菜单
Use when the final swarm phase completes. Run specialist review, artifact verification, UAT, review beads, finishing checks, and handoff to compounding.
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
Use when the user asks to create a persistent repo-local Codex agent, scaffold `.codex/agents/*.toml`, define a reusable specialist role, or match an agent to existing local skills and MCP servers.
Use when designing or implementing a premium animated landing page with AI-generated visuals or looping video, especially when the workflow involves Higgfield-style image and video generation, Google AI Studio-style code prompting, React or Tailwind landing-page implementation, dark-mode video blending, scroll-tied playback, aspect-ratio-matched media blocks, or motion-first section design.
Use when the user asks to fine-tune on books, create an SFT dataset from books, train a style-transfer or author-voice model, extract ePub text, segment long-form book content, or prepare literary data for LoRA or small-model training.
Bootstrap a new AI-agent session by reading the repository operating docs and rebuilding project understanding from source. Use when Codex needs to start a new conversation, get up to speed on an unfamiliar repo, read AGENTS.md and README.md completely before acting, investigate the codebase to understand the project's purpose and architecture, or turn a rough onboarding prompt into an execution-ready repo-orientation prompt.
Use when reviewing completes or work is intentionally abandoned. Extract durable patterns, decisions, and failures into history/learnings, then promote only critical reusable lessons to critical-patterns.md.
Use when Codex should turn a concept, topic, tutorial, lesson, algorithm, system, workflow, or abstract idea into a playable browser game that teaches through interaction. Use for planning or implementing educational web games with the Game Studio plugin, including concept-to-mechanic translation, gameplay loop design, learning progression, and browser-game QA.
| name | reviewing |
| description | Use when the final swarm phase completes. Run specialist review, artifact verification, UAT, review beads, finishing checks, and handoff to compounding. |
| metadata | {"version":"1.0","ecosystem":"khuym","position":"7-of-9","upstream":"swarming","downstream":"compounding","dependencies":{"beads-cli":{"kind":"command","command":"br","missing_effect":"unavailable","reason":"Reviewing creates review beads and closes the epic through br."},"beads-viewer":{"kind":"command","command":"bv","missing_effect":"degraded","reason":"Reviewing verifies the live bead graph before epic closeout."}}} |
If .khuym/onboarding.json is missing or stale for the current repo, stop and invoke khuym:using-khuym before continuing.
Reviewing is the final automated quality gate after execution. It verifies that the completed feature is correct, safe, wired, and acceptable to the user before compounding begins.
history/<feature>/CONTEXT.mdhistory/<feature>/approach.md.khuym/state.jsonLoad references/reviewing-reference.md for the agent roster, severity rules, artifact verification, UAT flow, review bead schema, and finishing checklist.
.khuym/state.json.learnings-synthesizer, always runs after agents 1-4.After finishing:
{
"active_skill": "reviewing",
"phase": "reviewing-complete",
"epic_id": "<id>",
"summary": "Review complete. Ready to run compounding.",
"next_action": "Invoke khuym:compounding.",
"focus": "compounding",
"blockers": []
}
Tell the user: Feature complete. Epic <id> closed. Invoke khuym:compounding skill.
| File | When to Load |
|---|---|
references/reviewing-reference.md | Review flow, specialist roster, review bead schema |