guide
Skill1 starsChanged 51 days agoMITView on GitHub
Use at the start of any session to understand which skill to invoke. Maps the full workflow — feature development, bug fixing, architecture, and utilities — for a C++ game server project with SVN.
20 other projects use a version of this.
Adopted by
Most recently taken up by
- cafe3310/public-agent-skillstheir own version, first seen Nov 8, 2026
- juanbermudez/skillstheir own version, first seen Nov 8, 2026
- Jasenpan1987/multi-codetheir own version, first seen Nov 8, 2026
- assisjp/specflowtheir own version, first seen Nov 1, 2026
- helderberto/agent-skillstheir own version, first seen Oct 13, 2026
- sangchane/claude-skillstheir own version, first seen Oct 13, 2026
Used with
Projects with it also use research, setup and 1 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.
NVIDIASkillresearch
Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.
Also in 3 projects that use this
VercelSkillsetup
Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".
Also in 3 projects that use this
GoogleSkillcode-review
Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.
Also in 3 projects that use this
Other versions20 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 20
- recharts/recharts★ 28ksame name
- cafe3310/public-agent-skills★ 256same name
- Senuto/nodeshub-seo-skills★ 40same name
- aleksander-dytko/ai-pm-workspace★ 34same name
- helderberto/agent-skills★ 19same name
- assisjp/specflow★ 17same name
- froster02/mini-Brain_skills★ 4same name
- MEKO747/claude-code-skill★ 4same name
- NYTC69/review-loop★ 3same name
- leepokai/claude-code-guide★ 2same name
10 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- adversarial-gameplay-acceptanceSkill
- ai-daily-pulseSkill
- beautiful-feishu-whiteboardSkill
- cpp-codereviewSkill
- daily-weekly-reportSkill
- feishu-cardSkill
- architectSkill
- brainstormSkill
- cavemanSkill
- debugSkill
- grillSkill
- handoffSkill
- implementSkill
- planSkill
- prototypeSkill
- reviewSkill
- to-issuesSkill
- to-prdSkill
- triageSkill
- zoom-outSkill
- silk-designSkill
- tig-acting-taskSkill
- xhs-zine-coverSkill
The file
Files
Gameserver Agent Skills — Guide
This package provides a complete agent workflow for C++ game server development.
The Golden Rule
Invoke the relevant skill BEFORE any response or action. Even a 1% chance a skill might apply means you should invoke it. Skills tell you HOW to approach work; don't skip them.
Workflow Map
Feature Development
idea → /brainstorm → /to-prd → /plan → /to-issues → /implement loop → svn commit/brainstorm— Explore intent, ask clarifying questions, produce a design spec/to-prd— Turn the design into a formal PRD and publish to the issue tracker/plan— Break the PRD into a step-by-step implementation plan/to-issues— Slice the plan into independently-grabbable SVN-ready issues/implement— Execute: implement slice →./build.sh→/review→svn commit
Bug Fixing
bug report → /debug → implement fix → /review → svn commit/debug— Build a feedback loop, reproduce, hypothesise, fix/implement— Apply the fix with the implement→build→review loop/review— Code review before committing
Architecture Work
/zoom-out → /architect → /plan → /implement loop/zoom-out— Get a map of relevant modules and callers/architect— Find deepening opportunities, reduce coupling/plan+/implement— Execute the refactor
Prototyping
/prototype → capture decision → /plan → /implementSkill Reference
| Skill | When to use |
/brainstorm | Before any feature work — explore requirements, produce a design doc |
/to-prd | Turn conversation context into a formal PRD on the issue tracker |
/plan | Before touching code — write a step-by-step implementation plan |
/to-issues | Break a plan into independently-grabbable issues |
/implement | Execute: implement → build → review → commit (repeat per slice) |
/review | Code review before any SVN commit |
/debug | Disciplined bug diagnosis with feedback loop |
/architect | Find and fix architectural friction in the codebase |
/zoom-out | Get a broader map of modules and callers in an unfamiliar area |
/prototype | Build throwaway C++ code to answer a design question |
/grill | Interview the user or design relentlessly until shared understanding |
/triage | Move issues through the triage state machine |
/handoff | Compact the session into a document for the next agent to pick up |
/caveman | Ultra-compressed output mode (~75% fewer tokens) |
Project Context
- Language: C++17
- Framework: Custom in-house C++ game server framework
- Build:
./build.sh(Unity Build) - Deploy:
cpgame <server_id> - VCS: SVN — all commits use
svn commit -m "...", all history viasvn log - Protocol:
.sdpfiles inCommon/(CS/SC) andInter/(server-to-server) - Naming: PascalCase classes, m_ prefix for members, i/b/s/v/st/p prefixes for locals
Quality Gate
No code is committed without passing: ./build.sh compiles clean → /review subagent approves → svn commit.
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
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.

