All skills

A skill that designs REST/GraphQL APIs end to end — resource modeling, OpenAPI 3.1 specs, pagination, errors, and versioning.

A principal-architect skill that walks you from requirements to architecture diagrams and ADRs with explicit trade-offs.

A skill for designing and building command-line tools with commander, click, typer, or cobra — argument parsing, progress UI, and shell completions included.

Produces statistically rigorous A/B test plans with hypothesis, sample size, duration, safety metrics, and a results-interpretation guide.

Converts a raw git log into grouped, user-facing release notes with a headline and migration note.

Scrapes and aggregates bestseller/new-release rankings from major Chinese web-novel platforms to extract market trends and viable story-topic candidates.

An evidence-driven playbook that queries the Cloudflare API to diagnose redirect loops, SSL errors, DNS problems, and origin failures instead of guessing.

Turns a list of shell commands into polished animated terminal demo GIFs using VHS recordings.

Evidence-driven diagnosis and repair of repository setup, plus guarded Git sync, commit, push and hook workflows.

Runs N sub-agents on the exact same task, then makes them attack, defend and get judged in a single-elimination bracket until one solution survives.

Give it an issue number and it runs the whole loop: analyze, branch, implement, test, and open a PR.

Delegates coding, code review, and plan review to the OpenAI Codex CLI from inside Claude Code, with disciplined sandbox levels.

Lets Claude Code generate and edit images through OpenAI's GPT Image API with a bundled Python script.

Reviews GitHub pull requests with seven parallel specialist subagents, then adversarially verifies every finding so only high-confidence, high-severity issues get posted.

Clones and audits competitor repositories into evidence-based competitive intelligence with file:line citations.

A diagnose-first skill for writing, reviewing and debugging Terraform/OpenTofu code, tests, CI pipelines and state operations with version-aware guardrails.

A judgment-layer rulebook you load before drawing any chart or dashboard: it decides whether the chart should exist at all.

Turns audio or video into speaker-labeled, timestamped transcripts — locally with MLX/whisper.cpp on Apple Silicon or through a remote ASR endpoint.

Produces a statistically rigorous A/B test plan with hypothesis, sample size, duration, guardrail metrics, and a pre-committed results interpretation guide.

Builds a complete 360-degree feedback survey instrument, or turns raw reviewer notes into a structured feedback report.