Agent skill
skill-development
Create portable skills with SKILL.md. Use when building new skills or documenting patterns. Includes frontmatter syntax, quality standards, and primitives. Not for commands or agents.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/skill-development-git-fg-meta-plugin-manager
SKILL.md
Skill Development
Core Principle
Put everything useful in SKILL.md. AI agents are smart (can infer from examples) and lazy (won't hunt for scattered references).
Frontmatter
---
name: skill-name
description: "What it does. Use when {trigger + keywords}. Not for {exclusions}."
---
Description format: What it does, when to use it (with trigger phrases), what it's NOT for.
Optional fields: context: fork, agent:, skills:, disable-model-invocation, user-invocable
Primitives
| Primitive | Context | Use When |
|---|---|---|
Task() |
Forked | Heavy multi-step work |
Skill() |
Shared | Adding expertise |
Skill(fork) |
Isolated | Biased-free execution |
Key constraint: Task→Task is forbidden. Skill(fork)→Skill(fork) is allowed.
Directory Structure
.claude/skills/skill-name/
└── SKILL.md
Folder and file names use kebab-case. References folder is RARE—needs strong justification.
Quality Checklist
| Check | Requirement |
|---|---|
| Frontmatter | name + description (What-When-Not format) |
| Quick Start | Scenario-based entry point |
| Navigation | "If you need X → Read Y" table |
| Core knowledge | In SKILL.md, not in references/ |
| Footer | critical_constraint for non-negotiable rules |
Anti-Patterns to Avoid
- ❌ Hiding patterns in references/ when they could be in SKILL.md
- ❌ Vague names (
helper,utils) - ❌ Spoiling content in navigation
- ❌ Nested folder structures
- ❌ Task→Task (forbidden)
<critical_constraint> Portability Invariant: Every skill MUST work in isolation (zero external dependencies).
- All content in SKILL.md or its own references/
- No references to global rules or other components
- If references/ is used, MARK MANDATORY with critical_constraint
Gold Standards:
- Frontmatter first
- Description enables auto-discovery
- Navigation uses "If you need... Read this section..."
- critical_constraint footer present </critical_constraint>
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?