If not on the branch, first run gh pr checkout to switch.
Guardrails
Must check with me before submitting. Show file comments and review comment.
Don't insist on commenting on every PR. Propose approving with no comment if everything looks good.
Do match my writing style. You're commenting as me, not a generic AI assistant.
Do present technical questions to me for ambiguous code. Don't proceed until you understand fully.
Workflow
Research - Gather context (see research.md)
Context - Determine review context using repository visibility. Private repositories use corporate defaults. Public repositories use open-source defaults. Check visibility via the platform API (gh api repos/OWNER/REPO --jq .visibility or glab api projects/ENCODED_PATH | jq .visibility). If ambiguous, ask me.
Review - Examine changed files and existing comments
Delegate - Selectively dispatch PR review toolkit agents in parallel based on what the diff touches:
Skip delegation for trivial PRs (docs-only, config changes, dependency bumps).
Think - Evaluate against priorities (see priorities.md), incorporating toolkit agent findings
Suggest - Propose comments with revisions or issues
Comment - Add approved comments to PR review
Submit - Approve / Comment / Request Changes based on severity
See tone.md for comment style guidelines.
Service Support
This skill assumes GitHub. For GitLab merge requests, load gitlab:merge-request for the review submission workflow. Use draft-note.ts submit to publish draft notes with an optional summary and review decision (approve / request changes).
Converted and distributed by TomeVault — claim your Tome and manage your conversions.
1---2name: bendrucker-claude-peer3description: Peer Review4---56# Peer Review78Assist me in reviewing this PR: $ARGUMENTS910If not on the branch, first run `gh pr checkout` to switch.1112## Guardrails1314- **Must** check with me before submitting. Show file comments and review comment.15- **Don't** insist on commenting on every PR. Propose approving with no comment if everything looks good.16- **Do** match my writing style. You're commenting as me, not a generic AI assistant.17- **Do** present technical questions to me for ambiguous code. Don't proceed until you understand fully.1819## Workflow20211. **Research** - Gather context (see [research.md](research.md))222. **Context** - Determine review context using repository visibility. Private repositories use [corporate](references/corporate.md) defaults. Public repositories use [open-source](references/open-source.md) defaults. Check visibility via the platform API (`gh api repos/OWNER/REPO --jq .visibility` or `glab api projects/ENCODED_PATH | jq .visibility`). If ambiguous, ask me.233. **Review** - Examine changed files and existing comments244. **Delegate** - Selectively dispatch PR review toolkit agents in parallel based on what the diff touches:25 - Error handling, catch blocks, fallback logic: `silent-failure-hunter`26 - New type definitions: `type-design-analyzer`27 - New or modified tests: `pr-test-analyzer`28 - Skip delegation for trivial PRs (docs-only, config changes, dependency bumps).295. **Think** - Evaluate against priorities (see [priorities.md](priorities.md)), incorporating toolkit agent findings306. **Suggest** - Propose comments with revisions or issues317. **Comment** - Add approved comments to PR review328. **Submit** - Approve / Comment / Request Changes based on severity3334See [tone.md](tone.md) for comment style guidelines.3536## Service Support3738This skill assumes GitHub. For GitLab merge requests, load `gitlab:merge-request` for the review submission workflow. Use `draft-note.ts submit` to publish draft notes with an optional summary and review decision (approve / request changes).3940---41> Converted and distributed by [TomeVault](https://tomevault.io/claim/bendrucker) — claim your Tome and manage your conversions.42<!-- tomevault:4.0:skill_md:2026-04-11 -->
Run npx skillmds@latest add tomevault-io/bendrucker-claude-peer in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Peer Review It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.
tomevault-io