kenryu42/agent-skills

bro

Restate the last message in plain human language, with no jargon.

test-coverage-improver

Improve repository test coverage with autonomous, test-only quick wins. Run `bun run test:coverage`, inspect coverage artifacts, add tests that exercise real production behavior, repeat until no quick wins remain, validate the result, and report opportunities…

ultra

Manual multi-agent build workflow — Fable owns judgment (plan, investigate, design, review, decide), Opus owns execution (implement, fix, validate); a Fable planner designs a task-specific stage plan, then a Fable review + Opus fix loop closes it out.

codex-first

Delegate substantial implementation, fixing, code exploration, rebasing, and PR landing mechanics to Codex CLI while Claude handles design, decisions, review, and verification.

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

commit-with-context

Create a coherent Conventional Commit with concise, high-signal context. Use when the user explicitly asks to commit current work or invokes $commit-with-context. Keep unrelated changes out and avoid splitting one task into artificial micro-commits.

sponsor-miner

Find and verify potential sponsors for a GitHub repository by mining GitHub README sponsorship placements. Use when the user provides a target GitHub repo URL and wants sponsor leads, README sponsor discovery, sponsor verification, contact URLs, or a…

codex-security

Use when the user asks for Codex Security workflows: repository-wide or scoped-path security scans, security reviews of pull requests, commits, branch diffs, or working-tree patches, deep exhaustive repository scans, fixing validated or plausible security…

repo-explorer

Clone and inspect external repositories in a reusable local exploration cache. Use this skill when the user asks to explore, inspect, investigate, compare, or answer questions about a repository that may not already be in the current workspace.

atomic-commit

Create atomic git commits

runtime-review

Use when diagnosing or fixing runtime CPU spikes, high event-loop latency, memory growth, heap leaks, garbage-collection pressure, or OOM crashes in Node.js, Bun, Deno, JavaScript/TypeScript services, or comparable long-running runtimes. Includes code-first…

sqlite-expert

SQLite database optimization, query writing, indexing, and best practices specialist. Proactively analyzes and optimizes SQLite databases for performance and reliability.

thermo-nuclear-code-quality-review

Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.