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/davidyichengwei/agentic-engineering-framework/workflow-test-generationnpx skills add davidYichengWei/agentic-engineering-framework --skill workflow-test-generationgit clone --depth 1 https://github.com/davidYichengWei/agentic-engineering-frameworkWhat 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 | $0.00048 | $0.01232 |
| Opus 5 | $0.00024 | $0.00616 |
| Sonnet 5 | $0.00010 | $0.00246 |
| Haiku 4.5 | $0.00005 | $0.00123 |
Grade A, and why
workflow-test-generation 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 3d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
测试生成
Step 0: 意图识别与路径路由
根据调用上下文判断走哪条路径：
| 信号 | 路径 | 执行步骤 |
|---|---|---|
由 workflow-code-generation 完成后衔接进入，或用户明确提到需求管理链接 |
完整流程 | Step 1 → 2 → 3 → 4 → 5 |
| 用户直接说"给 X 写个测试"/"补个单测"，指定了具体代码 | 快速补测试 | Step 2 → 3 → 4 |
由 workflow-system-design 讨论测试计划章节时加载 |
测试策略设计 | Step 1 → 2 → 3，只输出计划，不生成代码 |
如果无法判断，默认走完整流程。
Step 1: 收集测试上下文
完整流程和测试策略设计执行本步骤。快速补测试跳过（用户已指定了被测代码）。
尝试读取 docs/design-docs/<module>/<feature>/spec.md：
有 spec.md：
- 读取 "7. 测试计划"
- 测试计划明确 → 进入 Step 2
- 测试计划不完整 → 补充读取 "2. 目标"、"3. 需求"、"4. 设计方案"，自行判断
无 spec.md（为已有代码补测试）：
- 询问用户要测哪些函数/类，基于代码生成
Step 2: 确定测试类型
根据代码特征自动判断需要哪些测试类型（可组合，非互斥），无法判断时才询问：
| 特征 | 测试类型 |
|---|---|
| 纯函数、无外部依赖 | 单元测试 |
| 端到端流程、多组件交互 | 集成测试 |
| spec.md 有性能指标要求 | 性能测试 |
一个 feature 通常需要多种测试类型组合，例如：核心逻辑用单元测试 + 端到端用集成测试。
Step 3: 制定测试计划
分析被测代码，制定测试计划（不生成代码）：
- 读取被测代码，识别公共接口、输入/输出、副作用、需要 mock 的依赖
- 读取 reference/boundary-checklist.md，选择适用的边界条件
- 根据项目需要，读取对应模块的测试参考文档（如有）
- 为每个测试目标列出：正常路径、边界条件、异常场景的具体测试点
创建测试任务清单，与用户确认后再继续：
示例：
1. [pending] UnitTest - FooClass::Bar() 正常路径 + 边界条件
2. [pending] UnitTest - FooClass::Bar() 异常处理
3. [pending] IntegrationTest - 端到端流程
测试策略设计路径到此结束。将测试计划输出为 spec.md 测试计划章节的内容，不进入 Step 4。
Step 4: 逐个生成测试
仅完整流程和快速补测试执行本步骤。
4.1 加载编码规范（🚨 强制前置）
| 规范 | 何时加载 |
|---|---|
bp-coding-best-practices |
始终 |
std-cpp |
.cc/.cpp/.h 文件 |
std-go |
.go 文件 |
根据项目需要，额外加载其他编码规范 skill。
4.2 逐个生成
对每个测试任务生成测试代码。每个测试必须覆盖三类场景：
- 正常路径 — happy path
- 边界条件 — 基于 Step 3 选出的 boundary-checklist 条目
- 异常场景 — 错误输入、异常处理
生成后更新构建配置，复用项目现有的测试基类和断言工具（不要自己造）。
每完成一个任务，标记 [completed]，继续下一个。
Step 5: 收尾流程
仅完整流程执行本步骤。
前置条件：所有测试用例已通过。
提示用户进入 workflow-code-review 进行 AI 代码评审（同时评审功能代码和测试代码）：
自测已全部通过。
推荐下一步：
- 说"CR"或"代码评审"进入 AI 代码评审阶段
强制规则
- 测试计划必须经用户确认后才能生成代码
- 必须覆盖三类场景：正常路径 + 边界条件 + 异常场景
- 必须应用 boundary-checklist：Step 3 中读取并选择适用条目
- 必须可编译运行：包含所有必要头文件/导入，更新构建配置
- 复用现有基础设施：使用项目的测试基类和断言工具，不要自己造
- 测试全部通过才能推进：编译失败或用例未通过时，先修复，确认全部 PASS 后才可进入 CR
What ships with it
1 file 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.
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.
- 3d ago First seen · 117 lines · 48 tokens per session scan A 8e824a6e2a1e
workflow-test-generation is a skill published in the GitHub repository davidYichengWei/agentic-engineering-framework (159 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 1,232 once invoked, about $0.0002 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
pest-testing
Use this skill for Pest PHP testing in Laravel projects only. Trigger whenever any test is being written, edited, fixed, or refactored — including fixing tests that broke after a code change, adding assertions, converting PHPUnit to Pest, adding datasets, and TDD workflows. Always activate when the user asks how to…
write-vibe-tests
Write or refactor Mistral Vibe tests with proper decoupling. Use when adding behavior coverage, testing ports/adapters, replacing brittle mocks, creating fakes, adding characterization tests before refactors, or changing tests under tests/ for vibe/core, vibe/cli, vibe/acp, tools, config, sessions, skills, hooks, MCP…
composing-matchers
Build compound Gomega assertions by combining matchers — And/SatisfyAll (all pass), Or/SatisfyAny (any pass), Not (negate), WithTransform to map the actual before matching, Satisfy for an ad-hoc predicate, HaveValue to dereference pointers/interfaces, HaveField for struct fields and method results, HaveEach for every…
adding-dbt-unit-test
Creates unit test YAML definitions that mock upstream model inputs and validate expected outputs. Use when adding unit tests for a dbt model or practicing test-driven development (TDD) in dbt.
testing-guide
Design, write, run, and diagnose Synergy tests with Bun, temporary Scope isolation, deterministic fixtures, and behavior-first assertions. Use for TDD, bug regressions, feature tests, migration tests, flaky tests, coverage, package tests, frontend tests, and selecting verification gates.
test
Generate tests and coverage plans. Triggers: "test", "generate tests and coverage plans.", "test skill".