AGENT SKILL

review

Review a local change, branch, pull request, or stack for correctness, regressions, security, tests, and unnecessary complexity. Use when asked to review rather than implement.

License 许可
Apache-2.0
最近更新
2026-09-29
Stars
★ 0
Forks
0

01 前言 Front Matter

name
review
description
Review a local change, branch, pull request, or stack for correctness, regressions, security, tests, and unnecessary complexity. Use when asked to review rather than implement.

02 资源文件 26

03 SKILL.md 正文

Review

Establish scope

Resolve the requested target before reading code: current working tree, branch, pull request, or stack. Prefer the smallest faithful diff. For a PR, inspect its description, changed files, and relevant base; for a stack, review each PR against its immediate parent as well as the complete stack when cross-PR interactions matter.

Do not modify the target unless the user explicitly asks for fixes. Do not review untrusted or sensitive files outside the agreed scope.

Review method

  1. Read the surrounding contract and callers for each non-trivial change.
  2. Check correctness, error paths, ownership/lifecycle, concurrency, security and privacy boundaries, API compatibility, and test coverage.
  3. Verify claims with targeted commands where possible. A passing test suite does not replace reasoning about untested paths.
  4. Report only actionable findings introduced by the target. Do not raise pre-existing issues unless they obstruct a correct assessment.

Use independent review passes only when they add distinct expertise; consolidate duplicates before reporting. Never claim a tool call or reviewer happened without its observable result.

Finding quality

Each finding must include severity, file and line, the failure condition, and a short explanation of the consequence. Severity is about impact and likelihood:

  • bug: a likely correctness, reliability, security, or compatibility defect.
  • suggestion: an improvement with a concrete maintenance or clarity benefit.
  • nit: cosmetic; omit unless the user requested exhaustive feedback.

Prefer a few high-confidence findings to speculative lists. If there are none, say so and name residual risks or checks not run.

Output

Lead with the findings, ordered by severity. Then give a concise scope, evidence, and any verification performed or unavailable. For a stack, retain the PR association for every finding. Do not include generated command dumps, reviewer prompts, or internal orchestration logs in the user-facing report.

04 同仓库更多 Skills

maxjbarfuss
maxjbarfuss/max_llm

train

Launch a new max_llm training run on both GPUs (RTX 4090 + RTX 3090 Ti) through torchrun DDP, resolving the TOML config by name or path. Use only when the user explicitly asks to start, launch or begin a run — "resume", "continue" or "keep training" mean the existing run; takes an optional config name or path.

★ 0
maxjbarfuss
maxjbarfuss/max_llm

serve-live

Before a person looks at a running service, make sure what is running IS the code in the checkout. Restart the services your change actually touched — not every service — and verify each is serving the current commit rather than merely answering; check the remaining dependencies are up without bouncing them. Use whenever you finish work a person will view in a browser or client, whenever you say a page or service is ready, after any commit that changes served code, and when asked to 'restart', 'refresh the services', 'is it live', or 'serve the latest'. Also covers waiting for lazy warm-up before calling a service ready.

★ 0
maxjbarfuss
maxjbarfuss/max_llm

review

Review a local change, branch, pull request, or stack for correctness, regressions, security, tests, and unnecessary complexity. Use when asked to review rather than implement.

★ 0
maxjbarfuss
maxjbarfuss/max_llm

regression-coverage

Reshape a slow or brittle test suite around observable user journeys and published contracts. Use when pruning tests, repairing weak smoke coverage, or addressing repeated feature regressions.

★ 0
maxjbarfuss
maxjbarfuss/max_llm

pr-babysit

Monitor selected pull requests and report or safely act on review, CI, mergeability, and stack state.

★ 0
maxjbarfuss
maxjbarfuss/max_llm

keel

Use a project's local keel code graph to assess change impact, find callers and reuse candidates, validate a plan, or check an edit. Applies only in a repository with a .keel/ directory; skip it for prose-only work.

★ 0