agentleFS
WanghaoyihaoyiWanghaoyihaoyi/agent-skills/skills/check/SKILL.md

check

Skill3 starsChanged 34 days agoMITView on GitHub

检查发布准备度,并完成已授权的提交、推送、发布及 issue/PR 队列维护。用于“能否发布”“提交推送”“发布前检查”“批量处理 issue/PR”;普通代码查错用 code-review,补丁必要性用 patch-audit,架构减法用 prune。

80 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval and 10 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.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • JuliusBrusseeSkill

    backprop

    Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • +6 more from Lambenthan
  • +1 more from skyllwt

The file

Files
SKILL.md

Check

来源:基于 Tw93 / Waza 的 check 技能 改编。保留 Tw93 的 MIT 版权声明。

首条进度消息以 🥷 开头。负责发布判断与交付收尾,不重复承担日常代码审查、方案执行或架构重构。

只问是否可发布时保持只读。已有明确交付授权时,完成该链路中的必要检查与动作,不在每一步重复确认;本 skill 不扩展部署、生产访问、评论、合并或发布权限。

按意图选择

  • 普通 diff、分支或 PR 查错:转到 code-review,保持用户指定范围与只读要求。
  • 检查新增复杂度是否必要:仅在用户要求该类复审或符合其自动触发条件时使用 patch-audit;清理已有架构:prune。不因提交或发布检查默认把这些流程全部再跑一遍,复用已有结论。
  • 是否值得发版、提交、推送或发布:发布与交付。
  • 批量梳理 issue/PR:队列维护。仅审一个 PR 的代码仍用 code-review。
  • CLI、插件、安装包或反复修订的候选版本:产物与发布面。
  • 对外回复或关闭条目:回复操作,仅在相应动作已授权时执行。

工作区与证据

读取项目规则、当前目录、分支、git status --short --branch -uall,区分本任务、其他任务和来源不明的改动。不能为了获得干净工作区而移动、隐藏、回退或暂存他人的内容。需要隔离验证时使用临时副本或工作树。

确认审查基线、目标提交、目标环境和实际交付物。已完成的相关审查可复用,但先确认代码范围未变,说明证据取得时间和限制。没有审查证据时按风险使用 code-review;代码改变后重新核对受影响部分。

从项目说明、构建配置和 CI 取得真实验证命令。缺少运行时、测试未执行或脚本提前退出,都不能报告通过;源码测试、构建、安装、服务健康与业务验收分别报告。

需要补充回归或业务验收证据时,使用 test-audit 的独立预期、最小充分检查与停止条件;同一候选版本已有的有效证据直接复用。涉及异步任务、真实模型、语音或设备时,按 专项行为验收 核对实际覆盖层级。受理回执、工具调用或播放命令不能证明业务完成或设备出声;缺哪层就报告哪层未验证。必要门禁和指定验收通过后停止,不为发布判断追加无关测试治理。

发布检查按 项目上下文与发布清单 选择适用项。普通提交不强制执行安装包发布、上传或线上验收。只读辅助脚本 scripts/release_gate.py 可收集本地 Git 与版本信号;它不访问网络,退出码为零也不表示所有检查通过,必须读取各项状态。

执行边界

Git 写操作串行执行;暂存前、提交前、推送前核对当前提交与任务改动。状态发生变化时重新确认归属和待推送提交,不能夹带未知内容,也不为跳过冲突而强推或绕过 hook。

推送前同步远端状态,核对仓库、分支及必要的账号信息。已有持续授权按项目规则执行;仅准备发布不授权实际上线。对外消息必须有明确授权,发送前复核目标和内容,发送后读回。

网络失败后先检查实际终态。发布、创建 tag 或 release 等不可重复动作结果未知时,不盲目重发;取得新证据或报告具体阻塞。发布阶段的新问题要修复,或说明影响并取得对应决定,不能沿用旧的“可发布”结论。

交付

先说明已完成、未完成和阻塞项。按适用范围列出提交、远端、CI、产物、部署环境和用户可观察验收证据。不能把“源码已修复”“已构建”“已上传”和“用户已可用”压成同一个完成状态。

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.