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

implement

Skill1 starsChanged 51 days agoMITView on GitHub

Disciplined implement→build→review→commit loop for C++ game server features. Use when executing a plan task, fixing a bug, or making any code change. One vertical slice at a time.

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-ts-deep-modules, ask-matt 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.
  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 43 projects that use this

  • GoogleSkill

    ask-matt

    Ask which skill or flow fits your situation. A router over the skills in this repo.

    Also in 91 projects that use this

  • RoentekSkill

    loop-me

    Grill me about specs for the workflows I want to build, within this workspace.

    Also in 50 projects that use this

  • AWSSkill

    to-questionnaire

    Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

    Also in 88 projects that use this

  • ryotaroh180105Skill

    claude-handoff

    Hand the current conversation off to a fresh background agent that picks up the work immediately.

    Also in 42 projects that use this

  • GoogleSkill

    to-spec

    Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

    Also in 168 projects that use this

  • +3 more from google

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 3

    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. Distinctive:

    Do NOT implement multiple tasks, then build, then review everything at once.

    line 23
  2. Distinctive:

    Before writing any code for a task:

    line 39
  3. Very specific:

    Commit types: feat (new feature), fix (bug fix), refactor (no behavior change), docs (documentation).

    line 83
  4. Distinctive:

    After all slices are done:

    line 87

“Common” is measured: kept by at least 6 in 10 of the 171 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

Implement

Execute one vertical slice at a time: implement → build clean → code review → SVN commit. Never pile up changes across multiple slices before reviewing.

Core Loop

SLICE: implement change
BUILD: ./build.sh  →  must compile with zero new errors/warnings
REVIEW: invoke /review skill  →  fix Critical + Important issues
COMMIT: svn commit -m "feat/fix: <description>"

Repeat per slice. Do not proceed to the next slice until the current one is committed.

Anti-Pattern: Big-Bang Implementation

Do NOT implement multiple tasks, then build, then review everything at once.

WRONG:
  change1 + change2 + change3 → build → one big review → commit

RIGHT:
  change1 → build → review → commit
  change2 → build → review → commit
  change3 → build → review → commit

Big-bang implementations fail review for reasons that cascade. Small slices = small reviews = faster iteration.

Planning the Slice

Before writing any code for a task:

  • Read the relevant files: sdp definitions, CmdParser handler, Logic Manager
  • Understand what currently exists — don't duplicate or conflict
  • Identify the vertical path: sdp → Logic → CmdParser → response
  • Confirm the slice boundaries with the plan

C++ Game Server Checklist

Before building, verify:

  • All subtraction uses SafeSub(value, sub) — no -- or -=
  • All map lookups use FindMapPtr — no raw .find() + iterator compare
  • setChanged() called after every data modification that needs persistence
  • sendResponse() only in CmdParser layer — never inside Logic/Manager
  • All control flow bodies (if/for/while) use full brace blocks, braces on their own lines
  • New CS/SC commands registered in CommandRegister.h via REGISTER_COMMAND
  • Integer variables use int32_t for iRet (not uint32_t)
  • Error codes use ERR_ prefix, propagated via if (iRet != 0) { return iRet; }
  • Protocol IDs are unique — check the surrounding CmdId enum range before assigning

Build

cd <workdir> && ./build.sh

Expected: clean compilation, no new warnings. Fix any warnings before proceeding to review.

After Build — Request Review

Invoke the /review skill. Pass:

  • DESCRIPTION: what this slice implements
  • BASE_REV: the SVN revision before your changes
  • HEAD_REV: current revision (or use svn diff for uncommitted changes)

Fix all Critical issues immediately. Fix all Important issues before committing. Log Minor issues for later.

Commit

svn commit -m "<type>: <concise description>"

Commit types: feat (new feature), fix (bug fix), refactor (no behavior change), docs (documentation).

Refactor (optional, after all slices committed)

After all slices are done:

  • Extract duplicated logic
  • Simplify complex functions
  • Verify naming conventions (m_ prefix, i/b/s/v/st/p prefixes, PascalCase classes)
  • Build clean after each change
  • Request review for the refactor batch

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.