agentskills-spec
Authoritative specification for the Agent Skills (agentskills.io) SKILL.md format.
Skill by cedricziel
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/cedricziel-agentskills-spec
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agentskills-spec
What's inside
- Skill 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
- Instructions
- 89 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
## Agent Skills Specification
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.
### Directory Structure
```
<skill-name>/
├── SKILL.md # Required — frontmatter + body
├── scripts/ # Optional — executable scripts
├── references/ # Optional — reference documents
└── assets/ # Optional — binary assets
```
### SKILL.md Format
```
---
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>
```
### Frontmatter Fields
| 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 |
### Body
- Written in Markdown
- Contains instructions the agent should follow when this skill is active
- Use `##` headings to organize sections
- Include examples, constraints, and step-by-step guidance
### Validation Rules
1. `name` must be kebab-case: only lowercase ASCII letters, digits, and non-leading/trailing/consecutive hyphens
2. `name` must match the directory name exactly
3. `description` must be non-empty and ≤ 1024 characters
4. `compatibility` if present must be ≤ 500 characters
5. The SKILL.md must have valid YAML frontmatter delimited by `---`
### Example
```
---
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
```
### When Generating a SKILL.md
1. Choose a `name` that is kebab-case and describes the skill's purpose
2. Write a `description` that is one clear sentence (≤ 1024 chars)
3. Set `license: MIT` unless the user specifies otherwise
4. List any tools the skill requires in `allowed-tools`
5. Write a body with `##` sections: purpose, rules/constraints, examples
6. Keep instructions actionable and specific — avoid vague language
7. Output the complete SKILL.md content including the `---` frontmatter delimitersFrom cedricziel/assistant, MIT.
More from cedricziel/assistant
- 0.582score
observability
cedricziel
Practical observability guide for this workspace.
SkillBFreshness: B★ 6Claude Code +9 - 0.532score
e2e-testing
cedricziel
Playwright visual regression testing for the assistant Flutter SPA.
SkillCFreshness: C★ 6Claude Code +9 - 0.532score
ios-codesigning
cedricziel
iOS code signing and provisioning profile management via fastlane match.
SkillCFreshness: C★ 6Claude Code +9 - 0.532score
coding-agent
cedricziel
Run coding agents (Claude Code, Codex, OpenCode, or others) as background processes for programmatic control.
SkillCFreshness: C★ 6Claude Code +9 - 0.532score
ux-principles
cedricziel
Flutter UX/UI principles for the assistant app.
SkillCFreshness: C★ 6Claude Code +9 - 0.532score
interface-implementation
cedricziel
Checklist and architectural rules for implementing new assistant interfaces (CLI, Slack, web, etc.).
SkillCFreshness: C★ 6Claude Code +9 - 0.532score
openapi-sync
cedricziel
Enforces OpenAPI spec discipline when working on REST API endpoints in this project.
SkillCFreshness: C★ 6Claude Code +9 - 0.532score
opentelemetry-rust-sdk
cedricziel
Best-practice guide for instrumenting Rust apps with the OpenTelemetry SDK.
SkillCFreshness: C★ 6Claude Code +9 - 0.532score
claude-code-agent
cedricziel
Run tasks on the local machine using Claude Code CLI as a background agent.
SkillCFreshness: C★ 6Claude Code +9 - 0.531score
opentelemetry-genai-spec
cedricziel
OpenTelemetry semantic conventions for Generative AI attributes.
SkillCFreshness: C★ 6Claude Code +9 - 0.529score
ci-organization
cedricziel
CI organization principles and workflow structure for this project.
SkillCFreshness: C★ 6Claude Code +9 - 0.529score
tdd
cedricziel
Test Driven Development discipline for this workspace.
SkillCFreshness: C★ 6Claude Code +9
Signals
- Stars
- 6
- Forks
- 1
- Open issues
- 14
- Last commit (this folder)
- Mar 29, 2026 (7 months ago)
- Last release
- May 26, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/cedricziel/assistant
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from cedricziel
- 0.582score
observability
cedricziel
Practical observability guide for this workspace.
SkillBFreshness: B★ 6Claude Code +9 - 0.567score

Aha.io
cedricziel
Search, read and update Aha.io ideas, features, epics, releases, goals and comments
ConnectorAFreshness: ALocal★ 6↓ 36/wkClaude Code +5 - 0.532score
interface-implementation
cedricziel
Checklist and architectural rules for implementing new assistant interfaces (CLI, Slack, web, etc.).
SkillCFreshness: C★ 6Claude Code +9 - 0.532score
e2e-testing
cedricziel
Playwright visual regression testing for the assistant Flutter SPA.
SkillCFreshness: C★ 6Claude Code +9 - 0.532score
ios-codesigning
cedricziel
iOS code signing and provisioning profile management via fastlane match.
SkillCFreshness: C★ 6Claude Code +9 - 0.532score
coding-agent
cedricziel
Run coding agents (Claude Code, Codex, OpenCode, or others) as background processes for programmatic control.
SkillCFreshness: C★ 6Claude Code +9
Cite this page
agentskills-spec. Agent Mart. https://agentmart.dev/skills/cedricziel-agentskills-spec (last updated 2026-10-24)