woc-qa
GitHub协调 World of ClaudeCraft 的贡献后 QA,执行准备度检查、回归测试及专家审查。涵盖建立范围、运行构建测试命令、分发专项审查员并报告结果,确保代码质量与合规性。
触发场景
安装
npx skills add levy-street/world-of-claudecraft --skill woc-qa -g -y
SKILL.md
Frontmatter
{
"name": "woc-qa",
"description": "Run end-of-contribution QA for World of ClaudeCraft, including readiness checks, scoped regression testing, and conditional specialist review. Use when asked to QA changes, make work ready, verify a branch or worktree, or assess whether a contribution is complete."
}
World of ClaudeCraft QA
Coordinate one evidence-backed QA pass for the requested change.
Establish authority and scope
- Read the root
CLAUDE.mdin full. - Read each relevant local
CLAUDE.mdbefore inspecting or editing that area. - Run
git status --shortand preserve unrelated work. - Establish the diff once. Prefer the working tree when changes are uncommitted;
otherwise use the user-provided base or active release base. Never assume
main. - Treat
review,check, andauditas read-only. Treatfix findings,make ready, or implementation requests as permission for scoped remediation. - Do not commit, push, post comments, or create pull requests unless explicitly asked.
CLAUDE.md owns repository architecture and invariants. Reference it instead of
restating or replacing it.
Run coordinator-owned checks
The coordinating agent owns build, test, lint, generation, and scanner commands. Specialist agents inspect code and shared command output without rerunning the full gate.
During iteration, run the smallest relevant set:
- Targeted Vitest files for changed behavior.
- Architecture or localization guard tests for touched domains.
npm run i18n:genbefore tests that require generated localization artifacts.npm run ci:changed.npx tsc --noEmit.
Before declaring implementation work ready, run:
npm run gate
If a command cannot run, report the exact blocker and continue with every safe check that remains.
Dispatch conditional reviewers
Give each reviewer the established diff, relevant files, applicable canonical instructions, and command results. Require read-only evidence with file and line references. Use only the agents relevant to the diff:
woc_sim_architecturefor simulation behavior, determinism, or module boundaries.woc_cross_platformfor world, network, wire, RL, matcher, or client parity.woc_persistencefor DDL, stored JSONB, save paths, or compatibility.woc_database_performancefor SQL, indexes, query call sites, pool or lock behavior, timeout policy, background database work, driver/dependency upgrades, PostgreSQL engine/resource/configuration/topology changes, or features that increase stored-data cardinality.woc_securityfor server, admin, auth, deployment, secrets, or trust boundaries.woc_test_coveragefor changed behavior, acceptance criteria, and regression tests.woc_frontendfor UI, render, CSS, i18n, accessibility, responsive, or fairness work.woc_release_malwarefor releases, dependencies, install behavior, AI instructions, or suspicious executable content.
Run independent reviewers in parallel when capacity permits. Verify consequential findings against the actual diff and surrounding code. Reject speculative, inherited, duplicate, or out-of-scope findings. In review-only mode, do not edit files.
Report
Return the scope and base, commands and results, reviewers used, confirmed findings,
authorized fixes, remaining risks, and one verdict: READY, READY WITH NOTES, or
NOT READY.
版本历史
- 2edc3ac 当前 2026-07-19 18:52


