From claudelint
Validates Claude Code skills for schema, naming, documentation, and security. Helps troubleshoot skill loading errors and dangerous command detection.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claudelint:validate-skills [flags][flags]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Runs `claudelint validate-skills` to validate Claude Code skill directories.
Runs claudelint validate-skills to validate Claude Code skill directories.
claudelint validate-skills $ARGUMENTS
--path <path> - Custom path to skills directory--skill <name> - Validate specific skill--verbose - Show detailed output--warnings-as-errors - Treat warnings as errorsUser says: "I see my skill /deploy-app in the menu but when I run it, Claude says it can't find it" What happens:
deploy-app/ but SKILL.md has name: deployAppname: deploy-appResult: Skill executes correctly after fixing name mismatch
User says: "My skill script.sh needs to run bash commands but Claude says 'Tool Bash not allowed'" What happens:
allowed-tools: ["bash", "read"]allowed-tools: ["Bash", "Read"]Result: Claude can now execute bash commands in the skill
User says: "Pre-commit hook is failing on my cleanup skill with 'dangerous command detected: rm -rf'" What happens:
rm -rf $TEMP_DIR$TEMP_DIR could be empty or / (dangerous)[[ -n "$TEMP_DIR" && "$TEMP_DIR" != "/" ]] && rm -rf "$TEMP_DIR"Result: Skill now validates paths before deletion, commit succeeds
Validate all skills:
claudelint validate-skills
Validate specific skill:
claudelint validate-skills --skill my-skill
name field must match directory namedescription must be present0 - No errors or warnings1 - Warnings found2 - Errors foundFor troubleshooting, see common issues. For customization, see configuration.
npx claudepluginhub pdugan20/claudelint --plugin claudelintGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.