From director-mode-lite
Validates SKILL.md files for correct frontmatter YAML format, required fields like name and description, optional configs like allowed-tools and hooks, and content structure. Ensures skills conform to Claude Code standards.
How this skill is triggered — by the user, by Claude, or both
Slash command
/director-mode-lite:skill-checkThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Validate skill files for correct format.
Validate skill files for correct format.
.claude/skills/*/SKILL.md---
name: skill-name # Required: lowercase, hyphenated
description: What it does # Required: shown in / menu
version: 0.1.0 # Optional: semantic version
user-invocable: true # Optional: default true
model: sonnet # Optional: inherit, haiku, sonnet, opus, best, sonnet[1m], opus[1m], opusplan
allowed-tools: # Optional: restrict tools (YAML list)
- Read
- Write
- Bash
context: fork # Optional: isolated context
agent: agent-name # Optional: run as specific agent
argument-hint: "<hint>" # Optional: hint for arguments
when_to_use: Description of when this skill should be used # Optional: underscore format
arguments: # Optional: structured argument definitions
- name: arg-name
description: What the argument does
required: true
disable-model-invocation: false # Optional: prevent programmatic invocation
hooks: # Optional: lifecycle hooks (same format as settings.json)
PreToolUse:
- matcher: Write
hooks:
- type: command
command: ./scripts/validate.sh
PostToolUse:
- matcher: Bash
hooks:
- type: command
command: ./scripts/log.sh
Stop:
- hooks:
- type: command
command: ./scripts/verify.sh
once: true
---
Read, Write, Edit, Bash, Grep, Glob, Task,
WebFetch, WebSearch, TodoWrite, NotebookEdit
name exists (lowercase, hyphenated)description existsallowed-tools are valid tool names (if specified)allowed-tools uses YAML list format (if specified)agent references existing agent file (if specified)version is valid semver format (if specified)model is valid value: inherit, haiku, sonnet, opus, best, sonnet[1m], opus[1m], opusplan (if specified)context is valid value: fork (if specified)argument-hint is a string (if specified)when_to_use is a descriptive string (if specified)arguments is a valid array with name/description/required entries (if specified)disable-model-invocation is boolean (if specified)hooks has valid structure (if specified)$ARGUMENTS if expecting input## Skill Validation Report
### Files Checked
| File | Status | Issues |
|------|--------|--------|
| workflow/SKILL.md | OK | None |
| my-skill/SKILL.md | WARN | Missing description |
### Summary
- Total: [N]
- Valid: [N]
- Needs fixes: [N]
name from directory namedescription$ARGUMENTS handlingnpx claudepluginhub claude-world/director-mode-liteValidates SKILL.md files against agentskills specification and Anthropic best practices. Catches structural, semantic, naming, and quality issues before publishing or debugging triggers.
Internal development tool that validates all SKILL.md and agent .md files against the Claude Code spec. Checks frontmatter completeness, field validity, allowed-tools presence, line count, hardcoded paths, and description quality. Use when the user says "lint skills", "validate skills", "check skill quality", "run the linter", "are my skills valid", or before shipping changes to the skills repo.
Validates SKILL.md files against the agentskills.io standard, checking YAML frontmatter, required sections, line count limits, procedure format, and registry sync. Use before merging new or modified skills.