auto-test-project SKILL.md skillA
auto-test-project from huangwb8/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add huangwb8/skills/auto-test-project@git:20260906.d5147b3Pins git:20260906.d5147b3 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- huangwb8/skills
- Path
skills/alpha/auto-test-project/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260906.d5147b3, committed Sep 6, 2026
- First version recorded
- Sep 4, 2026
- Size
- 9,491 bytes
- Repository stars
- 50
- License
- MIT
当用户明确要求“测试项目”、 “运行 auto-test-project”或“进行项目级测试”时使用。对完整项目执行多轮 A 轮批判性测试与 B 轮质量检查，发现、记录、修复并验证问题。⚠️ 不适用：用户只是想优化功能、询问项目问题，或没有明确测试意图。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# auto-test-project（项目级自动化测试驱动优化） ## 目标 为具备明确目录和可执行入口的完整项目提供可追溯的项目级测试与优化流水线：项目初始化、A 轮问题发现与修复、B 轮质量原则检查、验证和交付总结。仅在用户明确要求项目级测试时触发；单个 Agent Skill 使用 `auto-test-skill`。 本 Skill 将“项目”定义为具有指令文件或等价入口、明确目录结构和功能模块，并包含可执行代码、脚本或流程定义的项目，包括 Agent Skills、工作流项目、脚本工具集和结构化文档项目。本 Skill 不替代领域业务判断，不默认修改远程系统，不把报告模式误当作发布阻断，也不负责单 Skill 测试。 ## 流程 ### 输入 - 项目根目录、用户指定的测试范围、优化目标或 A 轮次数。 - 项目指令文件、配置文件、模块目录、可执行代码/脚本和已有测试入口。 - 需要关注的历史问题、已知约束和可接受的修改边界。 排除历史任务产物、缓存、依赖目录和敏感信息。先验证项目结构与可执行入口，再确定项目类型、核心模块和跨模块测试边界；配置中的 `project_testing`、`a_round` 和 `b_round_check` 是规划口径的单一来源。 ### 执行步骤 1. **初始化会话**：使用宿主已经公开并锁定的任务根；调用 `scripts/create_test_session.py` 创建 A/B 会话及模板文件。缺省 `--task-root` 时才分配新任务；A/B 轮和 continuation 必须显式复用同一 task root，不猜测最近任务。 2. **识别项目**：检查指令文件、目录结构、功能模块、入口和测试边界，排除 `node_modules/`、`__pycache__/`、`.git/`、`tests/`、`plans/` 和 `_artifacts/` 等配置的排除路径。 3. **执行 A 轮（可重复 N 次）**：结合 `references/CRITICAL_THINKING_GUIDE.md` 与配置的审查范围独立发现问题；为每个问题记录证据、影响、优先级、修复建议和验收标准，形成可引用的 `P0-1` 等编号。 4. **修复并轻量测试**：按计划优先修复 P0/P1，再处理其它问题；只做最小必要修改，补充 `TEST_PLAN.md` 和 `TEST_REPORT.md` 中的可复现命令、结果和证据。项目已有测试时优先运行受影响范围，再按风险扩大验证。 5. **判断下一轮**：检查计划中的问题是否均有报告对应项、成功标准是否有验证结论，以及 P0/P1 是否闭环；达到用户指定轮数或明确的停止条件后进入 B 轮。 …
Read the whole file at its exact version.
How to install
mdr add huangwb8/skills/auto-test-project@sha256:4b61e85906d1ae5dThe line at the top of this page pins the label git:20260906.d5147b3, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_2ffbm5ckeirkbhxj)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 4, 2026 and Sep 6, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260906.d5147b3 latest | 2026-09-06 | d5147b3 | 9,491 B | A | view · diff |
| git:20260905.a346b91 | 2026-09-05 | a346b91 | 24,336 B | A | view · diff |
| git:20260905.7c0ea7c | 2026-09-05 | 7c0ea7c | 24,297 B | A | view · diff |
| git:20260905.a39953d | 2026-09-05 | a39953d | 23,621 B | A | view · diff |
| git:20260904.10fceff | 2026-09-04 | 10fceff | 23,491 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9491 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
huangwb8/skills · 50 stars · license MIT · pushed 2026-10-17 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_2ffbm5ckeirkbhxj GET https://markdownregistry.com/api/v1/resolve?ref=huangwb8/skills/auto-test-project GET https://markdownregistry.com/api/v1/blob/4b61e85906d1ae5d032f8169aa3427d7b5d1c7e0c9ba9c11b896b235ea0c5dc9
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.