AI Agent Skills

Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control

Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, buil…

Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need…

Instruments code so production behavior is visible and diagnosable. Use when adding logging, metrics, tracing, or alerting. Use when shipping any feature that runs in pr…

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code…

Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove th…

Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.

Evaluate systematic strategy ideas through signal testing, statistical validation, decay, execution costs, and model-risk review.

Generate topic-first, two-part video-title candidates from an approved video brief or final script.

Perform a forensic company financial-statement review across earnings quality, health, fraud risk, and operating efficiency.

Formulate clear semantic abstractions from desired behavior before committing to implementation. Use when designing or revising terminology, entities, boundaries, respon…

Assess business quality, economic moats, management, competitive positioning, and durable value creation.

The Finn-loop: a 3-skill AI software factory for Claude Code — spec, build, review. Humans merge.