Index of every page on this site: llms.txt
All skills
qoderai avatar

/skill-review

@c6240a8
by qoderaiqoderai/better-harness2.5k stars
208
Run it yourself

Use when reviewing Codex, Qoder, or repo-local skills and their prompt chains for trigger quality, workflow clarity, progressive disclosure, duplicated instructions, template ownership, output readability, validation gaps, or whether a skill should be edited.

Use this Skill: https://skilld.dev/gh/qoderai/better-harness/skill-review

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesaudit-checklist.md

≈513 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Audit Checklist

Trigger contract

  • Frontmatter description states when to use the skill, not the workflow.
  • Name is short, hyphen-case, action-oriented, and discoverable by likely user words.
  • Body does not rely on a "when to use" section to fix weak metadata.

Progressive disclosure

  • SKILL.md holds only the main workflow, routing rules, and required invariants.
  • Detailed variants, schemas, examples, style rules, and long checklists live in directly linked references.
  • References are one hop from SKILL.md, named by the decision that loads them, and non-empty.

Workflow and delegation

  • The main workflow is explicit enough that an agent knows what to do first, what gates the next phase, and when to stop.
  • Subagents are part of the workflow only when they reduce real scope risk; they are not a decorative list of roles.
  • The lead agent owns final consistency, evidence quality, and output claims.

Template ownership

  • Base report templates own structure and parser-safe fields.
  • Runtime-specific templates own runtime rules such as Canvas, HTML, SDK imports, companion bullets, preview, and validation.
  • Style templates own visual grammar only. They should not duplicate runnable skeletons, shared SDK rules, or mode-selection logic.

Prompt and report readability

  • Cut explanations an AI can infer from headings, examples, or local code.
  • Prefer one concrete contract over repeated warnings in several files.
  • Replace placeholder walls, consecutive empty headings, and giant table rows with compact field requirements or one realistic example.
  • Keep exact labels, scoring scales, and parser-sensitive metadata centralized.

Evidence and validation

  • Every important review claim has a file path, line, command, diff, or artifact anchor.
  • Missing evidence is reported as missing or unverified, not filled by inference.
  • Validation checks the same surface the skill claims to support. For visual chains, build/preview/runtime validation is separate from Markdown review.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts3mo3 checks · Risk SAFE
  • Gen Agent Trust Hub3mo

    This skill provides a structured workflow for auditing and improving other AI agent skills within a repository. It utilizes common command-line utilities for repository inspection and is designed to patch identified issues. The identified behaviors, such as shell command execution and file editing, are consistent with its stated purpose as a developer tool.

  • Socket3mo

    No alerts

  • Snyk3mo

    Risk: LOW · No issues

Signed by skilld at c6240a8. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 4 months ago

README badge

README badge for qoderai/better-harness/skill-review