Initial commit

skills/identity-resolution/SKILL.md

@@ -0,0 +1,31 @@
+---
+name: identity-resolution
+description: Use to match accounts, contacts, and opportunities across enrichment
+  sources with governed rules.
+---
+
+# Identity Resolution Playbook Skill
+
+## When to Use
+- Normalizing provider outputs before syncing to CRM/CDP.
+- Tying intent, enrichment, and product telemetry to the same account/contact IDs.
+- Diagnosing duplicate or conflicting records in downstream systems.
+
+## Framework
+1. **Key Hierarchy** – define primary/secondary keys (domain, account_id, email, person_id).
+2. **Matching Logic** – configure deterministic and fuzzy rules, tie-breakers, and confidence scoring.
+3. **Conflict Handling** – specify precedence rules, merge policies, and exception queues.
+4. **Governance** – document owners, change control, and monitoring cadence.
+5. **Audit Trail** – capture lineage metadata, before/after snapshots, and rollback steps.
+
+## Templates
+- Matching rule matrix (field, rule type, weight, confidence threshold).
+- Exception queue workflow with owners + SLAs.
+- Audit workbook for sampling matches vs source-of-truth.
+
+## Tips
+- Start with deterministic keys (domain, CRM ID) before fuzzy logic to reduce noise.
+- Version rules so downstream teams know when behavior changes.
+- Pair with `signal-taxonomy` to keep IDs aligned with schema updates.
+
+---

skills/provider-scorecard/SKILL.md

@@ -0,0 +1,31 @@
+---
+name: provider-scorecard
+description: Use to track enrichment provider success, cost, latency, and quality
+  trends.
+---
+
+# Provider Scorecard Skill
+
+## When to Use
+- Monthly/weekly ops reviews of enrichment vendors.
+- Before renewing contracts or adjusting credit allocations.
+- After outages or performance regressions to inform routing changes.
+
+## Framework
+1. **Metric Definition** – success rate, fill %, latency, credit burn, confidence.
+2. **Data Sources** – provider logs, credit usage tables, QA samples, incident tickets.
+3. **Scoring Model** – weight metrics by enrichment type and business priority.
+4. **Visualization** – dashboard or memo highlighting leaders/laggards.
+5. **Action Tracker** – document optimization experiments and owner assignments.
+
+## Templates
+- Scorecard table per provider.
+- Executive summary slide with top takeaways.
+- Jira/Asana template for provider improvement tasks.
+
+## Tips
+- Normalize metrics per enrichment type to avoid unfair comparisons.
+- Capture qualitative notes (support responsiveness, roadmap access).
+- Pair with `waterfall-blueprint` updates to reflect routing decisions.
+
+---

skills/signal-taxonomy/SKILL.md

@@ -0,0 +1,31 @@
+---
+name: signal-taxonomy
+description: Use to define schemas, topic tags, and lineage metadata for enriched
+  signals.
+---
+
+# Signal Taxonomy Skill
+
+## When to Use
+- Normalizing multiple provider outputs into a unified schema.
+- Rolling out new intent topics, enrichment attributes, or scoring dimensions.
+- Auditing lineage + compliance requirements.
+
+## Framework
+1. **Schema Definition** – fields, datatypes, required/optional flags.
+2. **Topic & Attribute Mapping** – align provider-specific attributes to canonical names.
+3. **Versioning** – maintain change logs, effective dates, and migration steps.
+4. **Validation Rules** – min/max values, allowed lists, dependency rules.
+5. **Documentation** – publish data dictionary + lineage diagrams.
+
+## Templates
+- Data dictionary sheet (field, description, source, owner).
+- Topic mapping table by provider.
+- Migration checklist for schema changes.
+
+## Tips
+- Keep names human-readable for GTM teams but consistent with data warehouse standards.
+- Tag every field with owner + refresh cadence.
+- Pair with `identity-resolution` to ensure IDs and linkages stay consistent.
+
+---

skills/validation-rulebook/SKILL.md

@@ -0,0 +1,31 @@
+---
+name: validation-rulebook
+description: Use to define validation, freshness, and compliance checks for enriched
+  data.
+---
+
+# Validation Rulebook Skill
+
+## When to Use
+- Running QA before syncing enrichment outputs to GTM systems.
+- Auditing providers after schema changes or outages.
+- Documenting compliance-ready validation procedures.
+
+## Framework
+1. **Rule Catalog** – list required fields, regex patterns, allowed values, and dependencies.
+2. **Freshness Thresholds** – define time-based SLAs per signal type.
+3. **Confidence Scoring** – set weighting for provider, validation method, and history.
+4. **Exception Handling** – create workflows for quarantining, reprocessing, or escalation.
+5. **Compliance Hooks** – log approvals, data residency tags, and retention policies.
+
+## Templates
+- Rule table (field, check, threshold, severity, owner).
+- QA runbook with pre/post sync steps.
+- Compliance audit packet ready for legal/infosec reviews.
+
+## Tips
+- Automate as many rules as possible but keep manual sampling for high-impact signals.
+- Version rules alongside taxonomy updates.
+- Pair with `data-quality-steward` outputs for sign-off history.
+
+---

skills/waterfall-blueprint/SKILL.md

@@ -0,0 +1,31 @@
+---
+name: waterfall-blueprint
+description: Use to design provider sequences, throttling logic, and credit policies
+  for enrichment waterfalls.
+---
+
+# Waterfall Blueprint Skill
+
+## When to Use
+- Building contact/company enrichment workflows across multiple providers.
+- Updating fallback rules after provider outages or cost shifts.
+- Documenting waterfall logic for RevOps + engineering handoffs.
+
+## Framework
+1. **Goal & Constraints** – define enrichment type, data requirements, credit ceiling, SLA.
+2. **Provider Catalog** – list eligible providers with success %, latency, compliance notes.
+3. **Routing Logic** – determine sequence, branching, and retry intervals.
+4. **Safeguards** – set throttles, dedupe checks, and exception triggers.
+5. **Versioning** – log changes, approvals, and effective dates.
+
+## Templates
+- Waterfall diagram (sequence, inputs, outputs, fallback paths).
+- Routing table (provider, criteria, cost, notes).
+- Change log with owners + rationale.
+
+## Tips
+- Keep sequences short for real-time use cases; reserve long chains for batch mode.
+- Use A/B tests to validate new providers before full rollout.
+- Pair with `provider-scorecard` to continuously optimize routing.
+
+---