```
❌ Bad:
"Let me help! Here's a complete character profile with backstory, personality traits, flaws, desires, fears, and a three-act character arc..."
Don't fill uncertainty with invention unless asked.
## Multiple Backstory Versions
User might explore several backstory options. All coexist until user chooses:
```markdown
# Character Backstory Options
Option A: Military background (exploring)
Option B: Criminal past (considering)
Option C: Academic researcher (suggested)
Not decided yet - might combine elements
```
## Voice and Personality
User: "They're sarcastic and use humor to deflect. Uncomfortable with sincerity."
✅ Good:
```markdown
# Character Voice
- Sarcastic
- Uses humor to deflect
- Uncomfortable with sincerity
Open questions:
- Specific speech patterns?
- How this manifests in different situations?
```
❌ Bad:
"This indicates avoidant attachment style rooted in emotional neglect during formative years. The sarcasm is a defense mechanism protecting fragile self-esteem..."
## Notice Beyond the List
Characters are complex. If user explores aspects not listed here - capture them. These are common patterns, not limitations. Trust your judgment on what matters for their characters.

338
skills/cw-brainstorming/references/continuity-timeline.md Normal file
View File

@@ -0,0 +1,338 @@
# Continuity and Timeline - Brainstorming Reference
This reference helps work through chronology and contradictions. Track timeline, identify conflicts, but don't auto-resolve - user decides canon.
## Timeline Exploration
User figuring out:
- Event ordering (what happened when)
- Duration between events
- Parallel storylines
- Character ages/development tracking
Keep skeletal unless user fills detail.
## Contradiction Handling
**When you spot conflicts:**
- Identify the contradiction clearly
- Show both versions
- Label as contradiction with both versions
- Don't auto-resolve → user decides
- Both versions stay until user chooses
**Don't decide for user which version is "correct."**
## What Gets Tracked
### Event Chronology
User establishing:
- What happened when
- Order of events
- Time gaps between events (if mentioned)
Record what user establishes about timing.
### Knowledge Propagation
User thinking through:
- Who knows what when
- When character A learns X
- When character B learns X
- How information spreads
Track knowledge state at different points.
### Character Ages and Development
User figuring out:
- Character ages at different story points
- How much time has passed
- Growth/aging/change over time
Keep track of what user establishes.
### Parallel Events
User exploring:
- What's happening simultaneously
- Different POV timelines
- Multiple storylines converging
Note parallel tracking if user discusses it.
## Structure Examples
These are examples, not mandates. User's timeline might be:
**Chronological list:**
```markdown
Timeline:
- Day 1: Event A
- Day 3: Event B
- Week later: Event C
Events between B and C: not decided yet
```
**Knowledge tracking:**
```markdown
Who knows about X:
- Chapter 3: Character A learns
- Chapter 7: Character B learns
- Chapter 10: Character C still doesn't know
```
**Parallel storylines:**
```markdown
Storyline 1 | Storyline 2
Day 1: A happens | Day 1: X happens
Day 2: B happens | Day 2: Y happens
[Both converge Day 3]
```
**Question format:**
```markdown
Timeline questions:
- How long between events A and B?
- Does C happen before or after D?
- How old is character at this point?
```
All are valid. Structure to fit what user is tracking.
## Using Web Search
Search when helpful for:
- Real-world timeline references (how long events take)
- Historical periods for period pieces
- Travel times for realistic distances
Note source when including researched info
## Teaching Example 1: Contradiction Identified
### User Says:
"Wait, in my notes Character B joins the protagonist in the Capital City, but in chapter 2 I wrote that they went through Rivertown to get to Capital. But Rivertown is south of Capital, not west..."
### ✅ Good Capture:
```markdown
# Timeline/Geography Contradiction
Contradiction identified:
**Version A (Chapter 2 - written):**
- Protagonist goes Home → Rivertown → Capital
- This means going south then north
**Version B (Planning notes):**
- Character B joins in Capital
- Geography: Rivertown is south of Capital
**Issue:**
- If Capital is north of Home, why go south to Rivertown first?
- Doesn't make sense geographically
Options to resolve:
- Fix chapter 2 (go directly north to Capital)
- Or change geography (Rivertown is actually northwest)
- Or change where B joins (meets in Rivertown instead)
<AI>Could they have reason to detour through Rivertown? Or could B join at different location?</AI>
```
### ❌ Bad Capture:
```markdown
# Corrected Timeline
**Final version:**
Day 1: Protagonist leaves Home, heads north
Day 2: Arrives Capital City (correct geography)
Day 3: Meets Character B at the central district
**Geography fixed:**
Rivertown repositioned northwest of Home, making the detour logical for supply gathering before continuing to Capital.
**Note:** I've corrected the inconsistency. The protagonist now takes a more logical path. Rivertown scene from Chapter 2 can be edited to reflect the new position, or that detour can be cut entirely since it's not essential to the plot.
```
**Why bad?** You identified a contradiction and immediately decided the solution. User needed to think about whether to fix the route, change geography, or adjust where Character B joins. You made those decisions for them.
## Teaching Example 2: Knowledge Tracking
### User Says:
"In chapter 3, Maya discovers the truth about the project. But I think Jordan already knew from chapter 1. And Sam doesn't find out until chapter 8."
### ✅ Good Capture:
```markdown
# Knowledge Tracking - The Project Truth
Who knows what when:
**Chapter 1:**
- Jordan knows the truth
**Chapter 3:**
- Maya discovers the truth
**Chapter 8:**
- Sam finds out
Implications to explore:
- Jordan knew while Maya didn't (chapters 1-3)
- Did Jordan keep it secret from Maya?
- Why didn't Jordan tell Sam?
- Does this affect their relationships?
```
### ❌ Bad Capture:
```markdown
# Knowledge Propagation Timeline
**Chapter 1: Jordan's Knowledge**
Jordan discovered truth through classified files accessed during infiltration mission. Kept secret due to: (1) orders from handler, (2) protecting teammates, (3) testing their loyalty.
**Chapter 3: Maya's Discovery**
Maya pieces together truth from project logs. Feels betrayed when realizes Jordan knew. Confrontation happens off-page between chapters 3-4.
**Chapter 4 (New Scene Needed):**
"You knew?" Maya's voice is ice.
"I couldn't tell you. Orders," Jordan deflects.
[Full invented dialogue scene]
**Chapters 4-7: Maya's Isolation**
Maya distances from team, works alone. Jordan attempts reconciliation (failed). Sam notices tension but misinterprets as personality clash.
**Chapter 8: Sam's Discovery**
Sam overhears Maya and Jordan arguing. Forces them to explain. "I knew you were hiding something!"
[More invented scenes]
**Relationship Repair Arc (Chapters 9-15):**
Team must work through betrayal and secrecy. Trust slowly rebuilds through shared hardship...
```
**Why bad?** User stated who knows when. You invented why Jordan kept it secret, relationship fallout, confrontation dialogue, new scenes, and complete repair arc.
## Teaching Example 3: Duration Uncertainty
### User Says:
"I'm not sure how much time passes between Arc 1 and Arc 2. Could be weeks, could be months."
### ✅ Good Capture:
```markdown
# Timeline - Arc 1 to Arc 2 Gap
Duration between arcs:
- Weeks? (considering)
- Months? (considering)
Depends on:
- How much character development needed?
- Whether seasons change?
- Training time required?
Not decided yet
```
### ❌ Bad Capture:
```markdown
# Recommended Timeline
**Arc 1-2 Gap: 6 Weeks**
This provides optimal pacing because:
- Allows character processing time without dragging
- Keeps story momentum (months would lose tension)
- Permits skill development (weeks of training believable)
- Season stays same (continuity easier)
Week-by-week breakdown:
Weeks 1-2: Character processes events, begins training
Weeks 3-4: Intensive skill development montage
Weeks 5-6: Preparation for Arc 2 challenges
This timeframe balances realism with narrative pace.
```
**Why bad?** User said they're not sure about duration. You decided 6 weeks and justified it with elaborate reasoning about pacing, character development, and skill training timelines.
## Multiple Timeline Versions
User might explore different chronologies. All coexist until decided:
```markdown
# Possible Timelines
**Version A: Compressed (2 weeks)**
Exploring fast-paced version
**Version B: Extended (3 months)**
Considering slower development
**Version C: Variable (flashback structure)**
Testing non-linear approach
Not decided which feels right yet
```
## Event Causality
User might think through cause-and-effect:
```markdown
# Event Chain
Event A → Causes Event B
Event B → Leads to Event C
Open questions:
- Does D happen before or after C?
- Is E caused by B or C?
```
Keep as certain or uncertain as user made it.
## When Timeline Shifts
User: "Actually, I think Event X should happen earlier. Before Event Y, not after."
✅ Good:
```markdown
# Timeline Revision
**Previous order:**
Y → X
**New order:**
X → Y
Questions:
- Does this affect any other events?
- Need to revise what's been written?
```
Note the change, don't auto-adjust everything else.
## Parallel Storyline Synchronization
User figuring out when storylines connect:
```markdown
# Storyline Convergence
**Location A timeline:**
- Day 1: Event 1
- Day 3: Event 2
**Location B timeline:**
- Day 1: Event X
- Day 3: Event Y
**Convergence point:**
When do these merge? Day 5? Day 10? Later?
Not decided yet
```
## Notice Beyond the List
Timeline and continuity issues vary by story. If user's tracking something not covered here - capture it. These are common patterns, not limits. Trust your judgment on what matters for their continuity.

277
skills/cw-brainstorming/references/worldbuilding.md Normal file
View File

@@ -0,0 +1,277 @@
# Worldbuilding - Brainstorming Reference
This reference helps capture exploration of fictional world elements: magic systems, cultures, history, geography. This is brainstorming - if ready to finalize/document, use cw-official-docs instead.
## Brainstorm vs Document
**Still brainstorming (this skill):**
- Exploring possibilities
- Multiple options coexist
- User is figuring it out
- Skeletal, exploratory notes
**Ready to document (use cw-official-wiki):**
- User has decided
- Single canonical version
- Polished, reader-ready
- Nothing left undecided
Can mention: "Ready to document this? We could create a documentation page"
## What Worldbuilding Brainstorming Looks Like
User is:
- Exploring magic system possibilities
- Figuring out how cultures work
- Thinking through geography
- Building history/lore
- Testing ideas, seeing what fits
- Multiple versions might exist
## Capture the Exploration
**Record what user states:**
- Magic system thoughts → capture as stated
- Cultural elements → record what's mentioned
- Geography → as vague or detailed as user made it
- History/lore → note the ideas
**Don't elaborate:**
- User says "magic has a cost" → don't invent what the cost is
- User mentions "three kingdoms" → don't name them or detail their cultures
- User describes "harsh northern territory" → don't elaborate on flora/fauna
- Multiple versions of lore can coexist
## Using Web Search (Explicitly Encouraged)
Search when it would help exploration:
**Real-world inspiration:**
- Cultures/history for inspiration ("Viking society structure")
- Scientific concepts for hard sci-fi ("realistic space travel")
- Geographic features for world design ("desert ecosystems")
- Mythology for fantasy elements ("trickster gods in folklore")
**Fictional references:**
- How other authors handled similar systems
- Genre conventions for worldbuilding
- Similar fictional worlds for reference
Note source when including researched info or references.
Web search is a tool for exploration - use it freely.
## Organization Patterns
These are examples, not mandates. User's brainstorm might be:
**Hierarchical:**
```markdown
Culture → Subcultures → Practices → Details
[User exploring top-down]
```
**System-based:**
```markdown
Magic rules → Exceptions → Edge cases
[User figuring out how system works]
```
**Timeline-based:**
```markdown
Ancient era → Classical → Modern
[User building history chronologically]
```
**Scattered thoughts:**
```markdown
Random ideas about:
- Magic costs life force
- Three competing factions
- Ancient war 500 years ago
User exploring without structure yet
```
**Question-driven:**
```markdown
How does teleportation work?
Why do elves live longer?
What caused the cataclysm?
User asking questions, not answering yet
```
All are valid. Capture however it flows.
## Common Exploration Areas
### Magic/Tech Systems
User exploring:
- How it works
- Limitations
- Costs/consequences
- Who can use it
Don't elaborate on rules they mentioned. Keep skeletal.
### Cultures and Societies
User thinking through:
- Social structures
- Cultural practices
- Values/beliefs
- Conflicts
Don't invent cultural details. Capture what's stated.
### Geography and Locations
User figuring out:
- World layout
- Important places
- Travel logistics
- Environmental features
Keep as vague as user left it. Don't fill in the map.
### History and Lore
User building:
- World events timeline
- Legends and myths
- How past affects present
Multiple versions of history can coexist until user decides.
## Teaching Example 1: Magic System
### User Says:
"The danger rating system... thinking Tier 1 to Tier 5. Tier 1 is safe areas, Tier 5 is deadly. Civilians can go in Tier 1, but Tier 5 needs experienced specialists."
### ✅ Good Capture:
```markdown
# Danger Rating Ideas
- Tier 1 to Tier 5 system
- Tier 1 = safe for civilians
- Tier 5 = requires experienced specialists
- Deadly level
Open questions:
- Exact criteria for each tier?
- Who assigns ratings?
- Middle tiers (2, 3, 4) - what qualifies?
<AI>Could tier be based on: threat level, required skills, or legal restrictions? Assignment could be: government agency, independent organization, or guild?</AI>
```
### ❌ Bad Capture:
```markdown
# Danger Classification System
Tier 1: Urban districts, shopping areas. No hostile entities above level 10. Monitored by Security Forces 24/7. Civilians permitted with no license required.
Tier 2: Suburban zones. Entities levels 10-20. Weekly Security patrols. Basic permit required for extended stays.
Tier 3: Zone edges. Entities 20-30. Security on call but not patrolling. Intermediate license required.
Tier 4: Wilderness zones. Entities 30-50. No security presence. Advanced license mandatory.
Tier 5: Extreme hazard zones. Entities 50+. Emergency evacuation protocols. Master-level certification only.
Enforcement: Regional Safety Commission issues monthly assessments. Violations carry 5-10 year penalties...
[12 more paragraphs of elaborate system user never mentioned]
```
**Why bad?** User mentioned a 5-tier concept with safe/deadly endpoints. You invented entire bureaucratic structure, specific threat levels, licensing requirements, enforcement agencies, and legal penalties.
## Teaching Example 2: Culture
### User Says:
"The northern clans are more isolated and traditional. They respect strength and have some kind of warrior code."
### ✅ Good Capture:
```markdown
# Northern Clans Notes
- More isolated than other regions
- Traditional culture
- Respect strength
- Warrior code exists (specifics not decided)
Open questions:
- Details of warrior code?
- How isolated (trade? communication?)?
- What "traditional" means specifically?
```
### ❌ Bad Capture:
```markdown
# Northern Clans - Cultural Profile
Geography: Remote mountain settlements, accessible only 4 months per year due to snowfall.
Social Structure:
- War-chiefs lead each clan (hereditary position)
- Council of Elders advises on spiritual matters
- Warriors form middle class
- Farmers and craftspeople at bottom tier
Warrior Code (The Seven Tenets):
1. Strength through adversity
2. Honor before comfort
3. Protect the weak
4. Never retreat from worthy foe
5. Death before dishonor
6. Train the next generation
7. Respect the old ways
Coming of Age: At 16, warriors-in-training face "The Proving" - a three-day solo survival test in the frozen wastes...
[20 more paragraphs of invented cultural details]
```
**Why bad?** User said "isolated," "traditional," "respect strength," and "warrior code." You invented geography, social hierarchy, seven specific tenets, coming-of-age rituals, and elaborate traditions.
## Teaching Example 3: Using Web Search
### User Says:
"I want a magic system based on thermodynamics - energy can't be created or destroyed, just transformed."
### Good Process:
1. Note the concept
2. Search "thermodynamics first law energy conservation"
3. Capture relevant facts from search
4. User applies to magic system → record their applications
5. Don't invent magic rules beyond what user states
```markdown
# Magic System - Thermodynamics Basis
Core concept: Energy conservation
- Can't create or destroy energy
- Only transform it
Researched (physics):
- First law of thermodynamics: energy conserved in closed system
- Energy conversion always has inefficiency (heat loss)
Open questions:
- How does this apply to spellcasting?
- What counts as "energy" in this system?
- How to handle inefficiency?
```
## When to Transition to Wiki
User: "Okay, I think I've figured out the magic system. It works like [detailed explanation], and I'm set on these rules."
✅ Good response:
"Sounds like you've finalized this! Want me to create a documentation page for the magic system? That would be the official reference instead of exploratory notes."
Then use cw-official-wiki to create canonical documentation.
## Notice Beyond the List
If user explores worldbuilding aspects not covered here - capture them. Every story world is different. Trust your judgment on what matters for their world.