implement-review SKILL.md skillB

This file is byte-identical to the first copy the registry indexed, one of 3 indexed copies. Same content hash, so the same checks give both the same grade.

implement-review from yzhao062/agent-config is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add yzhao062/agent-config/implement-review@git:20261019.917207c

Pins git:20261019.917207c in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
yzhao062/agent-config
Path
skills/implement-review/SKILL.md
Versions recorded
13
Latest version
git:20261019.917207c, committed Oct 19, 2026
First version recorded
Sep 25, 2026
Size
154,500 bytes
Repository stars
16
License
none declared

Review loop for staged changes. Detects content type, prepares a review request for Codex (Terminal-relay manual default, opt-in Auto-terminal codex-exec subprocess, or IDE plugin) or an explicitly selected Agy, Copilot, or headless Claude backend, categorizes feedback, revises, and iterates. Works for code, papers, proposals, or any text-based output.

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

# Implement-Review

## Overview

A review loop for staged changes. Claude Code detects the content type, sends the changes to one or more reviewers, categorizes the feedback, revises, and iterates. Codex is the primary reviewer via three channels: terminal relay (manual copy-paste, default on every platform), Auto-terminal (opt-in subprocess dispatch), or IDE plugin. The Auto-terminal channel also supports explicit cross-vendor reviewer backends for GitHub Copilot CLI, Claude Code, and Gemini through Antigravity CLI. Other reviewers are driven ad-hoc by the user through their own UI and only need to honor the `Review-<AgentName>.md` save contract defined in Phase 1c. Bare `/implement-review auto` is unchanged and still selects Codex.

## When to plan-review first
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add yzhao062/agent-config/implement-review@sha256:83e23473ba2dd1f0

The line at the top of this page pins the label git:20261019.917207c, 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_w7x7pcd5krjkbtux.svg)](https://markdownregistry.com/a/art_w7x7pcd5krjkbtux)

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

Versions

The registry has recorded 13 versions of this file, between Sep 25, 2026 and Oct 19, 2026, about one every 2 days.

versioncommittedcommitsizeaudit
git:20261019.917207c latest2026-10-19 917207c 154,500 BB view · diff
git:20261018.3693c512026-10-18 3693c51 154,545 BB view · diff
git:20261017.c9a6cdf2026-10-17 c9a6cdf 154,181 BB view · diff
git:20261016.8bc00ac2026-10-16 8bc00ac 154,061 BB view · diff
git:20261013.4e3f1432026-10-13 4e3f143 153,565 BB view · diff
git:20261008.7485eba2026-10-08 7485eba 153,212 BB view · diff
git:20261007.002b1d52026-10-07 002b1d5 152,798 BB view · diff
git:20261003.f8f474d2026-10-03 f8f474d 152,799 BB view · diff
git:20261001.2da125d2026-10-01 2da125d 152,641 BB view · diff
git:20260929.3764d582026-09-29 3764d58 151,595 BB view · diff
git:20260928.b5afdc02026-09-28 b5afdc0 150,652 BB view · diff
git:20260925.6cd06b92026-09-25 6cd06b9 148,547 BB view · diff
git:20260925.c951e5a2026-09-25 c951e5a 143,459 BB 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 script tag (matched: <script)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (154500 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

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

yzhao062/agent-config · 16 stars · license none declared · pushed 2026-10-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_w7x7pcd5krjkbtux
GET https://markdownregistry.com/api/v1/resolve?ref=yzhao062/agent-config/implement-review
GET https://markdownregistry.com/api/v1/blob/83e23473ba2dd1f0901d995815867a615458b8a537d4d441fbcb1114d66e9be5

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 yzhao062/agent-config

AGENTS.md AGENTS.md file
yzhao062/agent-config · AGENTS.md
git:20261023.0b3134e · audit A · 16 stars
CLAUDE.md CLAUDE.md file
yzhao062/agent-config · CLAUDE.md
git:20261023.0b3134e · audit A · 16 stars
condense-cv SKILL.md skill
yzhao062/agent-config · reference-skills/condense-cv/SKILL.md · Create 1-page or 2-page CV variants from a longer master LaTeX CV. Use when the user asks for a short CV, concise CV…
git:20260402.7b2dc4a · audit A · 16 stars
cs-meta-review SKILL.md skill
yzhao062/agent-config · reference-skills/cs-meta-review/SKILL.md · Draft grounded area chair, senior area chair, or editor style meta reviews for computer science and machine learning…
git:20260402.7b2dc4a · audit A · 16 stars
cs-paper-review SKILL.md skill
yzhao062/agent-config · reference-skills/cs-paper-review/SKILL.md · Draft grounded peer reviews for computer science and machine learning papers from a paper PDF, extracted text, venue…
git:20260402.7b2dc4a · audit A · 16 stars
deck-assembler SKILL.md skill
yzhao062/agent-config · reference-skills/deck-assembler/SKILL.md · Assemble a coherent USC Beamer talk from the reusable Yue Zhao intro module and one or more existing paper decks in…
git:20260402.7b2dc4a · audit A · 16 stars
nsf-bibref-filler SKILL.md skill
yzhao062/agent-config · reference-skills/nsf-bibref-filler/SKILL.md · Add or tighten bibliography citations in NSF proposal sections such as the intro, summary, team qualification…
git:20260402.7b2dc4a · audit A · 16 stars
figure-prompt-builder SKILL.md skill
yzhao062/agent-config · reference-skills/nsf-figure-builder/SKILL.md · Build copy-ready prompts for downstream LLM figure generation from source text, figure ideas, prior examples, or rough…
git:20260406.2404ea5 · audit A · 16 stars
nsf-proposal-composer SKILL.md skill
yzhao062/agent-config · reference-skills/nsf-proposal-composer/SKILL.md · Compose NSF proposal outlines and section drafts from a project idea, prior proposal examples, and solicitation…
git:20260406.2404ea5 · audit A · 16 stars
nsf-proposal-guardrail SKILL.md skill
yzhao062/agent-config · reference-skills/nsf-proposal-guardrail/SKILL.md · Unified NSF proposal requirements, question-answering, and preflight checking for a single proposal repository. Use…
git:20260406.2404ea5 · audit A · 16 stars
nsf-thrust-refiner SKILL.md skill
yzhao062/agent-config · reference-skills/nsf-thrust-refiner/SKILL.md · Refine one or more NSF thrust, aim, or study files after the initial scaffold exists. Use when Codex needs to deepen a…
git:20260406.2404ea5 · audit A · 16 stars
paper-to-beamer SKILL.md skill
yzhao062/agent-config · reference-skills/paper-to-beamer/SKILL.md · Convert an academic paper's LaTeX source, figures, and bibliography into a complete 20-25 minute Beamer presentation…
git:20260402.7b2dc4a · audit A · 16 stars

Every file in yzhao062/agent-config

Other files named implement-review

implement-review SKILL.md skill
yzhao062/anywhere-agents · packages/pypi/anywhere_agents/composer/skills/implement-review/SKILL.md · Review loop for staged changes. Detects content type, prepares a review request for Codex (Terminal-relay manual…
git:20261019.12548ac · audit B · 259 stars
implement-review SKILL.md skill
yzhao062/anywhere-agents · skills/implement-review/SKILL.md · Review loop for staged changes. Detects content type, prepares a review request for Codex (Terminal-relay manual…
git:20261019.12548ac · audit B · 259 stars

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