core
qa-skills shared knowledge base — dependency, NOT triggerable: executability standards, evidence grading, risk model, type matrix, templates, scripts.
Skill by fishzjp
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/fishzjp-core
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/core
What's inside
- Skill name
core- Description
- qa-skills shared knowledge base — dependency, NOT triggerable: executability standards, evidence grading, risk model, type matrix, templates, scripts. Never invoke standalone; always install with the skills, or references break. 共享知识库(依赖单元,非触发 skill):承载全系列引用的方法/模板/脚本。任何测试任务不要独立触发;装其他 skill 必须连装。
- License
- MIT
- Instructions
- 33 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (20)
- SKILL.md
- case-format.md
- clarify-pattern.md
- coverage.md
- evidence.md
- executability.md
- boundary.md · methods/
- data-driven.md · methods/
- data-factory.md · methods/
- permission.md · methods/
- state-machine.md · methods/
- pipeline-integration.md
- report-template.md
- risk-model.md
- schema-extraction.md
- scan_signals.py · scripts/
- validate_schema.py · scripts/
- test-type-matrix.md
- testing-principles.md
- triage.md
SKILL.md (first lines)
# 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 12 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 12 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)。
From fishzjp/qa-skills, MIT.
More from fishzjp/qa-skills
- 0.665score
qa-memory
fishzjp
Maintain the .qa/ knowledge base of cross-session QA knowledge (quirks, flaky verdicts, defect patterns, contract changes); read before test tasks.
SkillAFreshness: A★ 50Claude Code +9 - 0.660score
qa
fishzjp
End-to-end QA entry: "test this feature fully" orchestrates requirements, strategy, cases, review, execution, bugs, regression, report; resumable.
SkillAFreshness: A★ 50Claude Code +9 - 0.635score
test-reliability
fishzjp
Govern flaky tests and suite reliability: rerun-pass verdicts, root-cause classes, quarantine, retry semantics, health metrics.
SkillAFreshness: A★ 50Claude Code +9 - 0.625score
api-testing
fishzjp
API testing from OpenAPI/Swagger or case schemas: parameters, boundaries, auth, idempotency, concurrency, error responses, data consistency; runnable scripts…
SkillBFreshness: B★ 50Claude Code +9 - 0.625score
automated-e2e-testing
fishzjp
Turn manual cases into Playwright E2E automation run in a browser: page objects, helpers, bug evidence, reports.
SkillBFreshness: B★ 50Claude Code +9 - 0.620score
requirement-analysis
fishzjp
Model a requirement/system: extract goals, scope, roles, rules, exceptions, dependencies from PRD, docs, bugs, code; outputs a structured model with…
SkillBFreshness: B★ 50Claude Code +9 - 0.620score
bug-analysis
fishzjp
对已确认的 Bug 做根因定位、影响分析、回归建议时使用——复现 → 读代码定位根因 → 影响五面分析 → 回归建议,条目(根因/影响/Severity 依据/修复建议/回归建议五个扩展字段)落盘为 Bug 条目。不用于:仅收集 Bug 证据(automated-e2e-testing /…
SkillBFreshness: B★ 50Claude Code +9 - 0.620score
regression-testing
fishzjp
After a code change (diff/fix/requirement change), decide what to regression-test: changed files → functions → features → cases traceability; outputs a ranked…
SkillBFreshness: B★ 50Claude Code +9 - 0.620score
exploratory-testing
fishzjp
Exploratory testing sessions when requirements are vague or docs are missing — charter-driven; outputs system understanding, risks, test ideas.
SkillBFreshness: B★ 50Claude Code +9 - 0.590score
test-strategy
fishzjp
"How should this be tested?" Evidence-backed risk map → scope and depth across functional domains and 10 testing-type axes; includes carry signals, excludes…
SkillBFreshness: B★ 50Claude Code +9 - 0.590score
test-case-review
fishzjp
Review existing test cases (legacy, others', AI) for coverage and executability: build a testable-points baseline, assess independently, revise in place with…
SkillBFreshness: B★ 50Claude Code +9 - 0.590score
test-case-writing
fishzjp
Write manual test cases (markmap) from docs, bugs or code — code-first: review code for bugs first; extracts machine-readable schema.
SkillBFreshness: B★ 50Claude Code +9
Signals
- Stars
- 50
- Forks
- 9
- Open issues
- 1
- Last commit (this folder)
- Sep 20, 2026 (1 month ago)
- Last release
- Sep 20, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/fishzjp/qa-skills
- Website
- fishzjp.github.io/qa-skills/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from fishzjp
- 0.665score
qa-memory
fishzjp
Maintain the .qa/ knowledge base of cross-session QA knowledge (quirks, flaky verdicts, defect patterns, contract changes); read before test tasks.
SkillAFreshness: A★ 50Claude Code +9 - 0.660score
qa
fishzjp
End-to-end QA entry: "test this feature fully" orchestrates requirements, strategy, cases, review, execution, bugs, regression, report; resumable.
SkillAFreshness: A★ 50Claude Code +9 - 0.635score
test-reliability
fishzjp
Govern flaky tests and suite reliability: rerun-pass verdicts, root-cause classes, quarantine, retry semantics, health metrics.
SkillAFreshness: A★ 50Claude Code +9 - 0.625score
api-testing
fishzjp
API testing from OpenAPI/Swagger or case schemas: parameters, boundaries, auth, idempotency, concurrency, error responses, data consistency; runnable scripts…
SkillBFreshness: B★ 50Claude Code +9 - 0.625score
automated-e2e-testing
fishzjp
Turn manual cases into Playwright E2E automation run in a browser: page objects, helpers, bug evidence, reports.
SkillBFreshness: B★ 50Claude Code +9 - 0.620score
requirement-analysis
fishzjp
Model a requirement/system: extract goals, scope, roles, rules, exceptions, dependencies from PRD, docs, bugs, code; outputs a structured model with…
SkillBFreshness: B★ 50Claude Code +9
Cite this page
core skill. Agent Mart. https://agentmart.dev/skills/fishzjp-core (last updated 2026-10-24)