- Home
- Skills
- Agents & Orchestration
- fix broken claude skills
fix broken claude skills
Audit, debug, and fix Claude SKILL.md files to ensure they trigger reliably and follow official templates.
$5
Works with the AI Agents you already use
fix broken claude skills
Example session with this skill installed
Audit the SKILL.md in ./skills/data-fetcher. It's not triggering when I ask for database reports.
- Read your context and instructions
- Compiled the fix broken claude
Findings
- Critical: Frontmatter name 'DataFetcher' must be lowercase kebab-case.
- Major: Description is in first-person; needs third-person trigger phrases.
Fixed SKILL.md:
name: data-fetcher
description: Fetches raw data and generates SQL reports...
...
Verdict: ✅ DEPLOY-READY
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Skills often fail to trigger because of subtle frontmatter typos, vague descriptions, or invalid YAML. Manually debugging why an agent ignores a specific instruction is time-consuming and prone to trial-and-error.
What it does
- Audits SKILL.md files against official templates to find critical frontmatter and structural errors.
- Identifies hallucination risks where instructions reference non-existent scripts, files, or tools.
- Rewrites skill descriptions into high-performance, third-person trigger text for better routing.
- Provides a deploy-ready fixed file along with a severity-ranked findings report.
Why this beats prompting it yourself
General-purpose LLMs often overlook technical frontmatter requirements or silently hallucinate missing dependencies. This skill uses a specific checklist and validation script to ensure every line is load-bearing and compliant with the agent's router logic.
Use cases
- Debug a skill that is currently ignored by the agent during conversations.
- Standardize a large library of skills to ensure consistent behavior and formatting.
- Perform a pre-deployment QA check on new skills to catch silent failures before shipping.
Known limitations
This skill audits and edits file contents but does not perform filesystem operations like renaming folders without explicit confirmation.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Focuses on file content and frontmatter logic. Does not automatically rename directories on the filesystem without user permission.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 months ago