Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/fishzjp/qa-skills/corenpx skills add fishzjp/qa-skills --skill coregit clone --depth 1 https://github.com/fishzjp/qa-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fishzjp/qa-skills/core)<a href="https://agentmods.dev/skills/fishzjp/qa-skills/core"><img src="https://agentmods.dev/badge/skills/fishzjp/qa-skills/core.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00127 | $0.00689 |
| Opus 5 | $0.00063 | $0.00345 |
| Sonnet 5 | $0.00025 | $0.00138 |
| Haiku 4.5 | $0.00013 | $0.00069 |
Grade A, and why
core scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
qa-skills 共享知识库（core）
本目录是框架的公共层：不定义工作流、不面向用户触发，仅被 skills/ 下其余
10 个 skill（qa / requirement-analysis / test-strategy / …）以相对路径
../core/<file> 按需引用。单一维护源，多 skill 复用。
共享文档
| 文件 | 内容 |
|---|---|
evidence.md |
证据分级标准（E0–E4）与状态标注 |
risk-model.md |
风险评级模型（评级强制挂证据） |
executability.md |
用例可执行性硬标准（8 条，一票否决项） |
testing-principles.md |
测试原则 |
case-format.md |
用例编号与格式规范 |
coverage.md |
覆盖评估口径 |
schema-extraction.md |
schema.yaml 抽取规则 |
clarify-pattern.md |
澄清检查点模式 |
test-type-matrix.md |
类型决策矩阵（十轴全轴必答） |
triage.md |
失败分流规范（四分类判定树 + G/S 信号 + 反吞没条款，失败 ≥3 条触发） |
pipeline-integration.md |
流水线集成与非交互运行约定（⏸ 检查点降级、产物落盘、退出码语义、CI 触发分层与失败回流） |
report-template.md |
测试报告模板 |
methods/*.md |
设计方法细则（边界 / 数据驱动 / 权限 / 状态机）与执行层造数模式（数据工厂） |
scripts/*.py |
Schema 校验器、类型信号扫描器 |
When NOT to Use
- 任何具体测试任务（写用例、定策略、查 Bug 等）都不要触发本 skill： 它不包含工作流，独立使用没有产出。对应任务请用其余 10 个 skill 之一。
- 本 skill 仅在两种情况下被触及：① 其余 skill 工作流按需引用上述文件； ② 安装/校验场景（作为安装依赖单元被安装器识别）。
What ships with it
19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- case-format.md 10 KB
- clarify-pattern.md 3.8 KB
- coverage.md 12 KB
- evidence.md 4.3 KB
- executability.md 3.9 KB
- methods/boundary.md 2.9 KB
- methods/data-driven.md 3.7 KB
- methods/data-factory.md 3.6 KB
- methods/permission.md 1.8 KB
- methods/state-machine.md 2.4 KB
- pipeline-integration.md 9.4 KB
- report-template.md 7.7 KB
- risk-model.md 4.2 KB
- schema-extraction.md 6.8 KB
- scripts/scan_signals.py 19 KB runs code
- scripts/validate_schema.py 34 KB runs code
- test-type-matrix.md 17 KB
- testing-principles.md 3.6 KB
- triage.md 14 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed 9d17719c3cba
- 5d ago First seen · 40 lines · 127 tokens per session scan A 87b2f36f5915
core is a skill published in the GitHub repository fishzjp/qa-skills (23 stars, last pushed 2d ago), licensed MIT. It adds 127 tokens to every session and 689 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
qa-expert
Expert-level quality assurance, testing strategies, automation, and QA processes. Use when the user mentions testing, test automation, quality assurance, or Selenium, or when the task involves Testing Types, QA Processes, Test Strategy, or Defect Management.
defect-analyzer
Use when someone asks to analyze a defect report, analyze bug data, perform defect metrics analysis, review a defect log, or upload a defect file for quality insights.
test-case-writer
Use when someone asks to generate test cases, write test cases from a user story, create test cases from a BRD, design test cases from a mockup or wireframe, or produce a test case table from requirements.
test-review
Ревью только что написанных или изменённых автотестов на соответствие best practices TypeScript + Playwright (по официальной документации) и конвенциям вашего проекта. Используй по /test-review либо после написания/правки любого теста (UI E2E, API, UI+API, моки, visual, mobile) или Page Object/фикстуры/констант — до…
playwright-expert
Expert in Playwright E2E testing framework, auto-waiting mechanisms, test generation, trace viewer, and CI/CD integration. Use when the user mentions testing, end-to-end tests, QA, automation, end-to-end testing, or test automation, or when the task involves Playwright Framework, Test Organization, Advanced Features…
selenium-expert
Expert in Selenium WebDriver, Selenium Grid, page object model, waits, cross-browser testing, and test automation frameworks. Use when the user mentions testing, end-to-end tests, QA, automation, WebDriver, or Selenium grid, or when the task involves Selenium Components, Browser Support, Advanced Features, or Basic…