菜单
Guidelines for creating and managing skills in this project. Use when adding, modifying, or reviewing skills in .claude/skills/.
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
Efficient app-driving workflow for the real Flutter app on emulator or Linux/macOS desktop via VM service extensions, including common blocker recovery.
Quality gate protocol between implementation and handoff.
Guidelines for creating and maintaining documentation in the Nothingness project. Use when adding architecture docs, design docs, or complex logic explanations.
Standards for code quality, linting, and modern API usage in Flutter. Use when writing or modifying Dart code. Covers deprecations and analyzer rules.
Guidelines for running Flutter CLI commands and handling sandbox permissions. Use when executing flutter build, run, pub, or clean commands.
Guidelines for polling GitHub Actions workflow runs via MCP tools. Use when working with CI/CD workflows, monitoring builds, or debugging workflow failures.
| name | skill-creation |
| description | Guidelines for creating and managing skills in this project. Use when adding, modifying, or reviewing skills in .claude/skills/. |
This project uses the Agent Skills format. Skills live in .claude/skills/.
Each skill is a directory containing at minimum a SKILL.md file. The directory name must match the name field in frontmatter.
.claude/skills/
my-skill/
SKILL.md
scripts/ # Optional: executable code agents can run
references/ # Optional: additional docs loaded on demand
assets/ # Optional: templates, images, data files
| Field | Required | Description |
|---|---|---|
name | Yes | 1–64 chars. Lowercase alphanumeric + hyphens. No leading/trailing/consecutive -. |
description | Yes | 1–1024 chars. Describe what the skill does and when to use it. |
---
name: my-skill
description: Standards for doing X in this project. Use when creating or modifying X.
---
# My Skill
Step-by-step instructions, examples, edge cases…
Skills are loaded in stages to conserve context:
name and description are loaded at startup for all skills.SKILL.md body loaded when activated.scripts/, references/, assets/ loaded on demand.Keep SKILL.md under 500 lines. Move detailed reference material to separate files using relative paths (one level deep).
Skills must be registered in AGENTS.md under the Rules Index table so agents know when to consult them.
testing-standards/).