Перейти к содержимому
TakoAPI
Назад к навыкам

code-qc

от isonaei

Web & Frontend Development
435Число загрузок по данным clawskills.sh
0Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

Run a structured quality control audit on any codebase.

Описание

Что делает этот навык

Runs a structured, multi-phase quality control audit on a codebase and produces a report with a PASS, WARN, or FAIL verdict. Supports Python, TypeScript, and GDScript projects, covering tests, imports, type checking, static analysis, smoke tests, and documentation. Results can be saved as a baseline and compared across runs.

Combines language-specific static analysis tools (ruff, eslint, mypy) with AI-generated smoke tests and semantic checks in a single workflow, replacing the need to run and interpret each tool separately.

Когда его использовать

  • Auditing a Python package before publishing to PyPI
  • Running QC on a pull request before merging
  • Comparing code quality metrics between two releases
  • Quick sanity check on a TypeScript project after refactoring
  • Finding missing docstrings and type errors in a GDScript game project

Пример сценария

ВВОД

User asks: Run a full QC audit on my Python project

АГЕНТ
  1. 1

    Detect project type and load .qc-config.yaml if present

  2. 2

    Run the test suite with coverage using pytest

  3. 3

    Check import integrity, run ruff for static analysis, and mypy for type errors

  4. 4

    Generate smoke tests for discovered business logic entry points

  5. 5

    Verify documentation and git state, then determine verdict

ВЫВОД

qc-report.md with PASS/WARN/FAIL verdict and per-phase breakdown, plus .qc-baseline.json saved for future comparison

Установка

clawhub install isonaei/code-qc

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки