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 skills add ZTE-AICloud/Co-OmniSpec --skill e2e-designgit clone --depth 1 https://github.com/ZTE-AICloud/Co-OmniSpecWrote 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/zte-aicloud/co-omnispec/e2e-design)<a href="https://agentmods.dev/skills/zte-aicloud/co-omnispec/e2e-design"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/e2e-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zte-aicloud/co-omnispec/e2e-design"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/e2e-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00094 | $0.02715 |
| Opus 5.5 | $0.00038 | $0.01086 |
| Sonnet 5.5 | $0.00019 | $0.00543 |
| Haiku 4.5 | $0.00009 | $0.00271 |
Grade A, and why
e2e-design 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 1mo 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
用户输入
$ARGUMENTS
在继续之前, 你必须考虑用户输入(如果不为空).
概述
执行测试实现分析工作流,在黑盒测试用例基础上分析入口函数、外部依赖、测试数据、验证点,并复用存量测试设计。
调用场景:
- 初步设计(在
/design之后):基于设计文档和黑盒测试用例生成测试实现分析报告 - 独立调用:直接执行测试实现分析(需要已有 design.md 和 e2e-test.md)
输入要求:
spec.md:功能规范文档design.md:设计文档e2e-test.md:黑盒测试用例文档
输出:
e2e-impl-design.md:测试实现分析报告
执行流程
1. [ ] 设置环境
- 判断操作系统:Windows 或 Linux
- 运行前置检查脚本:
- Windows:
scripts/powershell/check-prerequisites.ps1 --json --require-design --require-e2e-test - Linux:
scripts/bash/check-prerequisites.sh --json --require-design --require-e2e-test
- Windows:
- 解析输出:
- 提取
FEATURE_DIR(特性目录绝对路径) - 提取
SPEC_FILE(规范文件路径) - 提取
DESIGN_FILE(设计文件路径) - 提取
E2E_TEST_FILE(黑盒测试用例文件路径) - 提取
AVAILABLE_DOCS(可用文档列表)
- 提取
重要:所有路径必须是绝对路径。
2. [ ] 验证前置文件
验证以下必需文件是否存在:
-
检查规范文件:
{FEATURE_DIR}/spec.md是否存在- 如果不存在:错误 "规范文件不存在,请先执行 /specify"
-
检查设计文件:
{FEATURE_DIR}/design.md是否存在- 如果不存在:错误 "设计文件不存在,请先执行 /design"
-
检查测试用例文件:
{FEATURE_DIR}/e2e-test.md是否存在- 如果不存在:错误 "黑盒测试用例文件不存在,请先执行 /e2e-specify"
-
报告验证结果:
- 所有文件存在:继续执行步骤3
- 任何文件缺失:终止流程并报错
3. [ ] 加载上下文文档
加载用于测试实现分析的上下文文档:
必需文档:
- spec.md:读取用户故事、功能需求、验收场景
- design.md:读取架构设计、详细设计、接口定义、数据结构
- e2e-test.md:读取所有黑盒测试用例(Given-When-Then 格式)
可选文档(按优先级加载):
-
baseline 文档:
baseline/code-structure.md:现有代码结构baseline/existing-apis.md:现有接口定义
-
存量测试代码:
- 搜索现有测试目录(如
tests/、test/) - 查找类似功能的测试实现
- 提取测试范式、Mock 对象使用、测试数据构造方法
- 搜索现有测试目录(如
加载策略:
- 每个文档独立容错,失败不中断流程
- 记录成功加载的文档列表
- 标注缺失的文档
4. [ ] 启动测试实现分析 Agent
使用 Agent 工具启动 @"test-impl-design (agent)",传递以下参数:
Agent 参数:
subagent_type: "general-purpose"(使用通用 agent)description: "测试实现分析 - 生成测试实现分析报告"prompt包含以下内容:
# 测试实现分析任务
## 调用场景
{场景类型}: 初步设计/独立调用
## 输入文件
- spec.md: {SPEC_FILE}
- design.md: {DESIGN_FILE}
- e2e-test.md: {E2E_TEST_FILE}
- feature_dir: {FEATURE_DIR}
- baseline_docs: {成功加载的 baseline 文档列表}
- existing_tests: {找到的存量测试代码}
## 任务要求
1. 读取 spec.md、design.md、e2e-test.md
2. 分析每个黑盒测试用例的入口函数
3. 识别外部依赖并设计 Fake 对象
4. 设计测试数据(输入数据、Fake 数据)
5. 定义验证点(返回值、状态变化、可观察行为)
6. 分析存量测试复用可能性
7. 生成测试实现分析报告(e2e-impl-design.md)
## 输出位置
- e2e-impl-design.md: {FEATURE_DIR}/e2e-impl-design.md
## 重要说明
- 重点关注入口函数签名、外部依赖、测试数据
- 复用存量测试模式和测试工具
- 保持黑盒测试特性,不暴露内部实现
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.
- 1mo ago First seen · 292 lines · 94 tokens per session scan A 61eeb99fcc12
e2e-design is a skill published in the GitHub repository ZTE-AICloud/Co-OmniSpec (57 stars, last pushed 3mo ago), licensed MIT. It adds 94 tokens to every session and 2,715 once invoked, about $0.0004 per session on Opus 5.5. 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
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.