More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    skilllint - Vet Agent Skills Before You Install

    1

    Private lint of agent skills: structure, triggers, secrets, injection, broken refs. Offline, verdict + SHA-256.

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    skilllint - Vet Agent Skills Before You Install

    skilllint - Vet Agent Skills Before You Install

    Example session with this skill installed

    Lint the SKILL.md at ./agents/weather-fetcher/SKILL.md and tell me if it is safe to install.

    • Read your context and instructions
    • Compiled the skilllint - vet

    Summary

    The candidate skill xmtplabs/xmtp-agent-examples was linted and failed. It has no
    frontmatter, so there is no description for an agent to match against and no reliable way
    to know the skill exists or when to reach for it. The package may still be good
    documentation - as an agent skill it is unreachable.

    Verdict

    MetricValue
    VerdictFAIL
    Score50/100
    SHA-256b9757a1d905df1061b2662fe2cc148c8335ee8d43f876c3a065b0db9956f55be
    File size1,633 bytes

    Findings

    • R-001 (critical) - frontmatter (--- ... ---) not found
    • R-002 (high) - name is missing or malformed: ''
    • R-003 (high) - description is missing
    • R-008 (medium) - referenced file not found: skills/building-agents/

    Raw output

    {
      "skill": "xmtplabs__xmtp-agent-examples__skills_SKILL",
      "path": "/tmp/opencode/skills-check/xmtplabs__xmtp-agent-examples__skills_SKILL/SKILL.md",
      "score": 50,
      "verdict": "FAIL",
      "sha256": "b9757a1d905df1061b2662fe2cc148c8335ee8d43f876c3a065b0db9956f55be",
      "bytes": 1633,
      "findings": [
        {
          "rule": "R-001",
          "severity": "critical",
          "message": "frontmatter (--- ... ---) not found",
          "line": null
        },
        {
          "rule": "R-002",
          "severity": "high",
          "message": "name is missing or malformed: ''",
          "line": null
        },
        {
          "rule": "R-003",
          "severity": "high",
          "message": "description is missing",
          "line": null
        },
        {
          "rule": "R-008",
          "severity": "medium",
          "message": "referenced file not found: skills/building-agents/",
          "line": null
        }
      ]
    }
    

    What the agent does with this

    The verdict is FAIL, so the skill is not installed. The four rule ids are reported back to
    whoever sent the candidate, because a rejection with rule ids is actionable for the author
    and a rejection with adjectives is not. The SHA-256 is kept: re-lint the same bytes later
    and the verdict is identical, and a changed hash means the skill is not the one that was
    vetted.

    The check was local: the file was read on this machine, nothing was uploaded, and the
    verdict carries the hash of exactly the bytes that were checked.

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

    About this skill

    A skill is an instruction set that gets injected into an agent's context, and three failures dominate - none of them announces itself.

    It never fires: no trigger wording in the description, so the agent never reaches for the capability. Nothing errors, you just never get it.

    It fires everywhere: a vague description plus a 100 KB file means every relevant request pays for the whole thing.

    It carries something: a secret literal, an injection marker, or "act without asking".

    This skill makes that check local, private and reproducible. The candidate's bytes are read on your machine, nothing is uploaded anywhere, and the verdict comes with the SHA-256 of exactly what was checked.

    What the check covers:

    • structure: frontmatter, name, description, trigger wording
    • consistency: dead instructions (TODO/deprecated/placeholder), references to files that are not in the package, files over 60 KB
    • safety: literals that look like secrets, prompt-injection and exfiltration markers, instructions that grant unbounded autonomy

    The verdict is PASS / WARN / FAIL with a score, the findings (rule id, severity, message) and the sha256 of the bytes that were checked - so the same file always produces the same verdict, and a changed file changes the hash. The hash is the input for a signed receipt and for an allowlist.

    When several candidates are in play, compare_skills ranks them by verdict, then score, then size, and shows the evidence side by side.

    Runs fully offline with the bundled script (standard library only). The hosted MCP endpoint is optional, not required.

    • SKILL.md - the check loop the agent follows

    • reference/rules.md - the 11 rules, what fires them, how to fix each

    • reference/setup.md - local and hosted connection, how to read a verdict

    • reference/candidates.md - comparing candidates, what to ask the author

    • scripts/linter.py - the linter itself, standard library only

    • Static analysis: it reads bytes, never executes the skill and never runs its scripts. A skill can pass the lint and still be wrong.

    • PASS means "structure is sound", never "safe". Eleven rules are an opinionated minimum, not a threat model.

    • The "referenced file not found" check only means something when the whole package is present: lint the directory, not a lone file.

    • The linter is opinionated and argues with itself in public: we lint our own skill with it, and we publish both our findings and our own false positives.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Prompt & Skill Engineering.

    Static analysis only: it reads bytes, never executes the skill and never runs its scripts - a skill can pass the lint and still be wrong.
    PASS means 'structure is sound', never 'safe': eleven rules are an opinionated minimum, not a threat model.
    The 'referenced file not found' check only means something when the whole package is present - lint the directory, not a lone file.
    The linter argues with itself in public: we lint our own skill with it and publish our own false positives.
    The checker decides; it never installs anything and never modifies the candidate.

    How to use

    1. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 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 27 days ago

    Software
    Python 3.10+

    Permissions

    Terminal / Shell
    Read Files

    File Scopes

    **/SKILL.md

    The skill reads a candidate SKILL.md from disk and writes a verdict to stdout. It does not write files, does not open a browser and makes no network calls. The hosted MCP endpoint is optional - everything works offline.

    Listed27 days ago

    What's inside

    Frequently Asked Questions

    skilllint performs a private, 11-rule static audit of agent instructions to identify "dead triggers" that never fire, security risks like prompt-injection markers, and excessive token usage that slows down your AI.

    Yes, it is fully compatible with any MCP-enabled environment like Claude Code and Cursor, and can also be run as a standalone Python utility for local workflows.

    No, skilllint performs local, offline static analysis using only the Python standard library, ensuring your sensitive skill code and prompts never leave your machine during the audit.

    The tool provides a structured report with a 0-100 score, a status verdict (PASS/WARN/FAIL), and a SHA-256 hash to ensure the code you vetted is exactly what you deploy.

    You receive the full Python source of the linter (standard library only), the rule reference with all eleven rules and how to fix each, the setup guide for local and hosted use, and the guide for comparing candidate skills. The hosted MCP endpoint is optional and is not part of the package.

    Because it uses static analysis, it does not execute the skill code; it requires all referenced files to be in the target directory to prevent false negatives regarding missing dependencies.

    New in Prompt & Skill Engineering