From plugin-dev
Guides developers in creating, improving, and structuring skills for Claude Code plugins, covering best practices for conciseness, degrees of freedom, progressive disclosure, and SKILL.md anatomy.
npx claudepluginhub basher83/lunar-claude --plugin plugin-devThis skill uses the workspace's default tool permissions.
> **Reference:** See [agent-skills-spec.md](references/agent-skills-spec.md) for the official specification.
Guides developers in creating Claude Code plugin skills: frontmatter metadata, Markdown instructions, bundled scripts/references/assets, and best practices.
Guides creation of new Claude Code skills from scratch, listing existing user/project skills, samples, current directory, and providing metadata templates for descriptions/tags.
Guides creation of effective Claude Code skills with principles on conciseness, degrees of freedom, anatomy, and bundling resources for workflows/tools.
Share bugs, ideas, or general feedback.
Reference: See agent-skills-spec.md for the official specification.
This skill provides guidance for creating effective skills for Claude Code plugins.
Skills are modular, self-contained packages that extend Claude's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform Claude from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.
The context window is a public good. Skills share the context window with everything else Claude needs: system prompt, conversation history, other skills' metadata, and the actual user request.
Default assumption: Claude is already very smart. Only add context Claude doesn't already have. Challenge each piece of information: "Does Claude really need this explanation?" and "Does this paragraph justify its token cost?"
Prefer concise examples over verbose explanations.
Match the level of specificity to the task's fragility and variability:
Think of Claude as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom).
Every skill consists of a required SKILL.md file and optional bundled resources:
skill-name/
├── SKILL.md (required)
│ ├── YAML frontmatter metadata (required)
│ │ ├── name: (required)
│ │ └── description: (required)
│ └── Markdown instructions (required)
└── Bundled Resources (optional)
├── scripts/ - Executable code (Python/Bash/etc.)
├── references/ - Documentation intended to be loaded into context as needed
└── assets/ - Files used in output (templates, icons, fonts, etc.)
Metadata Quality: The name and description in YAML frontmatter determine when Claude will use the skill. Be specific about what the skill does and when to use it. Use the third-person (e.g. "This skill should be used when..." instead of "Use this skill when...").
scripts/)Executable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten.
scripts/rotate_pdf.py for PDF rotation tasksreferences/)Documentation and reference material intended to be loaded as needed into context to inform Claude's process and thinking.
references/finance.md for financial schemas, references/mnda.md for company NDA template, references/policies.md for company policies, references/api_docs.md for API specificationsassets/)Files not intended to be loaded into context, but rather used within the output Claude produces.
assets/logo.png for brand assets, assets/slides.pptx for PowerPoint templates, assets/frontend-template/ for HTML/React boilerplate, assets/font.ttf for typographyA skill should only contain essential files that directly support its functionality. Do NOT create extraneous documentation or auxiliary files, including:
The skill should only contain the information needed for an AI agent to do the job at hand. It should not contain auxiliary context about the process that went into creating it, setup and testing procedures, user-facing documentation, etc. Creating additional documentation files just adds clutter and confusion.
Skills use a three-level loading system to manage context efficiently:
*Unlimited because scripts can be executed without reading into context window.
To create a skill, follow the "Skill Creation Process" in order, skipping steps only if there is a clear reason why they are not applicable.
Skip this step only when the skill's usage patterns are already clearly understood. It remains valuable even when working with an existing skill.
To create an effective skill, clearly understand concrete examples of how the skill will be used. This understanding can come from either direct user examples or generated examples that are validated with user feedback.
For example, when building an image-editor skill, relevant questions include:
To avoid overwhelming users, avoid asking too many questions in a single message. Start with the most important questions and follow up as needed for better effectiveness.
Conclude this step when there is a clear sense of the functionality the skill should support.
To turn concrete examples into an effective skill, analyze each example by:
Example: When building a pdf-editor skill to handle queries like "Help me rotate this PDF," the analysis shows:
scripts/rotate_pdf.py script would be helpful to store in the skillExample: When designing a frontend-webapp-builder skill for queries like "Build me a todo app" or "Build me a dashboard to track my steps," the analysis shows:
assets/hello-world/ template containing the boilerplate HTML/React project files would be helpful to store in the skillExample: When building a big-query skill to handle queries like "How many users have logged in today?" the analysis shows:
references/schema.md file documenting the table schemas would be helpful to store in the skillFor Claude Code plugins: When building a hooks skill, the analysis shows:
scripts/validate-hook-schema.sh and scripts/test-hook.sh utilities would be helpfulreferences/patterns.md for detailed hook patterns to avoid bloating SKILL.mdTo establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets.
For Claude Code plugins, create the skill directory structure:
mkdir -p plugin-name/skills/skill-name/{references,examples,scripts}
touch plugin-name/skills/skill-name/SKILL.md
Note: Unlike the generic skill-creator which uses init_skill.py, plugin skills are created directly in the plugin's skills/ directory with a simpler manual structure.
When editing the (newly-created or existing) skill, remember that the skill is being created for another instance of Claude to use. Focus on including information that would be beneficial and non-obvious to Claude. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Claude instance execute these tasks more effectively.
To begin implementation, start with the reusable resources identified above: scripts/, references/, and assets/ files. Note that this step may require user input. For example, when implementing a brand-guidelines skill, the user may need to provide brand assets or templates to store in assets/, or documentation to store in references/.
Also, delete any example files and directories not needed for the skill. Create only the directories you actually need (references/, examples/, scripts/).
Writing Style: Write the entire skill using imperative/infinitive form (verb-first instructions), not second person. Use objective, instructional language (e.g., "To accomplish X, do Y" rather than "You should do X" or "If you need to do X"). This maintains consistency and clarity for AI consumption.
Description (Frontmatter): Use third-person format with specific trigger phrases:
---
name: Skill Name
description: This skill should be used when the user asks to "specific phrase 1", "specific phrase 2", "specific phrase 3". Include exact phrases users would say that should trigger this skill. Be concrete and specific.
---
Good description examples:
description: This skill should be used when the user asks to "create a hook", "add a PreToolUse hook", "validate tool use", "implement prompt-based hooks", or mentions hook events (PreToolUse, PostToolUse, Stop).
Bad description examples:
description: Use this skill when working with hooks. # Wrong person, vague
description: Load when user needs hook help. # Not third person
description: Provides hook guidance. # No trigger phrases
To complete SKILL.md body, answer the following questions:
Keep SKILL.md lean: Target 1,500-2,000 words for the body. Move detailed content to references/:
references/patterns.mdreferences/advanced.mdreferences/migration.mdreferences/api-reference.mdReference resources in SKILL.md:
## Additional Resources
### Reference Files
For detailed patterns and techniques, consult:
- **`references/patterns.md`** - Common patterns
- **`references/advanced.md`** - Advanced use cases
### Example Files
Working examples in `examples/`:
- **`example-script.sh`** - Working example
For plugin skills, validation is different from generic skills:
plugin-name/skills/skill-name/Use the skill-reviewer agent:
Ask: "Review my skill and check if it follows best practices"
The skill-reviewer agent will check description quality, content organization, and progressive disclosure.
After testing the skill, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed.
Iteration workflow:
Common improvements:
Plugin skills live in the plugin's skills/ directory:
my-plugin/
├── .claude-plugin/
│ └── plugin.json
├── commands/
├── agents/
└── skills/
└── my-skill/
├── SKILL.md
├── references/
├── examples/
└── scripts/
Claude Code automatically discovers skills:
skills/ directorySKILL.mdPlugin skills are distributed as part of the plugin, not as separate ZIP files. Users get skills when they install the plugin.
Test skills by installing plugin locally:
# Test with --plugin-dir
cc --plugin-dir /path/to/plugin
# Ask questions that should trigger the skill
# Verify skill loads correctly
Study the skills in this plugin as examples of best practices:
hook-development skill:
agent-development skill:
plugin-settings skill:
Each demonstrates progressive disclosure and strong triggering.
Include (always loaded when skill triggers):
Keep under 3,000 words, ideally 1,500-2,000 words
Move to references/ (loaded as needed):
Each reference file can be large (2,000-5,000+ words)
Working code examples:
Users can copy and adapt these directly
Utility scripts:
Should be executable and documented
Write using verb-first instructions, not second person:
Correct (imperative):
To create a hook, define the event type.
Configure the MCP server with authentication.
Validate settings before use.
Incorrect (second person):
You should create a hook by defining the event type.
You need to configure the MCP server.
You must validate settings before use.
The frontmatter description must use third person:
Correct:
description: This skill should be used when the user asks to "create X", "configure Y"...
Incorrect:
description: Use this skill when you want to create X...
description: Load this skill when user asks...
Focus on what to do, not who should do it:
Correct:
Parse the frontmatter using sed.
Extract fields with grep.
Validate values before use.
Incorrect:
You can parse the frontmatter...
Claude should extract fields...
The user might validate values...
Before finalizing a skill:
Structure:
name and description fieldsDescription Quality:
Content Quality:
Progressive Disclosure:
Testing:
❌ Bad:
description: Provides guidance for working with hooks.
Why bad: Vague, no specific trigger phrases, not third person
✅ Good:
description: This skill should be used when the user asks to "create a hook", "add a PreToolUse hook", "validate tool use", or mentions hook events. Provides comprehensive hooks API guidance.
Why good: Third person, specific phrases, concrete scenarios
❌ Bad:
skill-name/
└── SKILL.md (8,000 words - everything in one file)
Why bad: Bloats context when skill loads, detailed content always loaded
✅ Good:
skill-name/
├── SKILL.md (1,800 words - core essentials)
└── references/
├── patterns.md (2,500 words)
└── advanced.md (3,700 words)
Why good: Progressive disclosure, detailed content loaded only when needed
❌ Bad:
You should start by reading the configuration file.
You need to validate the input.
You can use the grep tool to search.
Why bad: Second person, not imperative form
✅ Good:
Start by reading the configuration file.
Validate the input before processing.
Use the grep tool to search for patterns.
Why good: Imperative form, direct instructions
❌ Bad:
# SKILL.md
[Core content]
[No mention of references/ or examples/]
Why bad: Claude doesn't know references exist
✅ Good:
# SKILL.md
[Core content]
## Additional Resources
### Reference Files
- **`references/patterns.md`** - Detailed patterns
- **`references/advanced.md`** - Advanced techniques
### Examples
- **`examples/script.sh`** - Working example
Why good: Claude knows where to find additional information
The skill parser scans the entire SKILL.md for dynamic bash patterns without respecting fenced code block boundaries (GitHub #12781). This causes unintended execution during skill load.
Bad pattern: Using exclamation-backtick syntax (e.g., exclamation mark followed by backtick-command-backtick) in code block examples. The parser executes these during skill load. Escaping with backslash does NOT work.
Good pattern: Use $ shell notation instead:
# Safe in code blocks
$ git status
$ bash script.sh
Workarounds:
$ command notation in examplesThis also applies to @ file reference patterns in code blocks.
skill-name/
└── SKILL.md
Good for: Simple knowledge, no complex resources needed
skill-name/
├── SKILL.md
├── references/
│ └── detailed-guide.md
└── examples/
└── working-example.sh
Good for: Most plugin skills with detailed documentation
skill-name/
├── SKILL.md
├── references/
│ ├── patterns.md
│ └── advanced.md
├── examples/
│ ├── example1.sh
│ └── example2.json
└── scripts/
└── validate.sh
Good for: Complex domains with validation utilities
✅ DO:
❌ DON'T:
Plugin-dev's skills demonstrate best practices:
../hook-development/ - Progressive disclosure, utilities../agent-development/ - AI-assisted creation, references../mcp-integration/ - Comprehensive references../plugin-settings/ - Real-world examples../command-development/ - Clear critical concepts../plugin-structure/ - Good organizationFor complete skill-creator methodology:
references/skill-creator-original.md - Full original skill-creator contentFor complete Offical Anthropic skill specification:
references/agent-skills-spec.md - Full Offical Anthropic skill specificationTo create a skill for your plugin:
mkdir -p skills/skill-name/{references,examples,scripts}Focus on strong trigger descriptions, progressive disclosure, and imperative writing style for effective skills that load when needed and provide targeted guidance.