All skills
mblode avatar

/dx-audit

@b690e67
by Matthew Blodemblode/agent-skills134 stars
12

Audits libraries, CLIs, and SDKs using 38 rules for public contracts, package exports, piped output, errors, and configuration. Use when asked to "audit my CLI", "review my SDK", or diagnose package type resolution. For public site or docs agent scores use agent-ready; for agentic product trust use ax-audit; for docs prose use ghostwriter.

Use this Skill: https://skilld.dev/gh/mblode/agent-skills/dx-audit

This session only. Nothing lands on disk.

ruleserr-stable-error-codes.md

≈365 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Carry a Stable Code and Structured Fields, Not Just a Message

Callers handle specific failures programmatically. If the only discriminator is the message string, every consumer breaks the moment you reword it. Attach a stable code and a distinct error type, and put request-specific facts the caller needs (the offending parameter, a retry delay, a docs URL) in named fields rather than only interpolated into the message. Once those fields exist the message text can improve freely; Stripe's type/code/param/doc_url and Google's ErrorInfo.reason/metadata are the same split.

Incorrect (forces brittle message string-matching):

throw new Error("rate limit exceeded, retry after 2000ms");
// caller: if (err.message.includes("rate limit")) wait(parseInt(err.message.match(/\d+/)![0]));

Correct (typed error with a stable code and structured fields):

class RateLimitError extends Error {
  readonly code = "ERR_RATE_LIMIT";
  constructor(public readonly retryAfterMs: number, public readonly docUrl = "https://mytool.dev/errors#rate-limit") {
    super(`Rate limit exceeded. Retry after ${retryAfterMs}ms.`);
  }
}
// caller: if (err.code === "ERR_RATE_LIMIT") wait(err.retryAfterMs);

Source: SKILL.md on GitHub

No alerts9d3 checks · Risk SAFE
  • Gen Agent Trust Hub9d

    The dx-audit skill is a developer experience auditing tool designed to review public APIs, CLIs, and SDKs. It demonstrates a strong security posture by including explicit instructions to validate inputs against path traversal and shell injection, and by warning the agent to inspect potentially malicious lifecycle scripts in audited repositories before running packaging probes. All external tools mentioned are industry-standard utilities.

  • Socket9d

    No alerts

  • Snyk9d

    Risk: LOW · No issues

Signed by skilld at b690e67. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated last week

README badge

README badge for mblode/agent-skills/dx-audit