code-qc
Run a structured quality control audit on any codebase. Use when asked to QC, audit, review, or check code quality for a project. Supports Python, TypeScript, GDScript, and general projects. Produces a standardized report with PASS/WARN/FAIL verdict, covering tests, imports, type checking, static analysis, smoke tests, and documentation. Also use when asked to compare QC results over time.
Why use this skill?
Optimize your development workflow with the OpenClaw code-qc skill. Get comprehensive 8-phase audits, automated test reporting, and semantic code analysis for Python, TypeScript, and GDScript.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/isonaei/code-qcWhat This Skill Does
The code-qc skill acts as an intelligent, automated quality assurance engineer for your software projects. Rather than relying on simple linting, it executes an 8-phase audit that combines industry-standard static analysis (ruff, eslint, gdlint) with semantic logic checks and dynamic smoke test generation. It provides a standardized PASS/WARN/FAIL verdict, making it an essential tool for maintaining code health, ensuring type safety, and monitoring technical debt over time. By utilizing a configurable .qc-config.yaml file, it adapts to specific language requirements and team standards, allowing for project-specific thresholds and exclusions.
Installation
To integrate this skill into your environment, run the following command in your terminal:
clawhub install openclaw/skills/skills/isonaei/code-qc
Ensure your project contains a .qc-config.yaml in the root directory if you wish to override the default sensitivity or exclusion rules.
Use Cases
- Automated PR Reviews: Run the audit in
--changed-onlymode during CI/CD workflows to catch regressions before merging. - Legacy Codebase Audits: Perform a full 8-phase audit to establish a baseline of test coverage, documentation quality, and linting errors for a project you are inheriting.
- Trend Analysis: Periodically execute the skill to compare QC results over time, tracking whether code quality is improving or degrading as features are added.
- Sanity Checks: Use the
--quickflag for a rapid verification of imports, syntax, and linting status during active development iterations.
Example Prompts
- "Run a full quality control audit on this project and tell me if it passes our standard criteria."
- "Perform a quick sanity check and show me the report for the latest changes in the current branch."
- "Compare our current codebase quality against the baseline from last week—what has improved or regressed?"
Tips & Limitations
- Configuration: Always define your
thresholdsin.qc-config.yamlto match your team’s definition of 'clean' code; otherwise, the tool defaults to strict modes. - Language Support: While the tool is optimized for Python, TypeScript, and GDScript, it can handle general projects; ensure your project-specific testing tools (like
pytestornpm) are configured correctly in your environment. - Safety: Because this skill executes testing scripts and static analysis tools, ensure that your environment is properly sandboxed if you are auditing untrusted codebases.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-isonaei-code-qc": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, code-execution
Related Skills
godot-dev-guide
Godot 4.x 完整開發指南。涵蓋 GDScript 模式、文件格式(.gd/.tscn/.tres)、場景架構、物理/UI/音效、性能優化、多平台導出、測試。自動觸發於 Godot 相關開發。
literature-manager
Search, download, convert, organize, and audit academic literature collections. Use when asked to find papers, build a literature library, add papers to references, download PDFs, convert papers to markdown, organize references by category, audit a reference collection, or collect code/dataset links for tools mentioned in papers.
virtual-reading-group
Orchestrate a multi-agent virtual academic reading group. Use when reading multiple papers, generating expert discussion notes, cross-examining positions across papers, and synthesizing integrated summaries with full citations. Triggers on requests to analyze academic literature, run paper discussions, create reading group sessions, or synthesize research across multiple sources. Supports 1-50 papers with configurable expert personas (1-4 papers work but produce simpler single-expert output).