Review pull requests: diffs, comments, context and written review docs.

MITAuto-check passedDevelopment

Install PR Review

skills CLI
$ npx skills add Community-Access/accessibility-agents --skill pr-review -a claude-code

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

GitHub CLI
$ gh skill install Community-Access/accessibility-agents pr-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/Community-Access/accessibility-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/pr-review .claude/skills/pr-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
pr-review
GitHub stars
423
Token cost
~1.4k tokens
SKILL.md length
544 words
Files
5 (incl. references)
Skills in repo
108
Repo updated
First seen
Licence
MIT

At a glance

Review pull requests: diffs, comments, context and written review docs.

  • Works in 12 steps: Always show Change Map first. Before any… → Never show code without context. Every… → Confidence on every finding. No finding… → …
  • Tasks that involve Pull requests
  • SKILL.md covers PR Review Agent, Progress Announcements, Confidence Levels and Delta Tracking, plus 3 more sections
  • Calls node

What it does

PR Review is an agent skill from Community-Access/accessibility-agents. Review pull requests: diffs, comments, context and written review docs.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `agents/openai.yaml`, `references/core-capabilities.md` and `references/intelligence-layer.md`).

It sits in Development, covering Pull requests. It works with GitHub. The repository describes itself as: Accessibility review agents for Claude Code, GitHub Copilot, and Claude Desktop. Eleven specialists that enforce WCAG 2.2 AA compliance so AI coding tools stop generating… The licence is MIT.

When your agent uses it

  • Tasks that involve Pull requests

Example prompts

  • “/pr-review”

Workflow steps

12 steps, taken from the first numbered list in SKILL.md.

  1. Always show Change Map first. Before any diff, output the file-level change summary with categorization…
  2. Never show code without context. Every snippet includes 5 surrounding lines minimum.
  3. Confidence on every finding. No finding goes in a review document without a High/Medium/Low confidence tag.
  4. Delta-check before writing. If a review document already exists for this PR, run delta detection before generating a new one.
  5. Check workspace context first. Look for scan config files (.a11y-*-config.json) and previous audit reports in the workspace root.
  6. Narrate the asset pull. Use / announcements for metadata, diff, CI, and analysis steps.
  7. Never post a review comment without confirmation. Preview the comment, ask for approval, then submit.
  8. Flag security-sensitive files explicitly. Auth, crypto, tokens, and permissions changes get a dedicated security callout.
  9. Surface test ratio. Flag any PR where test lines added < 20% of production lines changed.
  10. Commit story before verdict. Reconstruct the narrative from commit messages before assigning an approval verdict.
  11. Parallel asset collection. Fetch metadata, diff, CI status, and linked issues simultaneously - don't wait for each before starting the next.
  12. Never truncate diffs silently. If a diff is too large to show fully, say so and offer to show it file-by-file.

What it can do on your machine

Read from SKILL.md and the folder at commit decf6ba. 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

    Shell commands in SKILL.md call:

    • node

    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

PR Review loads about 1.4k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 20 tokens; SKILL.md has 544 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~20
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~13k

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 Community-Access/accessibility-agents at commit decf6ba, republished under its MIT licence (© Community-Access). 544 words, ~1,352 tokens.

Download SKILL.mdSave it as .claude/skills/pr-review/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
pr-review
description
Review pull requests: diffs, comments, context and written review docs.
license
MIT
disable-model-invocation
true
metadata.tier
specialist
metadata.domain
github
metadata.output
report
metadata.effort
medium
metadata.title
Pull Request Review

PR Review Agent

Shared instructions Code review standards

Skills: github-workflow-standards, github-scanning, github-analytics-scoring

You are the user's code review command center -- a senior engineer who doesn't just show diffs but actively analyzes changes, spots patterns, flags risks, surfaces developer intent, and produces structured review documents that can be saved, annotated, and acted on later.

Critical: You MUST generate both a .md and .html version of every review document. Follow the dual output and accessibility standards in shared-instructions.md.

Progress Announcements

Narrate every step of the asset pull. Never mention tool names:

text
 Fetching PR metadata and file list...
 Pulling diff and before/after snapshots...
 Checking CI status and linked issues...
 Analyzing changes and generating review document...
 Review ready.

For delta detection (reviewing a PR that was already reviewed):

text
 Loading previous review for PR #{N}...
 Comparing against current diff...
 Delta detected: {N} new comments addressed, {M} findings remain open.

Confidence Levels

Every finding in the review document must include a confidence level:

LevelWhen to Use
HighPattern definitively identified, multiple signals corroborate it
MediumLikely issue, but context outside the diff might explain it
LowPossible concern; flag for human judgment, not blocking

Format in the review table:

text
| File | Finding | Severity | Confidence |
|------|---------|----------|------------|
| auth.ts | Token stored in localStorage | Critical | **High** |
| utils.ts | No null check before .map() | Warning | **Medium** |

Delta Tracking

When a previous review document exists for this PR:

StatusDefinition
ResolvedFinding was in previous review; no longer present in diff
NewNot in previous review; newly introduced
PersistentStill present from previous review
RegressedWas resolved in a previous round; has reappeared

Show a delta summary at the top of the review:

text
## Changes Since Last Review
| Change | Finding |
|--------|---------|
|  Resolved | SQL injection risk in query builder |
|  New | Missing error boundary in UserPanel |
|  Persistent (#2) | No rate limiting on login endpoint |

Behavioral Rules

  1. Always show Change Map first. Before any diff, output the file-level change summary with categorization (feature/bugfix/refactor/test/config).
  2. Never show code without context. Every snippet includes 5 surrounding lines minimum.
  3. Confidence on every finding. No finding goes in a review document without a High/Medium/Low confidence tag.
  4. Delta-check before writing. If a review document already exists for this PR, run delta detection before generating a new one.
  5. Check workspace context first. Look for scan config files (.a11y-*-config.json) and previous audit reports in the workspace root.
  6. Narrate the asset pull. Use / announcements for metadata, diff, CI, and analysis steps.
  7. Never post a review comment without confirmation. Preview the comment, ask for approval, then submit.
  8. Flag security-sensitive files explicitly. Auth, crypto, tokens, and permissions changes get a dedicated security callout.
  9. Surface test ratio. Flag any PR where test lines added < 20% of production lines changed.
  10. Commit story before verdict. Reconstruct the narrative from commit messages before assigning an approval verdict.
  11. Parallel asset collection. Fetch metadata, diff, CI status, and linked issues simultaneously - don't wait for each before starting the next.
  12. Never truncate diffs silently. If a diff is too large to show fully, say so and offer to show it file-by-file.
  13. Dual output always. Every review document is saved as both .md and .html with full accessibility standards.
  14. Release pressure gets a banner. If the PR targets a release branch or milestone, show a visible callout at the top of the review.
  15. Reviewer consensus summary. When other reviews exist, summarize agreement/disagreement - never leave the user to read all threads manually.
Show full SKILL.md (67 more words)Show less

Reference files

Read one only when the task reaches it. Do not read them all up front.

  • references/core-capabilities.md - Core Capabilities
  • references/workflow.md - Workflow
  • references/intelligence-layer.md - Intelligence Layer

Output contract

Collect findings as JSON from each specialist you dispatch, write them to .a11y-history/<timestamp>/, then render the report with node skills/a11y-core/scripts/render-report.mjs. Do not type the report by hand.

Shared rules, dispatch contract and schemas: skills/a11y-core/SKILL.md. Authoritative specifications for this skill: skills/a11y-core/references/sources.md.

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

Files

SKILL.md and 4 other files (references) in skills/pr-review of Community-Access/accessibility-agents.

  • SKILL.md
  • agents/openai.yaml
  • references/core-capabilities.md
  • references/intelligence-layer.md
  • references/workflow.md

Open the folder on GitHubat commit decf6ba

Compare with similar skills

PR 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.

PR Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
PR Review this skillCommunity-Access/accessibility-agents423—~1.4kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Check PRonyx-dot-app/onyx32k2 repos~2.3kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT
Create Pull Requestcline/cline70k1 repos~1.6kAutomated safety check: PassApache-2.0
Pull Request Title and Body Writeropeninterpreter/openinterpreter69k2 repos~1.1kAutomated safety check: PassApache-2.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Check PR

    onyx-dot-app/onyx

    Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.

    32k GitHub starsUsed in 2 repos~2.3k tokens
    DevelopmentAuto-check passed
  • Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed
  • Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.

    70k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed
  • Pull Request Title and Body Writer

    openinterpreter/openinterpreter

    Rewrites the title and body of one or more pull requests with gh, leading with why the change was made, then what changed, and describing only the net result.

    69k GitHub starsUsed in 2 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Official

    Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.

    48k GitHub stars~2.2k tokensUpdated today
    DevelopmentAuto-check passed

More from Community-Access/accessibility-agents

All 108 skills in this repo
  • A11y Core

    Community-Access/accessibility-agents

    Shared contract for the Accessibility Agents skills - dispatch, findings schema, report rules.

    423 GitHub stars~1.2k tokensUpdated 17 days ago
    Auto-check passed
  • Kb Web Scanning

    Community-Access/accessibility-agents

    Reference data, not a reviewer. An agent skill from Community-Access/accessibility-agents.

    423 GitHub stars~1.2k tokensUpdated 17 days ago
    Auto-check passed
  • Accessibility Lead

    Community-Access/accessibility-agents

    Web UI accessibility lead. An agent skill from Community-Access/accessibility-agents.

    423 GitHub stars~932 tokensUpdated 17 days ago
    Auto-check passed
  • Alt Text Headings

    Community-Access/accessibility-agents

    Alt text, SVGs, figures, charts, heading order, page titles and landmarks.

    423 GitHub stars~1.5k tokensUpdated 17 days ago
    Auto-check passed
  • Aria Specialist

    Community-Access/accessibility-agents

    ARIA roles, states and properties for custom widgets and dynamic content.

    423 GitHub stars~1.6k tokensUpdated 17 days ago
    Auto-check passed
  • Cognitive Accessibility

    Community-Access/accessibility-agents

    Plain language, WCAG 2.2 cognitive criteria, COGA guidance and auth UX.

    423 GitHub stars~1.4k tokensUpdated 17 days ago
    Auto-check passed

Works with

Categories

Questions about PR Review

What does PR Review do?

Review pull requests: diffs, comments, context and written review docs. PR Review is an agent skill from Community-Access/accessibility-agents. Review pull requests: diffs, comments, context and written review docs.

When should I use PR Review?

PR Review fits situations like: tasks that involve Pull requests.

How do I install PR Review in Claude Code?

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

How do I install PR Review in Codex?

Run `npx skills add Community-Access/accessibility-agents --skill pr-review -a codex`. Or copy the skill folder (skills/pr-review in Community-Access/accessibility-agents) into .agents/skills/pr-review in your project. Codex loads it when a task matches its description.

Can I use PR 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 Community-Access/accessibility-agents --skill pr-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/pr-review, .gemini/skills/pr-review, .github/skills/pr-review and .opencode/skills/pr-review in your project.

What does PR Review need to run?

Going by SKILL.md and its folder, PR Review needs the command-line tools its instructions call (node).

Does PR 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 PR 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 PR Review use?

PR Review is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does PR Review use?

About 1.4k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 12k tokens, read only when the agent opens those files.

What are the alternatives to PR Review?

Skills that share tags, products or a category with PR Review: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Check PR (onyx-dot-app/onyx, 32k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars) and Create Pull Request (cline/cline, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains PR Review?

Community-Access (a GitHub organization) maintains it in Community-Access/accessibility-agents, which has 423 GitHub stars. The repository holds 108 skills in this directory. The repository was last updated on September 23, 2026.

Source: Community-Access/accessibility-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.