prompt-rewrite SKILL.md skillA

prompt-rewrite from leahycc/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add leahycc/claude-skills/prompt-rewrite@git:20261102.543b89a

Pins git:20261102.543b89a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
leahycc/claude-skills
Path
skills/prompt-rewrite/SKILL.md
Versions recorded
4
Latest version
git:20261102.543b89a, committed Nov 2, 2026
First version recorded
Oct 23, 2026
Size
8,260 bytes
Repository stars
3
License
MIT

Rewrites a thin coding prompt into a deep one before it runs: same scope, plus the raw material to start from, the tools an expert would use, an existing file to copy, and a proof a third party can check. Covers refactoring, performance, UI, UX, API, frontend, debugging, testing, security, accessibility, docs, and planning, for a session, a `claude -p` run, a subagent brief, or a system prompt. Use when the user says "rewrite my prompt", "improve this prompt", "make this prompt better…

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 rewrite

Turn a thin prompt into one that gets expert work. **Deeper, not bigger.** The rewrite keeps the same scope. It adds what a top practitioner would start from, what they would reach for, and what proof shows the result is right.

Every line added must name a file, a tool, a number, a check, or a reason. If a line could be pasted into any prompt ("write clean, robust, best-in-class code"), delete it.

Source checks: [SOURCES.md](SOURCES.md). Test cases for this skill: [evals.md](./resources/evals.md).

## Procedure

```
draft prompt
     |
     v
1. look first -------> open the code, data, docs it points at
     |
     v
2. size it ----------> one-sentence diff?  -> short prompt
     |                 multi-file / unclear -> full prompt + plan gate
     |                 new feature, open design -> interview prompt
     v
3. ask (maybe) ------> 1 to 4 questions, only if an answer changes the prompt
     |
     v
4. four answers -----> pros do / raw material / tools / proof
     |
     v
5. fill template ----> resources/template.md
     |
     v
6. hand back --------> four answers, the prompt, how to enforce the proof
```
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add leahycc/claude-skills/prompt-rewrite@sha256:4df03351e0c4e6ca

The line at the top of this page pins the label git:20261102.543b89a, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_rnl32of5gl6woyuv.svg)](https://markdownregistry.com/a/art_rnl32of5gl6woyuv)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between Oct 23, 2026 and Nov 2, 2026, about one every 3 days.

versioncommittedcommitsizeaudit
git:20261102.543b89a latest2026-11-02 543b89a 8,260 BA view · diff
git:20261023.9ecc8c12026-10-23 9ecc8c1 6,911 BA view · diff
git:20261023.5e2a3c92026-10-23 5e2a3c9 7,049 BA view · diff
git:20261023.5bf738e2026-10-23 5bf738e 6,613 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8260 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

GitHub

leahycc/claude-skills · 3 stars · license MIT · pushed 2026-11-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_rnl32of5gl6woyuv
GET https://markdownregistry.com/api/v1/resolve?ref=leahycc/claude-skills/prompt-rewrite
GET https://markdownregistry.com/api/v1/blob/4df03351e0c4e6ca8aada65ff71d86f90e89610341846dd1112734fb1b504192

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.

More from leahycc/claude-skills

api-security SKILL.md skill
leahycc/claude-skills · skills/api-security/SKILL.md · OWASP API Security Top 10 (2023) with production Next.js App Router code. Access control, authentication with MFA and…
git:20261102.e28ea25 · audit A · 3 stars
ascii-art SKILL.md skill
leahycc/claude-skills · skills/ascii-art/SKILL.md · Use when drawing anything out of text characters, for work or fun. Diagrams (flowcharts, architecture, sequence, state…
git:20261025.9e9380f · audit A · 3 stars
code-readability SKILL.md skill
leahycc/claude-skills · skills/code-readability/SKILL.md · Makes code readable at the point of use: no floating (magic) numbers or strings without a name or a unit-and-why note…
git:20261024.79f60eb · audit A · 3 stars
gotchas SKILL.md skill
leahycc/claude-skills · skills/gotchas/SKILL.md · Catches silent bugs that look right in a diff, compile clean, and pass happy-path tests: 200 OK HTML stand-ins…
git:20261024.bd7364e · audit A · 3 stars
llm-agent-security SKILL.md skill
leahycc/claude-skills · skills/llm-agent-security/SKILL.md · Defensive review when a model can see untrusted content or act with real credentials. Covers prompt injection as an…
git:20261024.77a47ac · audit A · 3 stars
nextjs-app-router SKILL.md skill
leahycc/claude-skills · skills/nextjs-app-router/SKILL.md · Build, review, or migrate Next.js App Router applications with version-aware component boundaries, data fetching…
git:20261023.9ecc8c1 · audit A · 3 stars
plain-docs SKILL.md skill
leahycc/claude-skills · skills/plain-docs/SKILL.md · Use when writing or fixing documentation: README files, guides, how-tos, API references, concept pages, and ADRs. Cuts…
git:20261024.4f72c1b · audit A · 3 stars
product-marketing SKILL.md skill
leahycc/claude-skills · skills/product-marketing/SKILL.md · Product management and marketing strategy — positioning, discovery, go-to-market, prioritization, metrics, copywriting…
git:20261027.631e1bd · audit A · 3 stars
react-performance SKILL.md skill
leahycc/claude-skills · skills/react-performance/SKILL.md · Use when optimizing React component rendering, fixing Core Web Vitals (LCP, INP, CLS), reducing bundle size, diagnosing…
git:20261102.80f14b4 · audit A · 3 stars
react-testing SKILL.md skill
leahycc/claude-skills · skills/react-testing/SKILL.md · Writes and reviews React component tests with Vitest 5, React Testing Library 16, user-event 14, jest-dom 7, and MSW 3…
git:20261101.7fd4399 · audit A · 3 stars
seo SKILL.md skill
leahycc/claude-skills · skills/seo/SKILL.md · Use when adding metadata, creating sitemaps, generating robots.txt, implementing structured data (JSON-LD), optimizing…
git:20261027.631e1bd · audit B · 3 stars
spa-performance SKILL.md skill
leahycc/claude-skills · skills/spa-performance/SKILL.md · Use when an SPA is slow because of the main thread, frame time, or memory: Web Workers, OffscreenCanvas…
git:20261024.af7209a · audit A · 3 stars

Every file in leahycc/claude-skills

Browse by kind, by grade A, or by owner.