agentleFS
lgy1027lgy1027/specflow-agent-pack/skills/align/SKILL.md

align

Skill4 starsChanged 13 days agoApache-2.0View on GitHub

在实现前对齐跨角色、跨团队或跨系统的可观察行为;只在真实边界产生最小契约,优先沿用项目规范与测试。

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use blueprint, research and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • WordPressSkill

    blueprint

    Use when the deliverable is WordPress Playground Blueprint JSON or a Blueprint bundle, including creating, editing, reviewing, validating schema keys, choosing steps/resources, and debugging Blueprint files. For only running or sharing a Playground environment, use wp-playground.

    Also in 3 projects that use this

  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 3 projects that use this

The file

Files
SKILL.md

/align — 跨边界行为契约

仅当至少两个责任方/系统需要对齐可观察行为,或接口歧义可能造成明显返工时使用。单一负责人改内部实现通常不需要新契约。

1. 找到需要对齐的边界

  • 有 /probe 决策简报时复用;没有也可根据当前上下文工作,不要求完整发现流程。
  • 复用前序事实台账时,同时继承每项的证据状态和最新更正。用户明确撤回/更正的旧值视为已被新值取代;不得在理由、契约表或交接摘要中再次引用旧值为“已确认”。历史冲突无法判定时保留 Unknown,指出冲突并请求澄清。
  • 明确调用方、提供方、双方负责人、用户可见行为、数据/安全边界,以及最合适的现有公开接口/交接点。
  • 有仓库访问时读取相关项目规范、现有接口和测试,沿用项目词汇与格式;没有仓库/文件访问时标为 Unknown 或追问,不声称读过实现、测试或项目约定。不要为了满足 SpecFlow 引入新协议、Schema 语言、框架、CI 平台或状态机。
  • 如果不存在真实的跨边界分歧,说明原因并跳过契约生成。
  • 若生成或维护契约状态,区分“已评审”和“已确认”:已确认表示有权的业务决策人对本次范围/验收行为完成确认,技术负责人确认接口与实现边界;涉及数据、安全或设备风险时,补充对应责任人的确认。记录确认人角色、范围/版本和日期。授权人或确认记录缺失时保持草稿/待确认,不把文档状态解释为生产批准。

2. 对齐可观察行为

只定义当前边界所需的最小内容:

  • 将各方描述保留为“已报告说法”,直到现有实现/测试证据或有权负责人确认;不要因一方声称“后端现在就是这样”便判其正确,也不要把建议写成现行规则。新状态、失败语义、幂等、重试/回调和超时只列为待确认决策,除非已有证据支持或负责人明确确认。
  • 输入/触发条件与预期输出/效果;
  • 关键成功、歧义/边界和失败行为;
  • 责任归属、鉴权和副作用边界;
  • 仅在相关时讨论超时、重试、取消、幂等或部分结果;没有实现证据或负责人确认时,将它们列为待决项,不写成既定规则;
  • 验收证据和测试边界,并说明该测试不能证明什么。

优先用简洁行为表或项目原生规格,不生成大套契约包。只有工具链或多个调用方确实需要时才加机器可读 Schema。不要强制所有 AI 功能都有 confidence、source_quote、统一状态枚举或 CI Job。

默认把最小行为表直接回复在对话中。只有用户明确要求可交接/留档产物,或双方确实需要持久契约时,才创建文件;“帮我们对齐”本身不代表要写文件。需要文件且项目没有既有格式时,读取 references/contract-template.md 并删除不适用字段。即使生成文件,也只保留本次已确认内容和待决项,不为完整度填入未确认规则。

3. 技术选择随项目和边界决定

  • 有 OpenAPI、JSON Schema、Protobuf、类型定义、API 描述、测试框架或 CI 时沿用现有标准。
  • 只有实际采用流式、异步或 CLI 时,才定义相应通信细节。
  • 软件连接传感器/执行器或机器人时,约定相关命令限制、单位/坐标、状态反馈、断连行为、人工接管和停止方式。契约不能替代独立设备保护措施或安全审批。
  • 校验优先扩展项目现有测试,并在双方约定的公开边界上验证。不要为了演示而默认引入 Python、固定 Fixture 或新的 CI Job。
  • 仅当仓库有对应 CI 且能校验本次代码/测试生成的产物时才给 CI 接线。说明是否阻断合并还取决于仓库策略。

4. 交接

把已对齐行为、责任人、验收证据、未决阻断项和产物位置记入项目现有系统。不要为流程仪式生成文件。不得声称书面契约能强制运行时行为或保证零漂移。

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.