Globales Ranking · von 601 Skills
code-quality AI Agent Skill
Quellcode ansehen: rarestg/rarestg-skills
SafeInstallation
npx skills add rarestg/rarestg-skills --skill code-quality 10
Installationen
Code Quality Setup
When starting or scaffolding any project, set up formatting, linting, import
sorting, type checking, and pre-commit hooks before writing application code.
This prevents the painful scenario of adding these tools later and facing
thousands of lines of formatting changes in a single commit.
Detect the ecosystem
Determine the project type from existing files or the scaffolding context:
| Signal | Ecosystem |
|---|---|
pyproject.toml, setup.py, requirements.txt, .py files |
Python |
package.json, tsconfig.json, .ts/.js/.tsx files |
JavaScript/TypeScript |
| Both present | Monorepo — configure each ecosystem separately |
Also check for existing quality tooling configs (.eslintrc, .prettierrc, biome.json, [tool.black] or [tool.ruff] in pyproject.toml, .pre-commit-config.yaml, lefthook.yml). If present, preserve them — only migrate to different tools if the user explicitly requests it (see Guardrails).
Set up tooling
After detecting the ecosystem, follow the appropriate guide:
- Python projects — see python.md for Ruff + pre-commit setup
- JS/TS projects — see javascript.md for Biome + Knip + lefthook + tsc setup
Standard command contract
Every project must expose these five commands (via package.json scripts or Makefile):
| Command | What it does |
|---|---|
format |
Auto-format and sort imports |
lint |
Lint without writing (report only) |
typecheck |
Run type checker (tsc --noEmit, mypy, or pyright) |
check |
All non-writing checks: lint + typecheck + unused-code detection |
check:fix |
Run autofixers (format + lint fix), then run check |
Pre-commit hooks should run check:fix so that commits are always clean.
Workflow
- Install and configure the tools (formatter, linter, type checker)
- Add pre-commit hook infrastructure (lefthook or pre-commit)
- Run the full suite once to establish a clean baseline
- Fix any initial issues so the first "real" commit starts clean
- Commit the configuration files as the first or second commit in the project
When working on existing projects
If a project already has code but no quality tooling:
- Add and configure the tools
- Run the formatter first — commit the formatting changes in a single dedicated commit with a message like
chore: apply initial formatting - Run the linter — fix issues and commit separately:
chore: fix initial lint issues - Wire up pre-commit hooks last so all future commits are clean
Guardrails
- Don't replace existing mature tooling. If a project already uses ESLint/Prettier, Black, or other established tools, keep them. Only migrate to Biome/Ruff if the user explicitly asks.
- Don't broadly disable rules to force a green baseline. Use narrow, targeted exceptions (
// biome-ignore,# noqa: XX) with comments explaining why — never bulk-suppress to make errors disappear. - If tooling binaries aren't available, scaffold configs anyway. Write the configuration files and report the install commands the user needs to run.
Completion checklist
Before considering the setup done, verify:
- Formatter, linter, and type checker installed and configured for the project's ecosystem
- Import sorting enabled (Ruff's
Irules or Biome'sorganizeImports) - All five standard commands work:
format,lint,typecheck,check,check:fix - Pre-commit hooks configured and executable (
pre-commit run --all-filesornpx lefthook run pre-commit) - Baseline autofix applied and a clean check passes with no errors
Installationen
Sicherheitsprüfung
Quellcode ansehen
rarestg/rarestg-skills
Mehr aus dieser Quelle
Power your AI Agents with
the best open-source models.
Drop-in OpenAI-compatible API. No data leaves Europe.
Explore Inference APIGLM
GLM 5
$1.00 / $3.20
per M tokens
Kimi
Kimi K2.5
$0.60 / $2.80
per M tokens
MiniMax
MiniMax M2.5
$0.30 / $1.20
per M tokens
Qwen
Qwen3.5 122B
$0.40 / $3.00
per M tokens
So verwenden Sie diesen Skill
Install code-quality by running npx skills add rarestg/rarestg-skills --skill code-quality in your project directory. Führen Sie den obigen Installationsbefehl in Ihrem Projektverzeichnis aus. Die Skill-Datei wird von GitHub heruntergeladen und in Ihrem Projekt platziert.
Keine Konfiguration erforderlich. Ihr KI-Agent (Claude Code, Cursor, Windsurf usw.) erkennt installierte Skills automatisch und nutzt sie als Kontext bei der Code-Generierung.
Der Skill verbessert das Verständnis Ihres Agenten für code-quality, und hilft ihm, etablierte Muster zu befolgen, häufige Fehler zu vermeiden und produktionsreifen Code zu erzeugen.
Was Sie erhalten
Skills sind Klartext-Anweisungsdateien — kein ausführbarer Code. Sie kodieren Expertenwissen über Frameworks, Sprachen oder Tools, das Ihr KI-Agent liest, um seine Ausgabe zu verbessern. Das bedeutet null Laufzeit-Overhead, keine Abhängigkeitskonflikte und volle Transparenz: Sie können jede Anweisung vor der Installation lesen und prüfen.
Kompatibilität
Dieser Skill funktioniert mit jedem KI-Coding-Agenten, der das skills.sh-Format unterstützt, einschließlich Claude Code (Anthropic), Cursor, Windsurf, Cline, Aider und anderen Tools, die projektbezogene Kontextdateien lesen. Skills sind auf Transportebene framework-agnostisch — der Inhalt bestimmt, für welche Sprache oder welches Framework er gilt.
Chat with 100+ AI Models in one App.
Use Claude, ChatGPT, Gemini alongside with EU-Hosted Models like Deepseek, GLM-5, Kimi K2.5 and many more.