agentleFS
YorkWong1995YorkWong1995/OPC-Harness/.claude/skills/acceptance-check/SKILL.md

acceptance-check

Skill4 starsChanged 6 months agoMITView on GitHub

Produce a QA acceptance report for a task or change set following the acceptance-document field standard in docs/claude/standards.md.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. hirokisakabe/issuekit★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository7 other files it gives its agents.

The file

Files
SKILL.md

acceptance-check

按 docs/claude/standards.md#验收文档应至少包含 的字段结构,对一项任务或一组改动给出 QA 验收结论。

用法

/acceptance-check <验收对象>

示例:

  • /acceptance-check tasks-p5.md 中 T1-T7
  • /acceptance-check src/opc/agent.py 的工具循环上限

字段要求

输出必须严格包含以下 5 个字段:

  1. 验收对象 — 被验收的任务/改动/文件范围
  2. 验收标准 — 来自任务条目的"完成标准"或 PRD/architecture 中的对应验收点,若任务要求可恢复性,还应包含 evidence / handoff / 前置读取要求
  3. 检查方法 — 实际执行的命令、读取的文件、对比的基线,以及是否检查了可恢复性
  4. 结果记录 — 每项标准的检查结果(含证据:文件路径+行号 / 命令输出关键片段)
  5. 是否通过 — 通过 / 不通过 / 部分通过,并列出未通过项

执行规则

  1. 先定位"验收标准"来源。优先级:tasks-pX.md 条目 > PRD > 架构文档 > 用户口述。来源不明时,要求用户提供。
  2. 检查方法必须是可复现的(命令 / 文件路径),禁止"看起来 OK"这类模糊描述。
  3. 结果记录中,每项检查必须给出可点击引用,例如 [file.md:12](path/file.md#L12);长任务还必须标明 evidence / handoff / 前置读取是否齐全。
  4. "部分通过"必须显式列出未通过项及阻塞原因,不得将其合并为"通过"。
  5. 如果任务声称完成但缺少验证证据、交接信息或前置读取记录,不得直接判定为"通过"。
  6. 如果任务不能在清空聊天上下文后由任务文件和产物恢复,应输出可恢复性风险或不通过结论。
  7. 不擅自修复缺陷;发现问题时建议建立修复任务(可调用 /task-spec 配合)。

输出骨架

[示例:可清空上下文继续]
[验收对象] ...
[验收标准]
- 标准 1: ...
- 标准 2: ...
[检查方法]
- 命令 / 文件 / 对比项
[结果记录]
- 标准 1 → 通过 / 不通过(证据:path:line)
- 标准 2 → ...
[可恢复性结论] 可清空上下文继续(证据:任务条目、evidence、handoff、前置读取记录齐全)
[结论] 通过 / 不通过 / 部分通过
[未通过项 & 后续动作] (仅当非"通过"时)

[示例:不可清空上下文继续]
[验收对象] ...
[验收标准]
- 标准 1: ...
[检查方法]
- 命令 / 文件 / 对比项
[结果记录]
- 标准 1 → 部分通过(证据:path:line)
- evidence / handoff / 前置读取记录 → 不通过(缺少验证证据或交接信息)
[可恢复性结论] 不可清空上下文继续
[结论] 部分通过 / 不通过
[未通过项 & 后续动作]
- 补齐验证证据、交接信息或前置读取记录后重新验收

验收

  • 输出包含全部 5 个字段
  • 每条结果都有可定位的证据
  • "通过"结论与逐项结果不矛盾

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.