菜单
Measure whether Python tests detect behavior changes through diff-scoped mutation testing. Use when Codex needs to audit the strength of a pytest suite, evaluate whether tests cover changed code, investigate surviving mutants, or propose and verify targeted tests for missed behavior.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/buildfastwithai/gen-ai-experiments --skill test-strength命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Find and qualify evidence-backed potential first customers, early adopters, design partners, or beta users for a startup using recent public pain and buying signals. Use when Codex needs to analyze a product URL or idea, define an ideal customer profile, research public discussions and business pages, identify first-user prospects, rank lead fit and timing, prepare source-based outreach drafts, or create a shareable early-customer prospecting report without sending messages automatically.
Turn a startup, SaaS, app, developer tool, website, repository, or product idea into an evidence-backed business plan, monetization strategy, pricing architecture, editable 12-month financial model, and 90-day execution roadmap. Use when Codex needs to analyze how a startup can become a sustainable business; decide free versus paid, monthly, annual, usage-based, one-time, or lifetime pricing; design tiers and upgrade triggers; estimate unit economics and break-even under explicit assumptions; compare scenarios; or produce a native Markdown business plan, formula-driven Excel workbook, and CSV roadmap from a URL or description.
Audit a startup, SaaS, app, developer tool, landing page, or product before launch from a live URL, localhost page, repository, screenshots, or supplied copy. Use when Codex needs to determine what a startup appears to do, test whether its public experience is launch-ready, inspect positioning, calls to action, product proof, trust, UX, accessibility, responsive behavior, broken paths, technical surface, or launch operations, produce a Ready to launch / Launch after critical fixes / Not ready yet verdict, prioritize exact improvements, or create a polished standalone HTML launch-readiness report.
基于 SOC 职业分类
正在显示 SKILL.md
| name | test-strength |
| description | Measure whether Python tests detect behavior changes through diff-scoped mutation testing. Use when Codex needs to audit the strength of a pytest suite, evaluate whether tests cover changed code, investigate surviving mutants, or propose and verify targeted tests for missed behavior. |
Run the bundled runner from the repository being assessed. Keep the repository working tree unchanged: the runner copies it to a temporary directory before each mutant run.
Confirm that Python and pytest are available. Run from the target repository root.
Run the bundled script, using its absolute skill path:
python <skill-path>\scripts\strength.py [--base <ref>] [path]
Omit both arguments to compare the current worktree with the merge-base of the default branch. Use --base main (or a commit) to choose the diff base. Pass an optional file or directory path to limit which changed Python production files are mutated.
Read strength_report.json in the target repository root. Treat a killed mutant as behavior caught by the suite and a survived mutant as behavior that the suite did not catch. The runner executes the full test suite for every mutant so indirect, fixture-based, and integration coverage are included.
For each item in survived_mutants:
Inspect its diff and decide whether it changes observable behavior for valid inputs.
Discard only genuinely equivalent mutants; state why they are equivalent.
For every real survivor, add one focused test that passes on the original code and fails for the mutant.
Verify that test before suggesting it:
pytest <temporary-test-file>
python <skill-path>\scripts\strength.py verify "<mutant-id>" <temporary-test-file>
The first command must pass. The verification command must print VERIFICATION SUCCESS and exit with code 0. Remove the temporary verification file afterward unless the user asks to keep it.
Use this structure and include only real survivors:
<Total Tests> tests | <Total Mutants> mutants across <Changed Functions Count> changed functions
<Killed Count> killed | <Survived Count> survived | <Equivalent Count> equivalent (discarded)
### SURVIVED
#### <File Path>:<Line Number> <Function Name>
`<Original Expression>` -> `<Mutated Expression>`
Reason for survival: <why the current tests miss this behavior>
Suggested test:
```diff
+ <verified test change>