New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Quality Review

by ReviewStage in ReviewStage/stage-cli

A skill your agent uses when reviewing code changes against AGENTS.md implementation quality standards, or when asked to do an implementation quality review

MITAuto-check passedAgent Workflows

Install Quality Review

skills CLI
$ npx skills add ReviewStage/stage-cli --skill quality-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ReviewStage/stage-cli quality-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ReviewStage/stage-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/quality-review .claude/skills/quality-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
quality-review
GitHub stars
274
Token cost
~1.3k tokens
SKILL.md length
528 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when reviewing code changes against AGENTS.md implementation quality standards, or when asked to do an implementation quality review

  • Works in 4 steps: Parse Criteria from AGENTS.md → Dispatch Parallel Agents → Triage Raw Findings → …
  • Reviewing code changes against AGENTS.md implementation quality standards
  • SKILL.md covers Overview, Workflow, Step 1: Parse Criteria from… and Step 2: Dispatch Parallel Agents, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Quality Review is an agent skill from ReviewStage/stage-cli. Use when reviewing code changes against AGENTS.md implementation quality standards, or when asked to do an implementation quality review

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Agent instruction files. The repository describes itself as: A viewer for reviewing local code changes in small individual chapters. Works with any AI agent. The licence is MIT.

When your agent uses it

  • Reviewing code changes against AGENTS.md implementation quality standards
  • Asked to do an implementation quality review

Example prompts

  • “/quality-review”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Parse Criteria from AGENTS.md
  2. Dispatch Parallel Agents
  3. Triage Raw Findings
  4. Compile Report

What it can do on your machine

Read from SKILL.md and the folder at commit 59b977b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Quality Review loads about 1.3k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 528 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ReviewStage/stage-cli at commit 59b977b, republished under its MIT licence (© ReviewStage). 528 words, ~1,333 tokens.

Download SKILL.mdSave it as .claude/skills/quality-review/SKILL.md (or your agent's skills folder).
name
quality-review
description
Use when reviewing code changes against AGENTS.md implementation quality standards, or when asked to do an implementation quality review
metadata.internal
true

Quality Review

Overview

Dispatches one parallel Sonnet agent per bullet point in the ## Implementation Quality section of the nearest AGENTS.md. Each agent independently discovers what changed and checks the codebase against exactly one criterion. A triage pass then removes false positives, duplicates, and contradictions before the final report.

Workflow

1. PARSE    → Extract each bullet point from ## Implementation Quality in AGENTS.md
2. DISPATCH → One Task agent per criterion (all in parallel, single message)
3. TRIAGE   → Review all raw findings: drop false positives, duplicates, and contradictions
4. REPORT   → Compile cleaned findings into summary table

Step 1: Parse Criteria from AGENTS.md

Read the project's AGENTS.md and extract every bullet point under ## Implementation Quality. Stop at the next ## heading — do not include bullets from any other section. Each - line becomes one criterion.

Do not hardcode criteria — always read from the current project's AGENTS.md so the skill stays in sync with the project's actual standards.

Step 2: Dispatch Parallel Agents

CRITICAL: All agents must be launched in a SINGLE message with multiple Task tool calls. Do not loop sequentially.

Use subagent_type: "Explore" and model: "sonnet" on every Task call.

Agent prompt template for each criterion (set model: "sonnet" on every Task call):

You are a focused code reviewer responsible for checking ONE specific quality criterion.

Criterion:
{criterion_text}

Your job:
1. Discover what changed — start with `git diff origin/main...HEAD` or `git diff main...HEAD`.
2. Feel free to explore the broader codebase or search the web for anything — do as much research as needed to make a confident judgment.
3. Check whether the changes comply with your assigned criterion.
4. Report ALL violations you find — do not stop at the first one.

Output format (exactly this structure, nothing else):
**{criterion_short_name}**: PASS | WARN | FAIL
- `file:line` — description of violation  (repeat for every violation found)
(omit bullet lines entirely if PASS)

Replace {criterion_short_name} with a 2-5 word label derived from the criterion.

Step 3: Triage Raw Findings

After all agents complete, review their combined output before building the report table. Apply each filter below and silently drop any finding that fails:

FilterRule
False positiveThe flagged code is correct per the criterion when its full context is understood (e.g., a "one-time abstraction" that is actually reused elsewhere, framework-generated boilerplate the author didn't write, or a WARN that the criterion explicitly permits).
DuplicateTwo or more findings point to the same file+line for the same root cause, regardless of which criterion reported it. Keep only the most specific one.
ContradictionA finding is itself in tension with another principle in AGENTS.md — e.g., flagging missing abstraction under DRY when adding it would violate YAGNI, or flagging missing error handling when the code correctly follows "fail fast." Drop the finding if following its recommendation would violate a different criterion.

After filtering, re-evaluate each criterion's overall verdict:

  • If all its violations were dropped → change verdict to PASS.
  • If only FAIL violations were dropped but WARNs remain → change verdict to WARN.

Do not modify the verdict of a finding you decide to keep.

Show full SKILL.md (176 more words)Show less

Step 4: Compile Report

Output a table with one row per violation — if a criterion has multiple violations, give each its own row. Criteria with no violations get a single PASS row.

## Quality Review

| Criterion | Verdict | Finding |
|-----------|---------|---------|
| Engineered enough / YAGNI | WARN | `src/bar.ts:10` — abstraction added for single use case |
| Engineered enough / YAGNI | WARN | `src/baz.ts:88` — second violation of same criterion |
| DRY | PASS | |
| ... | | |

**Result: N criteria checked. X passed, Y warnings, Z failures.**

Each violation gets its own row, even when multiple violations share a criterion. List FAILs first, then WARNs, then PASSes so issues surface immediately.

If all pass: ✓ All N criteria passed.

Common Mistakes

MistakeFix
Launching agents sequentiallyAll Task calls in ONE message — that's the whole point
Hardcoding criteriaAlways read from AGENTS.md — criteria drift over time
Passing the diff to agentsDon't — agents discover changes themselves via git
Agents checking multiple criteriaEach agent gets exactly one criterion
Skipping PASS rows in outputInclude all criteria so nothing appears missed
Including TypeScript safety rulesOnly parse ## Implementation Quality — stop at the next ## heading
Skipping triageAlways run Step 3 — subagents can't see each other's output and will produce overlapping findings
Dropping findings without justificationEach dropped finding must match a specific triage filter; do not drop findings just because they seem minor

© ReviewStage, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/quality-review of ReviewStage/stage-cli.

Open the folder on GitHubat commit 59b977b

Compare with similar skills

Quality Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Quality Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Quality Review this skillReviewStage/stage-cli274—~1.3kAutomated safety check: PassMIT
Using Agent Skillsaddyosmani/agent-skills105k4 repos~2.4kAutomated safety check: PassMIT
Claude ReflectBayramAnnakov/claude-reflect1.8k2 repos~627Automated safety check: PassMIT
Writing For Agentsbestofjs/bestofjs3.1k20 repos~2.7kAutomated safety check: PassMIT
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~11kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Using Agent Skills

    addyosmani/agent-skills

    Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.

    105k GitHub starsUsed in 4 repos~2.4k tokens
    Agent WorkflowsAuto-check passed

  • Claude Reflect

    BayramAnnakov/claude-reflect

    Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.

    1.8k GitHub starsUsed in 2 repos~627 tokens
    Agent WorkflowsAuto-check passed

  • Writing For Agents

    bestofjs/bestofjs

    Writing documents for agents. An agent skill from bestofjs/bestofjs.

    3.1k GitHub starsUsed in 20 repos~2.7k tokens
    Agent WorkflowsAuto-check passed

  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed

  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~11k tokens
    Agent WorkflowsAuto-check passed

  • SkillOpt Sleep Cycle

    microsoft/SkillOpt

    Official

    Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.

    18k GitHub stars~2.3k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed

More from ReviewStage/stage-cli

All 10 skills in this repo

  • Fixing CI

    ReviewStage/stage-cli

    A skill your agent uses when CI is failing on a branch and you need to diagnose failures from GitHub, fix them locally with iterative verification, and re-push clean commits.

    274 GitHub stars~977 tokensUpdated 1 mo ago
    Auto-check passed

  • Fixing PR Comments

    ReviewStage/stage-cli

    A skill your agent uses when a pull request has unresolved review comments that need to be addressed, or when asked to fix PR feedback

    274 GitHub stars~953 tokensUpdated 1 mo ago
    Auto-check passed

  • Iterate PR

    ReviewStage/stage-cli

    A skill your agent uses when a PR is open and the user wants to autonomously monitor and fix PR review comments, CI failures, and rebase conflicts on a recurring loop, or when asked to…

    274 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Linear Issue

    ReviewStage/stage-cli

    A skill your agent uses when creating a Linear issue from the current coding context, or when the user invokes /linear-issue.

    274 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check passed

  • Rebase Origin Main

    ReviewStage/stage-cli

    A skill your agent uses when rebasing the current branch onto origin/main, including resolving merge conflicts along the way

    274 GitHub stars~927 tokensUpdated 1 mo ago
    Auto-check passed

  • Trade Off

    ReviewStage/stage-cli

    Use at any stage — planning, before implementing, or reviewing code that's already written — to surface high-level trade-offs that could significantly simplify the work.

    274 GitHub stars~3k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Quality Review

What does Quality Review do?

A skill your agent uses when reviewing code changes against AGENTS.md implementation quality standards, or when asked to do an implementation quality review. Quality Review is an agent skill from ReviewStage/stage-cli.

When should I use Quality Review?

Quality Review fits situations like: reviewing code changes against AGENTS.md implementation quality standards; asked to do an implementation quality review.

How do I install Quality Review in Claude Code?

Run `npx skills add ReviewStage/stage-cli --skill quality-review -a claude-code`. Or copy the skill folder (.agents/skills/quality-review in ReviewStage/stage-cli) into .claude/skills/quality-review in your project. Claude Code loads it when a task matches its description.

How do I install Quality Review in Codex?

Run `npx skills add ReviewStage/stage-cli --skill quality-review -a codex`. Or copy the skill folder (.agents/skills/quality-review in ReviewStage/stage-cli) into .agents/skills/quality-review in your project. Codex loads it when a task matches its description.

Can I use Quality Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ReviewStage/stage-cli --skill quality-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/quality-review, .gemini/skills/quality-review, .github/skills/quality-review and .opencode/skills/quality-review in your project.

What does Quality Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Quality Review is instructions for the agent only.

Does Quality Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Quality Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Quality Review use?

Quality Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Quality Review use?

About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Quality Review?

Skills that share tags, products or a category with Quality Review: Using Agent Skills (addyosmani/agent-skills, 105k stars), Claude Reflect (BayramAnnakov/claude-reflect, 1.8k stars), Writing For Agents (bestofjs/bestofjs, 3.1k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Quality Review?

ReviewStage (a GitHub organization) maintains it in ReviewStage/stage-cli, which has 274 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 7, 2026.

Source: ReviewStage/stage-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.