AI Agent Skills

Write an executable specification under docs/graph/specs/ that turns a clear goal into testable contracts. Use whenever a feature, endpoint, job, significant function, o…

The test-SHAPING technique applied inside the test-first protocol — pick the lowest test level that exercises the behavior (unit, integration, contract, e2e, golden, pro…

Prove that a knowledge base actually works before trusting it — after building or adopting docs, a knowledge graph, or a wiki, verify it can orient a fresh agent and res…

Script the first 1-3 second TikTok hook: the spoken line, the on-screen text, and the opening visual firing at once so the viewer cannot swipe. Picks a 2026 hook formula…

Audit and rewrite a TikTok profile for 2026: photo, name (searchable), username, bio (80 chars, niche clarity is everything), link (unlocks at 1k followers, plus a pre-1…

Repurpose content into a native TikTok script and caption. Take a LinkedIn post, blog, newsletter, or X thread that worked elsewhere and rebuild it as a spoken script: h…

Maintain bounded, durable AI project memory in a repository's docs/ai/ pack. Use when Codex or Claude Code needs to create, read, update, or audit project memory (projec…

Query and maintain the user's local LLM Wiki from any Codex or Claude Code conversation or project. Use when the user asks to search personal knowledge, recall prior res…

Use when a developer asks to improve code comments, documentation, naming, or private placement for a GitHub pull request, uncommitted files, or any repository folders a…

Use when evaluating test coverage gaps, planning test strategy, or assessing testing risk for code changes.

Use when reviewing a diff, PR, or set of code changes, or auditing a codebase area for quality issues. Triggers: 'review this', 'code review', 'audit X', 'look at these…

QA 流程倒数第二步的独立审查环节。在 qa-test-runner 执行完成后，以独立视角审查代码本身——检查架构、安全、并发正确性、数据一致性、 回归风险、测试覆盖缺口——不受执行方结论的影响。产出 code-review.json（含 severity 分级发现和 readiness 约束）， 和 assert-code-revi…

在风险分析完成后、写测试代码之前，生成中文业务用例并等待用户确认。这是整个 QA 流程中唯一的强制人工门禁——确认后不可回头改用例。 从 context、risk-analysis、已有用例索引出发，生成只含业务行为的 test-cases.json（不含技术检查如 Maven/build/安装）， 渲染 test-cases.html…

Use when the user invokes $encode-policy-v2 or asks Codex or Claude Code to implement a new PolicyEngine-US state benefit program or a new structural program component f…

Use when the user invokes $fix-pr or asks Codex or Claude Code to apply fixes to a PolicyEngine PR based on $review-program findings, GitHub review comments, CI failures…

PolicyEngine coding standards, environment setup, formatters, changelog, and CI requirements across every repo — what makes a PR pass and merge cleanly. Covers uv + .ven…