This is the disciplined counterpart to cs-learn and cs-trick. It appends one-line project facts to a fixed section in `.codestable/attention.md`, the file that CodeStable skills read on startup. The three-part filter is smart: length (one or two lines), frequency (needed almost every session), and stability (long-term constraints, not temporary workarounds). Typical entries are "run `pnpm gen` before build" or "don't use npm, project uses yarn berry." It won't let you bloat the file with background or multi-step guides, enforces a fixed set of subsections like "Build," "Environment Variables," and "Path Conventions," and checks for duplicates before writing. The 150-line soft cap keeps attention.md from becoming another junk drawer. One note per invocation, no batch writing.

skills.sh installs
1K
GitHub stars
1.1K
last updated
Jul 14, 2026

Install

$ npx -y skills add liuzhengdongfortest/codestable --skill cs-note --agent claude-code

Installs into .claude/skills of the current project.

Files

This is the disciplined counterpart to cs-learn and cs-trick. It appends one-line project facts to a fixed section in `.codestable/attention.md`, the file that CodeStable skills read on startup. The three-part filter is smart: length (one or two lines), frequency (needed almost every session), and stability (long-term constraints, not temporary workarounds). Typical entries are "run `pnpm gen` before build" or "don't use npm, project uses yarn berry." It won't let you bloat the file with background or multi-step guides, enforces a fixed set of subsections like "Build," "Environment Variables," and "Path Conventions," and checks for duplicates before writing. The 150-line soft cap keeps attention.md from becoming another junk drawer. One note per invocation, no batch writing.

Browse the repository on GitHub

Sponsors

Details

Repository
github.com/liuzhengdongfortest/codestable
First seen
Jun 3, 2026

More from liuzhengdongfortest/codestable

All 26

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/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
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-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