polish SKILL.md skillB

polish from tenequm/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add tenequm/skills/polish@v3.1.0

Pins v3.1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
tenequm/skills
Path
skills/polish/SKILL.md
Versions recorded
5
Latest version
v3.1.0, committed Sep 9, 2026
First version recorded
Sep 9, 2026
Size
24,993 bytes
Repository stars
40
License
MIT

Pre-release code review - lint and type checks, parallel review agents (cleanliness, design, efficiency, side-effect gating), findings validated, fixes on approval. Reviews a GitHub PR when given one. Run before committing, pushing, or on a PR.

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

# Pre-Release Polish

Argument (optional): $ARGUMENTS

## Setup

The argument selects what gets reviewed:

- **Nothing, or a git ref** - local mode. Review the working tree or branch (Phase 2).
- **A GitHub PR** - PR mode. Anything that identifies one counts: a URL, a bare number, "PR 42",
  "the PR for this branch". Resolve it with `gh`:
  - In the repo: `gh pr view <n> --json title,body,author,baseRefName,headRefName`, then `gh pr checkout <n>`
  - Not in the repo: `gh repo clone <owner>/<repo> /tmp/<owner>-<repo>-pr-<n> -- --depth=50` and work
    there, passing `-R <owner>/<repo>` to every `gh` call since a shallow clone has no default remote
  - If the user names an existing clone ("... in ~/pj/my-clone"), use that instead of cloning

### Fix mode vs review mode

The modes disagree on whether you may edit the tree and whose CLAUDE.md you may execute, so the mode
is decided once, here, from the argument - never re-derived from repository state in a later phase.

- Local (no PR): always **fix mode**.
- PR authored by the current user (`gh pr view <n> --json author` vs `gh api user --jq .login`):
  **fix mode**. It is your own branch - polish it exactly as if it were local work.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add tenequm/skills/polish@sha256:9830735c08d98132

The line at the top of this page pins the label v3.1.0, 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_qks3dwfom7l6wkbq.svg)](https://markdownregistry.com/a/art_qks3dwfom7l6wkbq)

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

Versions

The registry has recorded 5 versions of this file, all committed on Sep 9, 2026. Its first recorded version is graded A and its latest B.

versioncommittedcommitsizeaudit
v3.1.0 latest2026-09-09 75ee2d0 24,993 BB view · diff
v3.0.02026-09-09 0021c9b 22,397 BB view · diff
v2.7.02026-09-09 92fc04c 16,633 BB view · diff
v2.6.22026-09-09 7581ac6 15,732 BA view · diff
v2.6.12026-09-09 532dedd 15,896 BA view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No prompt-injection phrasing (matched: ignore previous instructions)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (24993 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 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

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

tenequm/skills · 40 stars · license MIT · pushed 2026-10-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_qks3dwfom7l6wkbq
GET https://markdownregistry.com/api/v1/resolve?ref=tenequm/skills/polish
GET https://markdownregistry.com/api/v1/blob/9830735c08d9813254e8d9ebe541ed368f56c9c7d54b8a66321ae72df4a7a323

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 tenequm/skills

CLAUDE.md@.claude CLAUDE.md file
tenequm/skills · .claude/CLAUDE.md
git:20260821.b16c242 · audit A · 40 stars
audio-quality-check SKILL.md skill
tenequm/skills · archive/audio-quality-check/SKILL.md · Analyzes audio recording quality - echo detection, loudness, speech intelligibility, SNR, and spectral analysis. Use…
v0.1.4 · audit A · 40 stars
cloudflare-workers SKILL.md skill
tenequm/skills · archive/cloudflare-workers/SKILL.md · Rapid development with Cloudflare Workers - build and deploy serverless applications on Cloudflare's global network…
v3.1.3 · audit A · 40 stars
grafana-foundation-sdk SKILL.md skill
tenequm/skills · archive/grafana-foundation-sdk/SKILL.md · Build Grafana dashboards as code with the grafana-foundation-sdk typed builders (TypeScript or Go). Use when creating…
v0.2.4 · audit A · 40 stars
privy-integration SKILL.md skill
tenequm/skills · archive/privy-integration/SKILL.md · Integrates Privy authentication, embedded wallets, and agent payment protocols into web and agentic apps. Covers React…
v0.4.4 · audit A · 40 stars
web3-protocol-gtm SKILL.md skill
tenequm/skills · archive/web3-protocol-gtm/SKILL.md · Go-to-market strategy for web3 builders - protocols, products, services, and solo founders. Use when planning growth…
v0.2.6 · audit A · 40 stars
acpx-faq SKILL.md skill
tenequm/skills · skills/acpx-faq/SKILL.md · Run coding agents (codex, claude, agy) through the acpx ACP CLI - one-shot dispatch into named sessions you can watch…
v0.10.0 · audit A · 40 stars
chrome-extension-wxt SKILL.md skill
tenequm/skills · skills/chrome-extension-wxt/SKILL.md · Build Chrome extensions with the WXT framework and TypeScript, React, Vue, or Svelte. Use when creating browser…
v1.1.5 · audit B · 40 stars
effect-ts SKILL.md skill
tenequm/skills · skills/effect-ts/SKILL.md · Effect-TS guide for TypeScript, v4 default with v3 support. Use when writing, debugging, or reviewing Effect code…
v0.6.5 · audit A · 40 stars
erc-8004 SKILL.md skill
tenequm/skills · skills/erc-8004/SKILL.md · Build with ERC-8004 Trustless Agents - on-chain agent identity, reputation, validation, and discovery on EVM chains…
v0.2.4 · audit A · 40 stars
founder-playbook SKILL.md skill
tenequm/skills · skills/founder-playbook/SKILL.md · Decision validation and thinking frameworks for founders. Use to pressure-test a decision, validate next steps, or…
v0.1.6 · audit A · 40 stars
foundry-solidity SKILL.md skill
tenequm/skills · skills/foundry-solidity/SKILL.md · Build and test Solidity contracts with Foundry. Use when developing Ethereum contracts, writing Forge tests, deploying…
v0.2.5 · audit A · 40 stars

Every file in tenequm/skills

Other files named polish

polish SKILL.md skill
educlopez/ui-craft · .agents/skills/polish/SKILL.md · Final craft pass applying the compound details from the polish checklist — micro-typography, spacing rhythm, hover…
git:20260806.bb71f4d · audit A · 425 stars
polish SKILL.md skill
educlopez/ui-craft · .codex/skills/polish/SKILL.md · Final craft pass applying the compound details from the polish checklist — micro-typography, spacing rhythm, hover…
git:20260806.bb71f4d · audit A · 425 stars
polish SKILL.md skill
quriosity-agent/qcut · qcut/.agents/skills/polish/SKILL.md · Final quality pass before shipping. Fixes alignment, spacing, consistency, and detail issues that separate good from…
git:20260308.8b86d2e · audit A · 43 stars
polish SKILL.md skill
travsteward/openwriter · skills/polish/SKILL.md · Polish copy to 90/100. Channel the top 10 advertising practitioners in history. Score, rewrite, score again. Don't stop…
v0.1.0 · audit A · 36 stars
polish SKILL.md skill
vzakharov/muthur · .claude/skills/polish/SKILL.md · Run the standard quality passes over work just done — `/dry`, then `/tend-prose` — scoped to what the branch has…
git:20261016.bb62c02 · audit B · 22 stars
polish SKILL.md skill
wpgaurav/wordpress-skills · skills/design/polish/SKILL.md · Final quality pass before shipping. Fixes alignment, spacing, consistency, and detail issues that separate good from…
git:20261024.783ca3d · audit A · 19 stars
polish SKILL.md skill
hyemin-ht-kang/better-korean · plugins/better-korean/skills/polish/SKILL.md · 한국어 텍스트에서 어색하고 장황한 표현을 찾아 자연스러운 문장으로 고칠 것을 제안한다. 사용자가 "/polish", "$polish", "윤문", "한국어 리뷰 해줘", "AI 말투 정리해줘", "이 문서…
git:20261002.c98a423 · audit A · 7 stars
polish SKILL.md skill
inkatze/planwright · skills/polish/SKILL.md · Autonomous act-then-review convergence loop: iterate /self-review passes, draining every action disposition…
git:20261101.13a74a0 · audit A · 5 stars

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