agentleFS
Aquarius-muAquarius-mu/skillManager/skills/gameserver-agent-skills/review/SKILL.md

review

Skill1 starsChanged 53 days agoMITView on GitHub

Dispatch a code reviewer subagent before any SVN commit. Mandatory after each implement slice, after completing a major feature, and before committing to trunk.

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use close-spec, design-with-images and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • dzhngSkill

    close-spec

    When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).

    Also in 5 projects that use this

  • dzhngSkill

    design-with-images

    Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.

    Also in 5 projects that use this

  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • +3 more from dzhng
  • +5 more from Lambenthan

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 157 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    After each implement slice (before svn commit)

    line 15
  2. Distinctive:

    After completing a major feature

    line 16
  3. Distinctive:

    Before committing to trunk

    line 17
  4. Distinctive:

    When stuck — fresh perspective often unblocks

    line 20
  5. Distinctive:

    Before a large refactor — establish a baseline

    line 21

“Common” is measured: kept by at least 6 in 10 of the 157 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review

Dispatch a code reviewer subagent to catch issues before they cascade into more work. The reviewer gets focused context — not your session history.

Core principle: Review early, review often. Fix Critical and Important issues before committing.

When to Review

Mandatory:

  • After each implement slice (before svn commit)
  • After completing a major feature
  • Before committing to trunk

Optional but valuable:

  • When stuck — fresh perspective often unblocks
  • Before a large refactor — establish a baseline

How to Request

1. Get SVN revisions:

# For committed changes:
HEAD_REV=$(svn info --show-item last-changed-revision)
BASE_REV=$((HEAD_REV - 1))

# For uncommitted local changes — skip rev lookup, just diff:
svn status
svn diff

2. Dispatch a code reviewer subagent (use Agent tool, general-purpose type):

Fill in these placeholders from code-reviewer-prompt.md:

  • {DESCRIPTION} — brief summary of what was built
  • {PLAN_OR_REQUIREMENTS} — what it should do
  • {BASE_REV} — starting SVN revision (or PREV)
  • {HEAD_REV} — ending revision (or use svn diff for uncommitted)

3. Act on feedback:

  • Critical — fix immediately, never commit with unresolved Critical issues
  • Important — fix before committing
  • Minor — note for later, optional

Reviewer Prompt Template

You are a Senior Code Reviewer for a C++ game server.
Review the changes below against the requirements and identify issues before they cascade.

## What Was Implemented
{DESCRIPTION}

## Requirements / Plan
{PLAN_OR_REQUIREMENTS}

## SVN Range to Review
Base revision: {BASE_REV}
Head revision: {HEAD_REV}

```bash
# For committed revisions:
svn diff -r {BASE_REV}:{HEAD_REV} --summarize
svn diff -r {BASE_REV}:{HEAD_REV}

# For uncommitted local changes:
svn status
svn diff

What to Check

C++ game server conventions:

  • Naming: m_ prefix for members; i/b/s/v/st/p prefixes for locals; PascalCase classes
  • Subtraction: must use SafeSub() — no direct -- or -=
  • Map lookups: must use FindMapPtr — no raw .find() + iterator compare
  • String conversion: ToString() not std::to_string()
  • Control flow: all if/for/while bodies use full brace blocks, braces on their own lines
  • setChanged() called after all persistent data modifications
  • sendResponse() only in CmdParser layer, never inside Logic/Manager
  • New CS/SC commands registered in CommandRegister.h
  • Error codes use ERR_ prefix; iRet declared as int32_t

Architecture:

  • CmdParser / Logic layer separation respected?
  • loop() functions have throttle guards?
  • Protocol IDs unique and non-overlapping?

Logic correctness:

  • Off-by-one errors?
  • Integer underflow risks?
  • Missing null checks on pointer lookups?

Output Format

Strengths

[What's well done — be specific]

Issues

Critical (Must Fix)

[Bugs, data loss risks, broken functionality, convention violations that cause runtime errors]

Important (Should Fix Before Commit)

[Architecture problems, missing setChanged(), wrong layer placement, missing registration]

Minor (Nice to Have)

[Style, optimization, documentation polish]

For each issue: file:line reference, what's wrong, why it matters, how to fix.

Assessment

Ready to commit? [Yes | No | With fixes]

Reasoning: [1-2 sentence technical assessment]


## Example

[Just implemented Task 2: Add feature query]

BASE_REV=$(svn info --show-item last-changed-revision) # e.g. 4820 BASE_REV=$((BASE_REV - 1)) # 4819 — before this task

[Dispatch code reviewer subagent] DESCRIPTION: Added getXxxRank() in RoleXxx.cpp and handle_Xxx_Yyy handler PLAN_OR_REQUIREMENTS: Task 2 from docs/plans/2026-05-12-feature.md BASE_REV: 4819 HEAD_REV: 4820

[Reviewer returns]: Strengths: Clean iRet propagation, correct layer separation Issues: Important: Missing setChanged() after m_oCache.iScore update Minor: Magic number 100 for rank cap — extract to constant Assessment: Fix before commit

[Fix setChanged() call] svn commit -m "feat: add feature query"

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.