Agent skill
examples-git-fg-meta-plugin-manager
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/examples-git-fg-meta-plugin-manager
SKILL.md
Example: Basic Skill
This example shows a minimal, well-structured skill following all thecattoolkit_v3 standards.
File Structure
skills/hello-world/
└── SKILL.md
Complete SKILL.md
---
name: hello-world
description: "Greets users with a friendly message. Use when you want to say hello or demonstrate basic skill structure. Not for complex greetings or personalized messages."
---
# Hello World Skill
This skill demonstrates the basic structure of a well-formed skill.
## What It Does
Greets users with a simple, friendly message.
## Usage
Say "Hello, World!" to the user.
## Message
Hello, World! Welcome to the thecattoolkit_v3.
Breakdown and Explanation
Frontmatter
---
name: hello-world # Max 64 chars, lowercase, hyphens only
description: "Greets users... Use when... Not for..."
---
Key Points:
name: Uses kebab-case (lowercase with hyphens)description: Non-spoiling, includes "Use when" and "Not for"- No
context: fork(uses default shared context) - No
agent(not needed without context: fork)
Frontmatter Fields Explained
| Field | Value | Why |
|---|---|---|
name |
hello-world |
Lowercase, hyphens, descriptive |
description |
"Greets users... Use when... Not for..." | Non-spoiling, clear triggers and exclusions |
Body Structure
# Hello World Skill <- Clear title
This skill demonstrates... <- Brief purpose statement
## What It Does <- What section
Greets users...
## Usage <- How section
Say "Hello..."
## Message <- Content
Hello, World!
Key Points:
- Clear headings for organization
- Brief purpose statement
- Separation of "what" and "how"
- Actual content/message at the end
Quality Checklist Applied
Frontmatter
-
namepresent:hello-world -
descriptionpresent: Non-spoiling -
descriptionhas "Use when": "Use when you want to say hello..." -
descriptionhas "Not for": "Not for complex greetings..."
Naming
- Gerund form:
hello-world(noun phrase acceptable for simple names) - Lowercase only: Yes
- Hyphens as separators: Yes
- Not reserved words: Yes
- Not vague:
hello-worldis specific
Description Quality
- Third person: "Greets users" not "I will greet"
- Non-spoiling: Doesn't reveal the exact message
- Trigger conditions: "Use when you want to say hello..."
- Exclusions clear: "Not for complex greetings..."
Progressive Disclosure
- Core in SKILL.md: All content in main file
- No references/ folder: Not needed for simple skill
- No scripts/: Not needed
How to Invoke
User Invocation
# From command palette
/hello-world
# Or from chat
Use the hello-world skill
Agent Invocation
# In another skill or command
Skill(hello-world)
What Happens When Invoked
- Metadata loaded:
nameanddescriptionalready in system prompt - SKILL.md read: Body content loaded into context
- Skill executes: Agent reads and follows instructions
- Result: "Hello, World!" message displayed
Common Variations
With argument-hint
---
name: greet
description: "Greets users with a custom message. Use when you want to say hello with a name. Not for complex greetings."
argument-hint: "<name>"
---
With user-invocable: false
---
name: internal-helper
description: "Internal helper skill. Use when performing internal operations. Not for user-facing tasks."
user-invocable: false
---
Result: Skill is hidden from / menu, but Claude can still invoke via Skill(internal-helper).
With disable-model-invocation
---
name: dangerous-operation
description: "Performs a dangerous operation. Use when user explicitly requests this operation. Not for automated tasks."
disable-model-invocation: true
---
Result: Skill won't auto-invoke; requires explicit user intent.
Next Steps
After understanding this basic skill:
- Study
worker-skill.mdfor isolated context - Review
loadout-agent.mdfor multi-skill bundling - See
quality-gate.mdfor validation patterns
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
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.
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.
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.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
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?