provenance-audit
AI generation provenance and audit trail tracking. Records decision factors, data lineage, reasoning chains, confidence scoring, and cost tracking for AI-generated content.
npx skills add majiayu000/claude-skill-registry --skill provenance-audit --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# AI Provenance & Audit Trail Complete provenance tracking for AI-generated content with decision factors, data lineage, and cost tracking. ## When to Use This Skill - Need to explain why AI made specific suggestions - Regulatory compliance requires audit trails - Want to track AI generation costs - Need confidence scoring for AI outputs - Building explainable AI systems ## Core Concepts Provenance tracking captures: decision factors (why), data lineage (from what), reasoning chain (how), confidence scoring, and generation metrics (cost/tokens). ## Implementation ### TypeScript ```typescript enum InsightType { CONTENT_SUGGESTION = 'content_suggestion', IMAGE_GENERATION = 'image_generation', TEXT_GENERATION = 'text_generation', } enum ConfidenceLevel { VERY_HIGH = 'very_high', // 90-100% HIGH = 'high', // 75-89% MEDIUM = 'medium', // 50-74% LOW = 'low', // 25-49% VERY_LOW = 'very_low', // 0-24% } interface DataSource { sourceType: string; // 'database', 'api', 'cache' sourceKey: string; // 'postgres:users', 'openai:gpt-4' recordsUsed: number; freshnessSeconds: number; qualityScore: number; // 0-1 sampleIds: string[]; } interface DecisionFactor { factorName: string; rawValue: number;
- When to Use This Skill
- Core Concepts
- Implementation
- TypeScript
- Usage Examples
- Best Practices
- Common Mistakes
- Related Patterns
What does the provenance-audit skill do?
AI generation provenance and audit trail tracking. Records decision factors, data lineage, reasoning chains, confidence scoring, and cost tracking for AI-generated content.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill provenance-audit --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.