Automates code quality assessment by collecting changes and running AI evaluations.
Install
mkdir -p .claude/skills/eval && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17046" && unzip -o skill.zip -d .claude/skills/eval && rm skill.zipInstalls to .claude/skills/eval
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
综合评测技能：先采集SDD流程的代码变更信息，再使用第三方评测模型对代码质量进行评估。当用户需要"综合评测"、"完整评测流程"、"SDD评测"时触发本技能。Key capabilities
- →Collect code change information from SDD branches
- →Scan target directories for code changes
- →Extract feature_infos and code_blocks for evaluation
- →Perform code quality assessment using third-party models
- →Output evaluation results to console and file
How it works
The skill orchestrates two sub-skills: one to collect code changes from an SDD branch and another to evaluate the code quality using a third-party LLM, then outputs the results.
Inputs & outputs
When to use eval
- →Evaluate code quality
- →Run SDD code assessment
- →Check code consistency
- →Get automated code review feedback
About eval
Captures code changes within an SDD workflow and utilizes external models to grade code quality, consistency, and correctness. It outputs detailed metrics and improvement suggestions.
综合评测技能：先采集SDD流程的代码变更信息，再使用第三方评测模型对代码质量进行评估。当用户需要"综合评测"、"完整评测流程"、"SDD评测"时触发本技能。
When not to use it
- →When the user does not need a complete evaluation
- →When the user does not need a complete SDD evaluation process
- →When the user does not need SDD evaluation
Prerequisites
Limitations
- →The skill requires a git repository and a valid SDD branch
- →The skill requires a configured LLM API access
- →The skill's evaluation process may take several minutes
How it compares
This skill provides an integrated, automated code quality assessment within an SDD workflow, unlike manual code reviews.
Compared to similar skills
eval side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| eval (this skill) | 0 | 3mo | Review | Intermediate |
| python-testing-patterns | 77 | 2mo | Review | Intermediate |
| dependency-upgrade | 26 | 5mo | Review | Intermediate |
| test-cases | 57 | 7mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
python-testing-patterns
wshobson
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.
dependency-upgrade
wshobson
Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing. Use when upgrading framework versions, updating major dependencies, or managing breaking changes in libraries.
test-cases
cexll
This skill should be used when generating comprehensive test cases from PRD documents or user requirements. Triggers when users request test case generation, QA planning, test scenario creation, or need structured test documentation. Produces detailed test cases covering functional, edge case, error handling, and state transition scenarios.
reviewing-code
CaptainCrouton89
Systematically evaluate code changes for security, correctness, performance, and spec alignment. Use when reviewing PRs, assessing code quality, or verifying implementation against requirements.
wcag-audit-patterns
wshobson
Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance. Use when auditing websites for accessibility, fixing WCAG violations, or implementing accessible design patterns.
code-coverage-with-gcov
gadievron
Add gcov code coverage instrumentation to C/C++ projects