一键导入
agentskills-spec
Authoritative specification for the Agent Skills (agentskills.io) SKILL.md format. Use this skill when generating or validating SKILL.md files.
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。
菜单
Authoritative specification for the Agent Skills (agentskills.io) SKILL.md format. Use this skill when generating or validating SKILL.md files.
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 | agentskills-spec |
| description | Authoritative specification for the Agent Skills (agentskills.io) SKILL.md format. Use this skill when generating or validating SKILL.md files. |
| license | MIT |
A skill is a directory containing a SKILL.md file that teaches an AI agent how to perform a task or use a domain of knowledge. This specification defines the required format.
<skill-name>/
├── SKILL.md # Required — frontmatter + body
├── scripts/ # Optional — executable scripts
├── references/ # Optional — reference documents
└── assets/ # Optional — binary assets
---
name: <kebab-case-name>
description: <human-readable description>
license: <SPDX license identifier>
compatibility: <optional version or platform constraint>
allowed-tools: <space-separated kebab-case tool IDs (e.g. file-read web-fetch bash)>
metadata:
key: value
---
<markdown body — instructions for the agent>
| Field | Required | Constraints |
|---|---|---|
name | Yes | kebab-case (lowercase letters, digits, hyphens); max 64 chars; must match directory name |
description | Yes | Non-empty; max 1024 chars |
license | No | SPDX identifier (e.g. MIT, Apache-2.0) |
compatibility | No | Max 500 chars; version constraint or platform note |
allowed-tools | No | Space-separated kebab-case tool IDs (e.g. file-read web-fetch bash) |
metadata | No | Arbitrary key/value map for custom attributes |
## headings to organize sectionsname must be kebab-case: only lowercase ASCII letters, digits, and non-leading/trailing/consecutive hyphensname must match the directory name exactlydescription must be non-empty and ≤ 1024 characterscompatibility if present must be ≤ 500 characters------
name: git-commit
description: Teaches the agent to write semantic git commit messages following the Conventional Commits specification.
license: MIT
allowed-tools: bash file-read
---
## Conventional Commits
Always format commit messages as: `<type>(<scope>): <description>`
Types: feat, fix, chore, docs, refactor, test, perf
### Rules
- Subject line max 72 characters
- Use imperative mood ("add feature" not "added feature")
- Reference issues with (#123) at end of subject
name that is kebab-case and describes the skill's purposedescription that is one clear sentence (≤ 1024 chars)license: MIT unless the user specifies otherwiseallowed-tools## sections: purpose, rules/constraints, examples--- frontmatter delimitersiOS code signing and provisioning profile management via fastlane match. Use when debugging CI signing failures, adding new app extensions or targets, rotating certificates, or troubleshooting match decryption errors.
Enforces OpenAPI spec discipline when working on REST API endpoints in this project. Triggers whenever adding, modifying, or removing HTTP routes, request/response types, or API handlers in the Rust web-ui crate (`crates/web-ui`). Reminds the agent to (1) update the committed `openapi.json` spec, (2) run `make dump-openapi` to re-export the spec from the running server, and (3) run `make generate-flutter-client` to regenerate the Dart/dio client in `app/packages/assistant_api/`. Also applies when changing route parameters, status codes, or authentication on existing endpoints.
Test Driven Development discipline for this workspace. Use whenever writing new features, fixing bugs, or refactoring — the test must be written and confirmed failing before any implementation code is added.
CI organization principles and workflow structure for this project. Use whenever modifying, adding, or reviewing GitHub Actions workflows — including adding jobs, changing job order, updating action versions, modifying cache keys, adding build targets, or debugging CI failures.
Playwright visual regression testing for the assistant Flutter SPA. Covers test structure, screenshot baselines, cross-platform diff tolerance, CI workflow with inline diff comments, and baseline management. Use when adding screens, changing layouts, or debugging visual test failures.
Checklist and architectural rules for implementing new assistant interfaces (CLI, Slack, web, etc.). Every interface MUST use the Orchestrator to ensure consistent behaviour: system prompt, tools, skills, memory, and the full ReAct loop. Use this skill when adding, reviewing, or fixing an interface.