Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Qa Test Strategy · echovic | DecimalAI

testingby echovic

Qa Test Strategy

echovic/qa-test-strategy

Source echovic/boss-skill ↗License MIT

测试策略和测试金字塔原则，定义单元测试、集成测试、E2E测试的分布和覆盖要求

SkillScore91Maintained

Automatic

QA & Test Engineering pack

Last verified 8/19/2026

What it changes

Passed 20 of 22 test cases with the skill, and 11 of 22 without it.

Without skill50%

With skill91%

Checks it passed that the model alone missed

Requires zero memory leaks for backend services.
Requires zero memory leaks for frontend applications.
Requires backend API P50 latency to be less than 100ms.

and 13 more in the full report

9 fixed11 passed either way2 still failing0 broke

Pass-rate lift: +41 pp
Tokens: +20%
Agent turns: 0%
Response time: -6%

Model gemini-3.6-flashMeasured 8/19/2026v120 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/echovic-qa-test-strategy/SKILL.md https://app.decimal.ai/s/echovic-qa-test-strategy/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add echovic-qa-test-strategy, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/echovic-qa-test-strategy/ and pins it in .decimal/skills.lock

decimalai skills add echovic-qa-test-strategy

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/echovic-qa-test-strategy/SKILL.md https://app.decimal.ai/s/echovic-qa-test-strategy/SKILL.md

Raw file: /s/echovic-qa-test-strategy/SKILL.md ↗ · machine-readable summary at /s/echovic-qa-test-strategy.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

We need to set up performance and quality benchmarks for our web service deployment. Please outline the performance testing goals for frontend and backend latency/throughput, along with rules for verifying core business paths vs mock data.

What was checked, without and with the skill
Checked	Without skill	With skill
Sets backend API performance targets to P50 latency under 100ms and P99 latency under 500ms with at least 100 concurrent users.	Missed	Passed
Sets frontend performance targets to first screen load time under 3 seconds.	Missed	Passed
Mandates that core user paths proven only by mock or stub data cannot serve as release evidence.	Passed	Passed

case-03 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md62 linessingle file

测试策略与测试金字塔

测试金字塔原则

          /\
         /  \
        / E2E \          ← ~10%：端到端用户流程【必须编写】
       /--------\
      /  集成测试  \       ← ~20%：组件/服务/API 交互
     /--------------\
    /    单元测试     \    ← ~70%：函数/组件/服务逻辑
   /--------------------\

E2E 测试是强制要求

每个项目必须编写 E2E 测试，最少覆盖：

创建流程
编辑流程
删除流程
列表展示
核心业务流程

前端 vs 后端测试分布

层级	前端测试	后端测试
单元测试	组件渲染、Hooks、工具函数	Service 层、业务逻辑、工具类
集成测试	组件交互、状态管理、API 调用	API 端点、数据库操作、服务间调用
E2E 测试	UI 用户流程	API 完整流程、跨服务调用

QA Attack Protocol

重放核心用户路径：证明核心用户路径真实可用
捕获真实 payload 与服务端响应：验证请求 payload、服务端响应和 schema 一致性
攻击认证授权：覆盖匿名、授权、非授权、过期、越权
攻击数据边界：empty state、pagination、第二页、旧数据、illegal enum、long input、double submit
攻击业务一致性：核对界面展示与服务端业务常量一致
验证产物类功能：验证核心产物、记录或状态存在、可展示、可继续用于下游流程

Track record

Benchmark

20 / 22

test cases passed, vs 11 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

echovic / boss-skill

skill/skills/qa/test-strategy/SKILL.md

View on GitHub ↗

License MITImported 10/2/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.