Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    Skill Surgeon: Find and Fix Skill Problems

    1

    Review agent skills for structure, references and security, with traceable findings and proposed fixes.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Skill Surgeon: Find and Fix Skill Problems

    Example session with this skill installed

    Audit this local skill folder without executing embedded commands. Report broken references, unclear permissions and security concerns. Show proposed patches without applying them.

    • Read your context and instructions
    • Compiled the surgeon

    I have completed the audit of the SKILL.md file. The analysis focused on structural validity, reference integrity, and security hygiene. One critical security risk was identified alongside two structural warnings.

    Skill Audit Report: ./SKILL.md

    Issue IDSeverityCategoryFindingRecommended Fix
    SEC-001CriticalSecurityFound rm -rf / in a cleanup exampleReplace with targeted file deletion
    STR-002WarningStructureMissing agensi-tags in YAML frontmatterAdd tags to improve marketplace discovery
    STR-003WarningStructureBroken relative link to LICENSE.txtUpdate path to absolute or correct relative loc

    Validation Score: 65/100

    • Structural validity: 20/30
    • Reference integrity: 15/20
    • Instruction clarity: 20/20
    • Security hygiene: 0/20
    • Documentation quality: 10/10

    Suggested Fixes

    --- SKILL.md
+++ SKILL.md
@@ -4,6 +4,7 @@
 metadata:
   agensi-title: "Example Skill"
   agensi-description: "A sample skill for testing."
+  agensi-tags: automation, productivity
 ---
 
 # Example Skill
@@ -45,5 +46,5 @@
 
 ## Cleanup
-To reset the environment, run `rm -rf /`.
+To reset the environment, delete the specific `./tmp/session` directory.

    Next steps

    1. Review the proposed diff above for accuracy.
    2. Run with mode: fix to automatically apply the metadata and cleanup fixes.
    3. Verify the existence of the LICENSE.txt file to resolve the broken reference.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Skill Surgeon is a single instruction skill for an AI agent that can read SKILL.md and work with user-supplied context. Place the skill in your agent's documented skill location after checking its format requirements. Installation compatibility has not been tested.

    The instructions guide the agent through a structured review or planning workflow. This draft package contains the skill document, not a standalone application. Its source marks the release as NOT READY FOR RELEASE.

    The problem

    Unstructured requests can hide missing requirements, weak evidence and unsafe assumptions. This skill specifies what the agent should examine, how to report uncertainty and what the output should contain.

    What you get

    PartIncluded
    Instruction skill1 SKILL.md
    Bundled scripts0
    Reference files0
    Plugin manifestNone found
    LicenseNot supplied

    How it works

    The agent follows the instructions using its own available tools. The package does not supply an executable engine. Every conclusion still needs evidence from the user's input.

    Uses

    Review YAML frontmatter. Request a focused deliverable with evidence and stated limitations. Try: "Review YAML frontmatter for the supplied input. State assumptions and identify what needs verification."

    Check referenced files. Request a focused deliverable with evidence and stated limitations. Try: "Check referenced files for the supplied input. State assumptions and identify what needs verification."

    Review activation conditions. Request a focused deliverable with evidence and stated limitations. Try: "Review activation conditions for the supplied input. State assumptions and identify what needs verification."

    Find contradictory instructions. Request a focused deliverable with evidence and stated limitations. Try: "Find contradictory instructions for the supplied input. State assumptions and identify what needs verification."

    Review unsafe command patterns. Request a focused deliverable with evidence and stated limitations. Try: "Review unsafe command patterns for the supplied input. State assumptions and identify what needs verification."

    Explain weighted scoring. Request a focused deliverable with evidence and stated limitations. Try: "Explain weighted scoring for the supplied input. State assumptions and identify what needs verification."

    Suggest reversible patches. Request a focused deliverable with evidence and stated limitations. Try: "Suggest reversible patches for the supplied input. State assumptions and identify what needs verification."

    Revalidate approved changes. Request a focused deliverable with evidence and stated limitations. Try: "Revalidate approved changes for the supplied input. State assumptions and identify what needs verification."

    Guardrails

    Do not claim tests passed, changes were applied or external actions completed without evidence. Review permissions and uncertainty before acting. The underlying agent determines actual access and data handling.

    Who it is for

    People who want structured assistance for this domain and can review the result. The current draft is not for buyers expecting tested software, a complete command-line tool or verified platform integrations.

    Safe handling

    Only provide inputs you are authorized to process. The package has no bundled executable scripts, network client or credentials. This does not make the host AI agent offline: its provider and tool settings determine how data is processed.

    How to use

    Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed 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 scanned

    Verified clean 6 days ago

    • Passed all security checks, Safe to install

    Listed6 days ago

    What's inside

    Frequently Asked Questions