菜单
Review LLM prompts against the prompt-engineering skill's gap-calibration principles, reporting issues without modifying files. Use when reviewing prompt quality, auditing a prompt, evaluating a system prompt, or checking whether prompt issues are high-confidence and fixable.
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 | review-prompt |
| description | Review LLM prompts against the prompt-engineering skill's gap-calibration principles, reporting issues without modifying files. Use when reviewing prompt quality, auditing a prompt, evaluating a system prompt, or checking whether prompt issues are high-confidence and fixable. |
| user-invocable | true |
Review LLM prompts. Report findings without modifying files — this skill diagnoses; it never edits the prompt.
First: invoke the prompt-engineering skill to load the principles. Evaluate the prompt against them.
Input: if no prompt is given (file path or inline text), ask before analyzing — don't assume.
Report format:
Strengths — what's working, what the author should preserve.
Issues:
| Issue | Severity | Fix | Tag |
|---|---|---|---|
| {description} | High / Medium / Low | {concrete recommendation} | NEEDS_USER_INPUT or AUTO_FIXABLE |
Priority: the highest-impact change first.
Severity:
Tag (parsed as control flow by /auto-optimize-prompt — do not rename or repurpose):
NEEDS_USER_INPUT — only the author can resolve: missing context, unclear intent, ambiguity the model can't infer.AUTO_FIXABLE — a clear fix exists per the loaded principles.Only flag high-confidence issues. Low-confidence findings are noise — skip style preferences, minor wording, and unverified hunches.
End-to-end autonomous execution: figure-out → define → do, chained without manual approval gates. Use when you want to define and execute without intervention during planning, when the user asks for autonomous or end-to-end work, says just build it, or asks to tend or babysit a PR.
Figure things out together — any topic, problem, or idea. Presses relentlessly until shared understanding is reached. Use when you need to understand before acting, when figuring it out is the goal, or when the user asks to think through a decision, dig deeper, press an assumption, investigate why something is happening, or work through a problem.
Generate multi-CLI distribution packages from the Claude Code plugin. Converts shared skills and package assets for OpenCode, Codex CLI, and Pi under dist/. Run after changing plugin components to keep distributions in sync.
End-to-end autonomous execution: figure-out → define → do, chained without manual approval gates. Use when you want to define and execute without intervention during planning, when the user asks for autonomous or end-to-end work, says just build it, or asks to tend or babysit a PR.
Manifest executor. Works through Deliverables verifying every Acceptance Criterion and Global Invariant. Use when executing a manifest, running a plan, implementing a defined task, or when the user asks to run, execute, implement, or ship a manifest-backed plan.
Completion marker for the /do workflow. Outputs a plain-prose summary of what was built. Called by /do after every Acceptance Criterion and Global Invariant has fresh PASS evidence, when the manifest is complete, all criteria pass, or the workflow needs to wrap up with a completion summary.