skills/good-code/SKILL.md
Generate a project-specific CLAUDE.md (or AGENTS.md) with coding standards, style guides, and best practices. Triggers on any request to set up a project, initialize coding standards, create or update CLAUDE.md or AGENTS.md, configure agent instructions, add code quality rules, or start a new codebase. Use this skill at the start of every new project.
npx skillsauth add kengz/good-code good-codeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are setting up agent instructions for this project based on The 6 Principles: Consistent, Correct, Clear, Concise, Simple, Salient. Framed for code, but medium-agnostic — they govern good writing, documentation, and design just as well.
Before writing anything, check if any of these files already exist in the project root:
CLAUDE.mdAGENTS.md.cursorrules.github/copilot-instructions.mdIf any exist, show the user what was found and ask whether to:
Do not overwrite without explicit confirmation.
Scan the project root for configuration files to determine the stack:
| File | Stack |
|------|-------|
| package.json | Node.js / TypeScript / JavaScript |
| tsconfig.json | TypeScript |
| pyproject.toml | Python (modern) |
| setup.py / setup.cfg | Python (legacy) |
| Cargo.toml | Rust |
| go.mod | Go |
| Gemfile | Ruby |
| pom.xml / build.gradle | Java / Kotlin |
| mix.exs | Elixir |
| Package.swift | Swift |
Also detect:
uv.lock, poetry.lock, pnpm-lock.yaml, yarn.lock, package-lock.json, Pipfile.lockpytest.ini, jest.config.*, vitest.config.*, .mocharc.*, test directories.eslintrc.*, biome.json, ruff.toml, .prettierrc.*, rustfmt.tomlRead the CLAUDE.md file located in this skill's directory (next to this SKILL.md file). This is the base template you will customize. For the full rationale behind each principle, see PRINCIPLES.md in the same directory.
Using the template from Step 3, create a CLAUDE.md (or AGENTS.md if the user's agent platform prefers it) in the project root. The template includes Python and TypeScript as examples — adapt the language-specific sections to match the detected stack:
package.json scripts, Makefile, pyproject.toml, etc.). The Python section in the template shows the level of detail expected.After writing the file, tell the user:
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.