菜单
QA cycling workflow - test, verify, fix, repeat until goal met. Activate when user says: ultraqa, qa cycle, fix all tests, make tests pass.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | ultraqa |
| description | QA cycling workflow - test, verify, fix, repeat until goal met. Activate when user says: ultraqa, qa cycle, fix all tests, make tests pass. |
| argument-hint | [--tests|--build|--lint|--typecheck] [--interactive] |
Autonomous QA cycling workflow that runs until your quality goal is met.
Cycle: run checks → diagnose failures → fix → repeat
| Flag | What to Check |
|---|---|
--tests | All test suites pass |
--build | Build succeeds with exit 0 |
--lint | No lint errors |
--typecheck | No TypeScript errors |
--interactive | Interactive CLI/service testing via @qa-tester |
Track in .omc/ultraqa-state.json. Clean up state files on completion.
[ULTRAQA Cycle 1/5] Running tests...
[ULTRAQA Cycle 1/5] FAILED - 3 tests failing
[ULTRAQA Cycle 1/5] Diagnosing...
[ULTRAQA Cycle 2/5] PASSED - All 47 tests pass
[ULTRAQA COMPLETE] Goal met after 2 cycles
Use this skill when working with the GitLab MCP server tools for merge requests, issues, repositories, pipelines, work items, variables, dependency proxy, webhooks, search, CI catalog, and related GitLab workflows.
Clean AI-generated code slop with regression-safe workflow. Activate when user says: deslop, anti-slop, AI slop, cleanup slop, clean up this code, remove bloat.
Cancel any active OMG mode and clean up state. Activate when user says: cancel, stop, cancelomg, stopomg, abort, kill it, stop everything.
Claude-Codex-Gemini tri-model orchestration for multi-perspective analysis. Activate when user says: ccg, tri-model, three models, multi-model, cross-validate, get multiple opinions, compare models.
Canonical cross-language coding standards reference. Shared rules embedded by reviewer agents. Activate when: viewing coding standards, checking naming rules, reviewing style baseline, consulting style guide, what are the rules.
2-stage pipeline: trace (causal investigation) then deep-interview (requirements). Activate when user says: deep dive, deep-dive, investigate deeply, trace and interview.