---

name: claude-skills-overview-2026 description: Reference guide for Claude Code skills system (January 2026). Use when creating, modifying, or understanding skills, SKILL.md format, frontmatter fields, hooks, context fork, or skill best practices.

Claude Code Skills System - Complete Reference (January 2026)

Skills extend what Claude can do. Create a SKILL.md file with instructions, and Claude adds it to its toolkit. Claude uses skills when relevant, or you can invoke one directly with /skill-name.

Skills and slash commands are now unified - they are the same system. A file at .claude/commands/review.md and a skill at .claude/skills/review/SKILL.md both create /review and work identically. Skills are the recommended approach as they support additional features like supporting files and advanced frontmatter options.

---

SKILL.md Complete Format

Copy---
name: skill-identifier
description: What this Skill does and when to use it
argument-hint: "[optional-arg]"
allowed-tools: Read, Grep, Glob
model: claude-sonnet-4-20250514
context: fork
agent: general-purpose
user-invocable: true
disable-model-invocation: false
hooks:
  PreToolUse:
    - matcher: "Bash"
      hooks:
        - type: command
          command: "./scripts/validate.sh"
          once: true
  PostToolUse:
    - matcher: "Write|Edit"
      hooks:
        - type: command
          command: "./scripts/lint.sh"
  Stop:
    - hooks:
        - type: command
          command: "./scripts/cleanup.sh"
---

# Skill Title

Your instructions here...

---

All Frontmatter Fields

All fields are optional. Only description is recommended so Claude knows when to use the skill.

---

Skill Tokenomics

Skills use progressive disclosure - only frontmatter loads initially (~100 tokens), full content loads on activation.

Budget Constraints

YAML Multiline Bug

Do NOT use YAML multiline indicators (>-, |, |-) for descriptions. Claude Code's skill indexer does not parse them correctly - the description appears as ">-" instead of actual content.

Copy# WRONG - will show ">-" as description
description: >-
  This is a multiline
  description that breaks.

# WRONG - same problem
description: |
  This breaks too.

# CORRECT - single quoted string
description: 'This works correctly. Use single quotes for descriptions with special characters or keep on one line.'

Truncation Behavior

When total skill metadata exceeds ~15,000 characters:

1. Skills are truncated from the <available_skills> block
2. Truncated skills cannot be auto-invoked by Claude
3. User can still invoke truncated skills explicitly with /skill-name

Fallback Strategy

If you have many skills, embed pointers in CLAUDE.md as a safeguard:

Copy## Skills Available
- For debugging: use `/scientific-thinking` skill
- For delegation: use `/delegate` skill

This ensures Claude can find skills even if truncated from <available_skills>.

---

String Substitutions

Skills support string substitution for dynamic values in the skill content:

---

Dynamic Context Injection

The !command`` syntax runs shell commands before the skill content is sent to Claude. The command output replaces the placeholder, so Claude receives actual data, not the command itself.

Example: This skill summarizes a pull request by fetching live PR data with the GitHub CLI:

Copy---
name: pr-summary
description: Summarize changes in a pull request
context: fork
agent: Explore
allowed-tools: Bash(gh:*)
---

## Pull request context
- PR diff: !`gh pr diff`
- PR comments: !`gh pr view --comments`
- Changed files: !`gh pr diff --name-only`

## Your task
Summarize this pull request...

How it works:

1. Each !command`` executes immediately (before Claude sees anything)
2. The output replaces the placeholder in the skill content
3. Claude receives the fully-rendered prompt with actual PR data

This is preprocessing, not something Claude executes. Claude only sees the final result.

Source: Official documentation at https://code.claude.com/docs/en/skills.md (section: "Inject dynamic context")

---

Directory Structure

Copyskill-name/
├── SKILL.md              # Required
├── references/           # Optional: docs loaded on demand
├── scripts/              # Optional: executed, not loaded into context
└── templates/            # Optional: reusable content

Location Priority (Highest to Lowest)

1. Managed/Enterprise - System-level
2. Personal - ~/.claude/skills/
3. Project - .claude/skills/
4. Plugin - Bundled with plugins

---

Hooks in Skills

Hook Events

• PreToolUse: Before tool executes
• PostToolUse: After successful execution
• Stop: When Skill finishes

Hook Structure

Copyhooks:
  PreToolUse:
    - matcher: "Bash"           # Regex pattern
      hooks:
        - type: command
          command: "./scripts/check.sh"
          once: true            # Run only once per session

Hook I/O

• Receives JSON via stdin (session info, tool name, parameters)
• Exit 0: Success
• Exit 2: Blocking error (prevents tool, shows stderr)
• Other: Non-blocking error

---

Context Fork Behavior

Add context: fork to your frontmatter when you want a skill to run in isolation. The skill content becomes the prompt that drives the subagent. It won't have access to your conversation history.

WARNING: context: fork only makes sense for skills with explicit instructions. If your skill contains guidelines like "use these API conventions" without a task, the subagent receives the guidelines but no actionable prompt, and returns without meaningful output.

Agent Types

Copycontext: fork
agent: Explore

Tool Restrictions in Forked Contexts

VERIFIED BEHAVIOR (experimentally confirmed 2026-01-22):

When context: fork is set, the forked subagent has access to:

• File operations: Read, Write, Edit, Grep, Glob
• Web operations: WebSearch, WebFetch
• MCP tools (if configured)
• Bash and other system tools (depending on agent type)

The Task tool is NOT available in forked contexts. This means forked skills cannot delegate to other subagents. If you need hierarchical delegation (subagent delegates to another subagent), the parent must run in the main context (no context: fork), not in a forked context.

Source: Experimental verification on 2026-01-22. Official documentation at https://code.claude.com/docs/en/skills.md does not explicitly document this restriction.

Skills vs Subagents

Skills and subagents work together in two directions:

With context: fork, you write the task in your skill and pick an agent type to execute it. For the inverse (defining a custom subagent that uses skills as reference material), see the Sub-Agents documentation.

---

Description Best Practices

Good:

Copydescription: Extract text and tables from PDFs, fill forms, merge documents. Use when working with PDF files or when user mentions PDFs, forms, extraction.

Bad:

Copydescription: Helps with documents

Template:

Copy[Action 1], [Action 2], [Action 3]. Use when [situation 1], [situation 2],
or when the user mentions [keywords].

---

Examples

Simple Skill

Copy---
name: commit-messages
description: Generate conventional commit messages from git diffs. Use when writing commits.
---

# Commit Messages

1. Run `git diff --staged`
2. Determine type (feat, fix, docs)
3. Write message under 50 chars
4. Use imperative mood

Tool-Restricted

Copy---
name: safe-reader
description: Read files without changes. Use for code review.
allowed-tools:
  - Read
  - Grep
  - Glob
---

# Safe Reader

ONLY read files. Never modify.

Forked Context

Copy---
name: deep-research
description: Thorough codebase research. Use for complex investigations.
context: fork
agent: Explore
---

# Deep Research

Runs in isolated context to avoid polluting main conversation.

With Hooks

Copy---
name: secure-ops
description: Audit-logged file operations.
hooks:
  PreToolUse:
    - matcher: "Bash"
      hooks:
        - type: command
          command: "./scripts/security-check.sh"
          once: true
  PostToolUse:
    - matcher: "Write|Edit"
      hooks:
        - type: command
          command: "./scripts/lint.sh"
---

# Secure Operations

All modifications logged and validated.

Hidden from Users

Copy---
name: internal-standards
description: Auto-apply code review standards.
user-invocable: false
---

Claude invokes this, users don't see it in menu.

User-Only (No Auto-Invoke)

Copy---
name: deploy-production
description: Deploy to production.
disable-model-invocation: true
---

Only runs when user types `/deploy-production`.

---

Skills vs Other Features

Note: Skills and slash commands are now the same system. Files in .claude/commands/ still work but skills are recommended.

---

Installation

Marketplace:

Copy/plugin marketplace add anthropics/skills
/plugin install document-skills@anthropic-agent-skills

Manual: Copy to ~/.claude/skills/ or .claude/skills/

Hot Reload: Changes apply immediately without restart.

---

Recent Updates (2.1+)

• Unified skills and commands - .claude/commands/ files now work as skills, skills recommended
• Dynamic context injection - !command`` syntax for preprocessing shell command output
• argument-hint field - Show autocomplete hints for expected arguments
• Optional name/description - If omitted, uses directory name and first paragraph
• once: true for hooks - Run only once per session
• ${CLAUDE_SESSION_ID} - Session-scoped operations
• 15,000 character budget for skill metadata
• context: fork with agent selection
• Hot reload - immediate updates without restart

---

Sources

• Primary: Claude Code Skills Documentation (accessed 2026-01-22)
• Standards: Agent Skills Open Standard
• Examples: anthropics/skills
• Blog: Anthropic Engineering Blog - Agent Skills
• Experimental: Context fork tool restrictions verified 2026-01-22