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

Review PR

by go-to-k in go-to-k/cdkd

Recommend the right reviewer set for a PR from what it touches.

Apache-2.0Auto-check passedDevelopment

Install Review PR

skills CLI
$ npx skills add go-to-k/cdkd --skill review-pr -a claude-code

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

GitHub CLI
$ gh skill install go-to-k/cdkd review-pr --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/go-to-k/cdkd.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/review-pr .claude/skills/review-pr && 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
review-pr
GitHub stars
146
Token cost
~793 tokens
SKILL.md length
376 words
Files
6 (incl. references)
Skills in repo
14
Repo updated
First seen
Licence
Apache-2.0

At a glance

Recommend the right reviewer set for a PR from what it touches.

  • Works in 7 steps: Is it your turn? A PUSH is not a… → Read the PR — paths above all, plus loc… → Default: ONE reviewer… → …
  • Fires) with ready-to-paste Agent dispatch prompts
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Pull requests

What it does

Review PR is an agent skill from go-to-k/cdkd. Recommend the right reviewer set for a PR from what it touches. Outputs a concrete plan (1 reviewer by default, plus the security reviewer or all three axes when a trigger fires) with ready-to-paste Agent dispatch prompts.

Its SKILL.md is about 790 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/bias-factors.md`, `references/dispatch-and-marker.md` and `references/output-template.md`).

It sits in Development, covering Pull requests and Accessibility. It works with Amazon Web Services and AWS CloudFormation. The repository describes itself as: Drop-in CDK CLI for existing CDK apps — up to 15x faster deploys via direct AWS SDK calls instead of CloudFormation. The licence is Apache-2.0.

When your agent uses it

  • Fires) with ready-to-paste Agent dispatch prompts
  • Tasks that involve Pull requests
  • Tasks that involve Accessibility

Example prompts

  • “/review-pr”

Workflow steps

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

  1. Is it your turn? A PUSH is not a round-completion signal — a REPLY is.
  2. Read the PR — paths above all, plus loc / fc for context and the
  3. Default: ONE reviewer (pr-code-reviewer). A docs-only or test-only
  4. Triggers from the paths list and the src/** size —
  5. Resolve the set: default one reviewer, plus the size axes when the size
  6. Render the recommendation —
  7. Dispatch reviewers and synthesize —

What it can do on your machine

Read from SKILL.md and the folder at commit aefb343. 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

Review PR loads about 793 tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 58 tokens; SKILL.md has 376 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~58
When it runs · the whole SKILL.md, loaded when a task matches
~793
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.9k

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 go-to-k/cdkd at commit aefb343, republished under its Apache-2.0 licence (© go-to-k). 376 words, ~793 tokens.

Download SKILL.mdSave it as .claude/skills/review-pr/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
review-pr
description
Recommend the right reviewer set for a PR from what it touches. Outputs a concrete plan (1 reviewer by default, plus the security reviewer or all three axes when a trigger fires) with ready-to-paste Agent dispatch prompts.
argument-hint
<PR-number>

PR Review Recommendation

Decide how much review rigor a PR warrants and surface the dispatch prompts. The recommendation says what a PR needs AT MINIMUM.

The recommended set is a FLOOR, not a cap, and wall-clock / token cost is never a reason to come in under it or to stop at it (AGENTS.md, "Cost is not a tiebreaker"): when unsure, add the axis. Reviewers are read-only agents that run in parallel.

This skill never spawns reviewers — it reads PR stats, applies the heuristic, and prints a recommendation. The main session orchestrator issues the Agent calls, extending the templates in references/output-template.md with PR-specific context.

The per-stage detail lives under references/, and reading a stage's file at stage entry is mandatory — the one-line summaries below are routing, not the procedure.

Steps

  1. Is it your turn? A PUSH is not a round-completion signal — a REPLY is. Read references/round-completion.md and apply it BEFORE opening a round on a head you have not reviewed.

  2. Read the PR — paths above all, plus loc / fc for context and the touched src/ files' recent history. Commands and their traps: references/pr-stats.md. The history probe is mandatory: it is the one step-3 signal not readable off paths.

  3. Default: ONE reviewer (pr-code-reviewer). A docs-only or test-only diff is not discounted below it.

  4. Triggers from the paths list and the src/** size — references/bias-factors.md, read at this step and AUTHORITATIVE for every list below.

    • Size: the src/** diff exceeds 400 lines OR 8 files → add pr-spec-reviewer + pr-test-reviewer (all three axes).
    • Security add-on (pr-security-reviewer, additive to whatever else runs): a secret / credential / redaction / masking / sensitive-value persistence / process-launch surface, src/provisioning/providers/**, or a PR that IS a security fix. A security blocker stops the merge like any other.
    • All three axes plus security: a state-schema bump, or a security fix.

  5. Resolve the set: default one reviewer, plus the size axes when the size trigger fired, plus pr-security-reviewer when its trigger fired (a 3-axis security fix dispatches four reviewers, not three). Reviewers run ONCE, on the FINAL sha: a fix round is re-checked by messaging the SAME reviewer with the delta (SendMessage), never by a fresh dispatch.

  6. Render the recommendation — references/output-template.md.

  7. Dispatch reviewers and synthesize — references/dispatch-and-marker.md. NEVER report a round closed without dispatching the reviewers first.

© go-to-k, Apache-2.0. 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 5 other files (references) in .claude/skills/review-pr of go-to-k/cdkd.

  • SKILL.md
  • references/bias-factors.md
  • references/dispatch-and-marker.md
  • references/output-template.md
  • references/pr-stats.md
  • references/round-completion.md

Open the folder on GitHubat commit aefb343

Compare with similar skills

Review PR 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.

Review PR compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Review PR this skillgo-to-k/cdkd146—~793Automated safety check: PassApache-2.0
PR Reviewaws/aws-cdk-cli107—~2kAutomated safety check: PassApache-2.0
Reviewquran/quran.com-frontend-next1.9k—~1.1kAutomated safety check: PassNone
Tsh Reviewing FrontendTheSoftwareHouse/copilot-collections284—~4.4kAutomated safety check: PassMIT
Review Component PRIgniteUI/igniteui-webcomponents170—~2.1kAutomated safety check: PassMIT
Cdk Contribution Skillcdklabs/cdk-contribution-skill110—~4.6kAutomated safety check: PassApache-2.0

Similar skills

  • PR Review

    aws/aws-cdk-cli

    Official

    AWS CDK CLI general PR reviewer. An agent skill from aws/aws-cdk-cli.

    107 GitHub stars~2k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

  • Review

    quran/quran.com-frontend-next

    Reviews PR(s) using comprehensive review guidelines including security, correctness, clean code, TypeScript, React patterns, i18n/RTL, performance, and accessibility.

    1.9k GitHub stars~1.1k tokensUpdated 5 mo ago
    DevelopmentAuto-check passed

  • Tsh Reviewing Frontend

    TheSoftwareHouse/copilot-collections

    Frontend-specific code review criteria, component anti-patterns, hooks quality, rendering correctness, accessibility and performance spot-checks, and module organization issues.

    284 GitHub stars~4.4k tokensUpdated 5 days ago
    DevelopmentAuto-check passed

  • Review Component PR

    IgniteUI/igniteui-webcomponents

    Code review checklist for component pull requests covering structure, public API, specification accuracy, accessibility, behavior, styles, tests, and build hygiene

    170 GitHub stars~2.1k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Cdk Contribution Skill

    cdklabs/cdk-contribution-skill

    Guide AWS CDK contributions from GitHub issue analysis to PR-ready code.

    110 GitHub stars~4.6k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed

  • PR Review

    cdklabs/cdk-nextjs

    Review the current PR branch and fix the findings in rounds until reviews come back clean.

    111 GitHub stars~2.4k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from go-to-k/cdkd

All 14 skills in this repo

  • Hunt Bugs

    go-to-k/cdkd

    Proactively hunt for cdkd bugs by deploying real CDK apps that exercise common-but-untested AWS resources, configs, and CloudFormation notations against real AWS, then fix what breaks.

    146 GitHub stars~2.2k tokensUpdated today
    Auto-check passed

  • Use Cdkd

    go-to-k/cdkd

    Build the current cdkd checkout and use it from another CDK project.

    146 GitHub stars~669 tokensUpdated today
    Auto-check passed

  • Verify PR

    go-to-k/cdkd

    Comprehensive PR readiness check before merge. An agent skill from go-to-k/cdkd.

    146 GitHub stars~2.1k tokensUpdated today
    Auto-check passed

  • Work Issues

    go-to-k/cdkd

    Work through already-filed GitHub issues (typically the bug-hunt's output) end to end — triage safely, pick as many FILE-DISJOINT issues as the run can carry, claim each on the issue before starting…

    146 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Cdkd

    go-to-k/cdkd

    Install cdkd and use it safely from an AWS CDK project. An agent skill from go-to-k/cdkd.

    146 GitHub stars~7k tokensUpdated today
    Auto-check: notes

  • Run Integ

    go-to-k/cdkd

    Run integration tests (deploy + destroy) against real AWS. An agent skill from go-to-k/cdkd.

    146 GitHub stars~5.8k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Review PR

What does Review PR do?

Recommend the right reviewer set for a PR from what it touches. Review PR is an agent skill from go-to-k/cdkd. Recommend the right reviewer set for a PR from what it touches.

When should I use Review PR?

Review PR fits situations like: fires) with ready-to-paste Agent dispatch prompts; tasks that involve Pull requests; tasks that involve Accessibility.

How do I install Review PR in Claude Code?

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

How do I install Review PR in Codex?

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

Can I use Review PR 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 go-to-k/cdkd --skill review-pr -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-pr, .gemini/skills/review-pr, .github/skills/review-pr and .opencode/skills/review-pr in your project.

What does Review PR need to run?

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

Does Review PR 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 Review PR 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 Review PR use?

Review PR is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Review PR use?

About 793 tokens (SKILL.md is roughly 3.2k 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 4.1k tokens, read only when the agent opens those files.

What are the alternatives to Review PR?

Skills that share tags, products or a category with Review PR: PR Review (aws/aws-cdk-cli, 107 stars), Review (quran/quran.com-frontend-next, 1.9k stars), Tsh Reviewing Frontend (TheSoftwareHouse/copilot-collections, 284 stars) and Review Component PR (IgniteUI/igniteui-webcomponents, 170 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review PR?

go-to-k (a GitHub user) maintains it in go-to-k/cdkd, which has 146 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 10, 2026.

Source: go-to-k/cdkd on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.