菜单
Use when starting any conversation - establishes how to find and invoke constellation skills before any response, including 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
Use when creating, editing, reviewing, or rendering software architecture or flow diagrams — C4 diagrams (system context, container, component, deployment, dynamic), sequence diagrams, request-flow visuals, or any Mermaid authoring where the rendered output must be readable. Also use when a Mermaid diagram renders with overlapping labels, parse errors, or a single-column layout, or when the user asks to "diagram the architecture", "draw the request flow", "map the sequences", or wants LucidChart-quality output from Mermaid.
Use when about to create a feature, build a component, add functionality, modify behavior, or start any new work — or when the user asks how should we, what approach, which way, explore options, design X, or spec this out. Triggers before any code, scaffold, or implementation skill runs.
Use when one request spans multiple domains (e.g. code + tests + docs + security + diagrams), has independent workstreams that could run concurrently, or is too large for a single agent in one pass — symptoms include "do all of X, Y, and Z", a multi-part review, or a task that would obviously thrash one agent's context
Use when defining product requirements, writing or updating a PRD, spec'ing out a feature, or deciding what to build — or when the user says write requirements, create a PRD, define the product, what should we build, or hands over stakeholder/engineering feedback to fold into an existing PRD. Especially for non-technical users translating a conversation into structured requirements.
Use when you want brutal, worst-case review of code resilience -- failure modes, race conditions, blast radius, and edge cases optimistic reviewers miss.
Use when reviewing code or a PR for high-confidence, real-exploitation security vulnerabilities (>80% confidence threshold, low false positives).
| name | using-constellation |
| description | Use when starting any conversation - establishes how to find and invoke constellation skills before any response, including clarifying questions |
IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.
This is not negotiable. You cannot rationalize your way out of it. If an invoked skill turns out to be wrong for the situation, you don't need to use it — checking is cheap, skipping is not.
If the user's instructions conflict with a skill, follow the user. The user is in control.
Never read skill files manually with file tools — use your platform's skill loader so the skill activates.
Skill tool. Slash commands map to skills.~/.agents/skills/; follow the instructions presented. For tool-name differences, consult the plugin's skills/_shared/platform/codex-tools.md.The full catalog of available skills is in CATALOG.md at the plugin root — consult it when deciding what applies. It is generated from the skills/ directory, so it always reflects what is installed.
Invoke relevant or requested skills BEFORE any response or action — even a 1% chance means check.
digraph skill_flow {
"User message received" [shape=doublecircle];
"About to design/plan/build?" [shape=diamond];
"Already brainstormed?" [shape=diamond];
"Invoke brainstorming skill" [shape=box];
"Might any skill apply?" [shape=diamond];
"Invoke the skill" [shape=box];
"Announce: 'Using [skill] to [purpose]'" [shape=box];
"Has checklist?" [shape=diamond];
"Create a todo per item" [shape=box];
"Follow skill exactly" [shape=box];
"Respond (including clarifications)" [shape=doublecircle];
"User message received" -> "About to design/plan/build?";
"About to design/plan/build?" -> "Already brainstormed?" [label="yes"];
"About to design/plan/build?" -> "Might any skill apply?" [label="no"];
"Already brainstormed?" -> "Invoke brainstorming skill" [label="no"];
"Already brainstormed?" -> "Might any skill apply?" [label="yes"];
"Invoke brainstorming skill" -> "Might any skill apply?";
"Might any skill apply?" -> "Invoke the skill" [label="yes, even 1%"];
"Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
"Invoke the skill" -> "Announce: 'Using [skill] to [purpose]'";
"Announce: 'Using [skill] to [purpose]'" -> "Has checklist?";
"Has checklist?" -> "Create a todo per item" [label="yes"];
"Has checklist?" -> "Follow skill exactly" [label="no"];
"Create a todo per item" -> "Follow skill exactly";
}
| 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 the codebase first" | Skills tell you HOW to explore. Check first. |
| "I'll just do this one thing first" | Check BEFORE doing anything. |
| "The skill is overkill" | Simple things become complex. Use it. |
| "I remember this skill" | Skills evolve. Read the current version. |
| "This doesn't count as a task" | Action = task. Check for skills. |
"Let's build X" → brainstorming, then planning, then implementation skills. "Fix this bug" → systematic-debugging first, then domain skills.
Each skill states which it is.
plan-validator (PASS ≥ 70) before being shown. Maintain .ai/sessions/<date>_<TICKET>_<slug>/ docs automatically.When you invoke a skill, say "Using [skill] to [purpose]" so the step is visible and tracked.