This is the front door to CodeStable, a Chinese language workflow system that models software development as entities and processes living in a `.codestable/` directory. You say "cs" or describe what you want to do, and it routes you to the right sub-skill: new features go to cs-feat, bugs to cs-issue, refactors elsewhere. It doesn't do the work itself, just reads your repo state and tells you which cs-* tool to invoke next. The whole thing assumes you're treating AI as an execution layer while you stay in control of architecture and decisions. If your repo isn't onboarded yet, it'll send you to cs-onboard first. Think of it as a dispatcher that prevents you from starting the wrong workflow.
- skills.sh installs
- 1.2K
- GitHub stars
- 1.1K
- last updated
- Jul 14, 2026
Install
$ npx -y skills add liuzhengdongfortest/codestable --skill cs --agent claude-codeInstalls into .claude/skills of the current project.
Files
cs
判断用户此刻要执行、先讨论、咨询还是了解体系。明确行动默认直接执行，不先加讨论 gate。
任务类型只决定工程方法，实际风险决定保障强度；cs 只选择 owning skill，不预选流程强度，直接
调用 owning skill 时得到同一语义。
判别与行为
| 用户输入 | 行为 |
|---|---|
| 明确行动诉求（修这个 bug、排查这个报错为什么发生、实现 X、重构 Y、审一下、记住这个…） | 同轮直转：报一句"按 cs-xxx 处理：{一句理由}"，随即在当前回合按该 skill 的纪律继续执行，不要求用户重新调用或再次确认 |
| 用户显式要求先讨论，或调查仓库事实后仍无法安全判断行动类型 / owning skill，且产品决策会实质改变建档或改代码路径 | 在当前会话对齐；用户没有要求先讨论且 owning skill 已可判定时，直接转入，不在入口层细化目标或验收 |
| 咨询（该用哪个 / 流程怎么走 / 你建议怎么做） | 只推荐入口并说明理由，不启动执行 |
| 只说 cs、想了解体系、无具体诉求 | 输出体系速读 |
| 诉求含糊但一个分类问题即可判断 | 先调查可核实事实，只问一个聚焦问题，不默认重流程 |
会话内讨论与 handoff
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/liuzhengdongfortest/codestable
- First seen
- May 16, 2026
More from liuzhengdongfortest/codestable
All 26- Cs Brainstorm1.2K
- Cs Feat1.2K
- Cs Feat Accept1.2K
- Cs Feat Design1.2K
- Cs Feat Ff1.2K
- Cs Feat Impl1.2K
- Cs Issue1.2K
- Cs Issue Analyze1.2K
- Cs Issue Fix1.2K
- Cs Issue Report1.2K
- Cs Onboard1.2K
- Cs Refactor1.2K
- Cs Refactor Ff1.2K
- Cs Req1.2K
- Cs Roadmap1.2K
- Cs Arch1.1K
- Cs Decide1.1K
- Cs Explore1.1K
- Cs Guide1.1K
- Cs Learn1.1K
- Cs Libdoc1.1K
- Cs Trick1.1K
- Cs Note1K
- Cs Audit942
Recommended
cavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
improveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
karpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs