Installed Skills Environment Check
Find why installed skills fail on this machine: missing CLIs, unset env vars, disconnected MCP servers, script permissions, name clashes.
Before & after
Same prompt, same agent — the only difference is the skill.
That's a good question to know if your setup is healthy. I can give you a general sense of what might be available based on what you've mentioned, but to really audit your skills, I'd need to know: Are you using a specific tool or framework that manages skills? Do you have a skills directory or manifest file? Are there any error messages you're seeing? If you can share your setup, I can help you assess what's installed and what might be broken.
SKILLS INVENTORY REPORT INSTALLED SKILLS (23 total) Active: 21 | Broken: 1 | Offline: 1 PRODUCTIVITY (5) ✓ Supermemory (cross-session memory) ✓ Folder Organizer (file organization) ✓ Video-to-Shorts (content repurposing) ✓ Sales Page Writer (conversion copy) ✗ Prompt Engineer (requires Playwright, disabled) DEVELOPMENT (8) ✓ React Expert ✓ Vue Expert JS ✓ Flutter Expert ✓ Senior Fullstack ✓ Spec to Repo ✓ API Designer ✓ Playwright (autonomous testing) ⚠ Claude Video Skill (needs ffmpeg, warn on use) DATA & ANALYTICS (3) ✓ Data Query (Snowflake connected) ✓ Vendor Management ✓ Skills General Counsel SALES & MARKETING (4) ✓ Sales (Prospect Prep) ✓ About-Me Cowork Setup ✓ Skills Status (this skill) ✓ Loki Instagram Captions BROKEN SKILLS (1) ✗ Prompt Engineer Toolkit Error: Playwright binary missing Fix: Run: npm install -D @playwright/test OFFLINE (1) ⚠ Vendor Management Status: Network timeout (API unreachable) Retry: Automatic (next 5 min) COMPATIBILITY CHECK All 21 active skills compatible with current CLI version NEXT STEPS Run: fix-broken-skills (fixes Prompt Engineer) Monitor: Vendor Management (expect reconnect soon)
About this skill
Your SKILL.md is fine but the skill still fails? This check diagnoses the error you paste, gives a read-only diagnostic script for the rest, and tells you exactly what is broken and the one command that fixes it.
What it does
- Finds skills across personal, project, and plugin locations and reports name collisions
- Checks scripts, interpreters, packages, and CLIs the skill calls
- Checks required environment variables for presence without ever printing values
- Verifies MCP servers and tool names a skill depends on, and permission rules that block it
- Reports and proposes fixes; runs checks only when you ask and never changes your setup without approval
What you get
A status table of every skill (broken, degraded, OK) with the problem and a concrete fix, plus collisions and anything it could not check.
Best for
Claude Code users with many skills or plugins, and teams debugging 'works on my machine' skill failures.
SKILL.md preview
---
name: skill-environment-check
… (sign up to view the full skill)More ai & agents skills
View all AI & Agents skills →New Skill Scaffolder
Create a new Claude Code skill correctly: right mechanism, valid name and folder, a triggering description, and a smoke test.
Skill Library Lint and Overlap Report
Lint every skill in a repo at once: frontmatter, name-folder match, weak descriptions, overlapping triggers, broken refs, plus a CI script.
Self-Verifying Agent Loop: Plan, Check, Retry, Close
Turns a goal into a task plan with machine-run checks, executes with retry caps, escalates, and refuses to close until verified.
Skill Test Runner (Trigger and A/B)
Test a skill in fresh sessions: ready-to-run prompts, commands, and rubric for trigger recall, false triggers, and blind A/B.