skills-reference
Claude Code skills (Agent Skills) configuration reference. Use when creating skills, understanding skill activation, SKILL.md format, user-invoked vs model-invoked skills, or skill best practices.
What this skill does
# Claude Code Skills Reference Skills extend Claude's capabilities. They're defined as Markdown files that Claude loads when needed. ## Two Types of Skills | Type | Trigger | Use Case | |------|---------|----------| | **Model-invoked** | Claude decides automatically | Reference docs, specialized knowledge | | **User-invoked** | User types `/skill-name` | Workflows, actions with side effects | ## Skill File Structure ``` ~/.claude/skills/ # User skills (all projects) .claude/skills/ # Project skills (team shared) skill-name/ ├── SKILL.md # Required: skill definition ├── reference.md # Optional: additional docs └── scripts/ # Optional: supporting files ``` ## SKILL.md Format ```markdown --- name: my-skill description: What this skill does and when Claude should use it user_invocable: false model: sonnet tools: - Read - Bash --- # Skill Title Instructions Claude follows when this skill is activated. ## When to Use Describe scenarios when this skill applies. ## How to Execute Step-by-step instructions for Claude. ``` ## Frontmatter Fields | Field | Required | Type | Description | |-------|----------|------|-------------| | `name` | Yes | string | Skill identifier | | `description` | Yes | string | When/why to use this skill | | `user_invocable` | No | boolean | Allow `/skill-name` invocation | | `model` | No | string | Model to use (haiku, sonnet, opus) | | `tools` | No | array | Restrict available tools | | `allowed_tools` | No | array | Alias for `tools` | ## Model-Invoked Skills Claude automatically uses these when the task matches the description. ```markdown --- name: python-debugging description: Debug Python code. Use when user encounters Python errors, exceptions, or unexpected behavior. --- # Python Debugging When debugging Python code: 1. Read the error traceback carefully 2. Identify the failing line and function 3. Check variable types and values ... ``` ## User-Invoked Skills User explicitly triggers with `/skill-name`. ```markdown --- name: deploy description: Deploy to production environment user_invocable: true --- # Deploy Workflow 1. Run tests: `npm test` 2. Build: `npm run build` 3. Deploy: `npm run deploy` ``` ## Skill with Tool Restrictions ```markdown --- name: readonly-analyzer description: Analyze code without modifications tools: - Read - Glob - Grep --- # Read-Only Analysis Analyze codebase patterns without making changes. ``` ## Skill Activation **Model-invoked activation**: - Claude checks skill descriptions against current task - Matching skills are loaded into context - Claude follows skill instructions **User-invoked activation**: - User types `/skill-name` - Skill is loaded immediately - Claude executes skill instructions ## Best Practices 1. **Clear descriptions**: Be specific about when the skill applies 2. **Progressive disclosure**: Keep SKILL.md concise, reference external docs 3. **Single responsibility**: One skill per task type 4. **Limit scope**: Use tool restrictions for safety 5. **Test thoroughly**: Verify skill activates correctly ## Example: Reference Skill (Model-Invoked) ```markdown --- name: api-patterns description: REST API design patterns. Use when designing APIs, endpoints, or discussing HTTP conventions. --- # REST API Patterns Quick reference for API design. ## Endpoint Naming - Use nouns: `/users`, `/orders` - Use plural: `/users/123` not `/user/123` ... For complete API design guide, see [api-full.md](api-full.md). ``` ## Example: Workflow Skill (User-Invoked) ```markdown --- name: commit description: Create git commits with conventional format user_invocable: true --- # Commit Workflow 1. Check status: `git status` 2. Review changes: `git diff` 3. Stage files: `git add <files>` 4. Commit with message following conventional commits ``` ## Debugging Skills ```bash # List all skills /skills # Check if skill is loaded # Look for skill in available skills list # Test skill description matching # Ask Claude a question that should trigger the skill ``` --- For complete documentation, see: - [skills-full.md](skills-full.md) - Complete skills reference - [skills-best-practices.md](skills-best-practices.md) - Authoring guidelines
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.