prompt-audit SKILL.md skillA
prompt-audit from appleboy/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add appleboy/skills/prompt-audit@git:20260606.832a70aPins git:20260606.832a70a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- appleboy/skills
- Path
plugins/prompt-audit/skills/prompt-audit/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260606.832a70a, committed Jun 6, 2026
- First version recorded
- Apr 29, 2026
- Size
- 6,465 bytes
- Repository stars
- 23
- License
- none declared
Audit a prompt the user is about to send to Claude (or another coding AI) for completeness and effectiveness. Use this skill whenever the user shares a prompt and asks for feedback — phrases like "is this prompt good", "audit my prompt", "review this prompt", "will Claude understand this", "improve this prompt", "is this enough context". Also trigger proactively when you notice the user is about to dispatch a vague, under-specified, or over-constrained prompt for non-trivial work. Checks the 6…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# prompt-audit Most AI-coding failures trace back to thin prompts. A prompt that takes 30 seconds to write and 2 minutes for Claude to "execute" produces code that takes 2 hours to fix. This skill catches that before it happens. ## When to use Use whenever the user is evaluating, drafting, or about to send a prompt for non-trivial coding work. Triggers include: - "Is this prompt good?" - "Audit / review / check my prompt" - "Will Claude understand this?" - "How do I improve this prompt?" - The user pastes a prompt and asks anything about it - You notice the user is about to send a vague prompt for a complex task — proactively offer to audit it Don't audit: - Single-line throwaway prompts the user is happy with - Pure conversation / clarification messages (not actual task prompts) ## The six essential elements A good coding prompt for non-trivial work has all six. Missing any one drops the success rate noticeably. | # | Element | What it answers | Why it matters | |---|---|---|---| | 1 | **Goal** | What problem are we solving? Who uses the result? | Without a goal, Claude optimizes the wrong thing | …
Read the whole file at its exact version.
How to install
mdr add appleboy/skills/prompt-audit@sha256:490990e26696fa94The line at the top of this page pins the label git:20260606.832a70a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_folm3w5m2ennp2yt)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Apr 29, 2026 and Jun 6, 2026, about one every 38 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260606.832a70a latest | 2026-06-06 | 832a70a | 6,465 B | A | view · diff |
| git:20260429.fa68ec9 | 2026-04-29 | fa68ec9 | 6,466 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6465 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
appleboy/skills · 23 stars · license none declared · pushed 2026-09-12 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_folm3w5m2ennp2yt GET https://markdownregistry.com/api/v1/resolve?ref=appleboy/skills/prompt-audit GET https://markdownregistry.com/api/v1/blob/490990e26696fa94af22d4b56730fee869f8021f2783a507a277f038c796efce
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.