Agent skill
pr-review
Review a pull request for spec alignment, architecture, tests, and docs. No code changes.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/pr-review-lightforgelabsstudio-aide
SKILL.md
PR Review
Review a PR against its linked issue and project constraints. Do not push fixes.
Inputs
PR number or URL. Reviewer GitHub login (must not be PR author). Any custom concerns.
Review-aware
Before starting: check if <pr-slug>.findings.md exists. If it does, incorporate prior findings into this review.
Workflow
-
Verify identity — Run
gh api user --jq .login. If reviewer == PR author, stop and request an identity switch.If you need a separate reviewer identity (e.g., work vs. personal account):
bash# One-time setup for a reviewer account GH_CONFIG_DIR=~/.config/gh-reviewer gh auth login # Then prefix all gh commands with GH_CONFIG_DIR=~/.config/gh-reviewer GH_CONFIG_DIR=~/.config/gh-reviewer gh api user --jq .login -
Load PR + spec — Run
gh pr view <n>andgh pr diff <n>. Extract linked issue (Fixes #X) and read its full spec. -
Review — Check:
- Spec alignment (goals, scope, success criteria)
- Architecture compliance (AGENTS.md invariants, authoritative systems)
- Testing posture (new tests where appropriate; no unjustified test edits)
- Docs drift or duplication
- Git hygiene (commit structure, no debug leftovers)
- If a check is red, compare against
mainand inspect the full PR commit range before classifying it. If the failure appears anywhere in the PR range, treat it as branch-owned regression and review it as part of the PR.
-
Report findings — Group by severity (Critical/Major/Minor) with
path:linereferences. State a clear decision: approve / request changes / non-blocking. -
Submit — Use
/findingsto write<pr-slug>.findings.md, OR submit via:gh pr review <n> --request-changes --body "..."Do not review as the PR author.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?