菜单
Use when starting any conversation to discover relevant skills and open the right SKILL.md files before responding, including before clarifying questions.
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
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when the user asks to review a pull request or diff with a structured Codex CLI workflow using parallel review passes and filtered actionable findings.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Use when the user asks to build a new feature and wants a structured Codex CLI workflow with discovery, clarifying questions, architecture comparison, implementation, and review.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
| name | using-superpowers |
| description | Use when starting any conversation to discover relevant skills and open the right SKILL.md files before responding, including before clarifying questions. |
If a relevant skill exists, you do not get to skip it because the task feels small or familiar.
In Codex CLI: Open the relevant SKILL.md under ~/.codex/skills or the workspace-provided skill pack, then follow it directly.
If a skill includes a checklist: mirror the checklist in update_plan so progress stays visible while you work.
Open relevant or requested skills before any response or action. Even a 1% chance that a skill applies means you should inspect it first. If a skill turns out not to fit, you can stop using it after reading it.
`dot digraph skill_flow { "User message received" [shape=doublecircle]; "About to start work?" [shape=doublecircle]; "Already brainstormed?" [shape=diamond]; "Open brainstorming skill" [shape=box]; "Might a skill apply?" [shape=diamond]; "Open matching SKILL.md" [shape=box]; "Announce: Using [skill]" [shape=box]; "Has checklist?" [shape=diamond]; "Mirror checklist in update_plan" [shape=box]; "Follow skill exactly" [shape=box]; "Respond" [shape=doublecircle];
"About to start work?" -> "Already brainstormed?";
"Already brainstormed?" -> "Open brainstorming skill" [label="no"];
"Already brainstormed?" -> "Might a skill apply?" [label="yes"];
"Open brainstorming skill" -> "Might a skill apply?";
"User message received" -> "Might a skill apply?";
"Might a skill apply?" -> "Open matching SKILL.md" [label="yes, even 1%"];
"Might a skill apply?" -> "Respond" [label="definitely not"];
"Open matching SKILL.md" -> "Announce: Using [skill]";
"Announce: Using [skill]" -> "Has checklist?";
"Has checklist?" -> "Mirror checklist in update_plan" [label="yes"];
"Has checklist?" -> "Follow skill exactly" [label="no"];
"Mirror checklist in update_plan" -> "Follow skill exactly";
} `
These thoughts mean STOP and open the skill first:
| Thought | Reality |
|---|---|
| "This is just a simple question" | Questions are tasks. Check for skills. |
| "I need more context first" | Skill check comes before clarifying questions. |
| "Let me explore quickly first" | Skills tell you how to explore. Check first. |
| "I remember this skill already" | Skills evolve. Read the current file. |
| "The skill is overkill" | Small tasks still benefit from the right workflow. |
| "I'll do one thing first" | Check before acting. |
When multiple skills could apply, use this order:
Rigid skills enforce a workflow and should be followed closely.
Flexible skills provide patterns you can adapt to context.
User instructions say what to do. Skills tell you how to do it safely and consistently.