Skip to content

DBinK/dbk-handoff / skills/dbk-pickup

dbk-pickup

Verified

读取 .agent/handoff/ 下的交接快照,校验协议版本与 Git 工作区状态,恢复任务上下文并向用户确认后继续开发。本技能是读取交接报告的唯一入口。当用户粘贴了交接引导 Prompt、要求接手上一个 Agent 或上一轮会话未完成的任务、让 Agent 读取 .agent/handoff/ 下的报告或 latest.md 继续干活,或提到“接手”“接着做”“pickup”“恢复上下文”时使用。不适用于在当前会话结束时总结进度并导出交接报告(应使用 dbk-handoff)。

FileKindSize
SKILL.mdskill md5.0 KB
evals/trigger-queries.jsonconfig2.0 KB

evals/trigger-queries.json

View on GitHub
[
  {
    "query": "我在使用另一个 AI 协助开发,现需要你接手该任务。请调用 dbk-pickup skill,交接报告路径:.agent/handoff/261018-1230-auth-refactor.md",
    "should_trigger": true
  },
  {
    "query": "跑一下 dbk-pickup,接着上一个 agent 的进度往下做",
    "should_trigger": true
  },
  {
    "query": "读一下 .agent/handoff/latest.md,跟我确认一下当前进度和下一步,然后继续改",
    "should_trigger": true
  },
  {
    "query": "我刚从 Cursor 切过来,工作区里有之前留下的 handoff 报告,帮我接手继续开发",
    "should_trigger": true
  },
  {
    "query": "用 dbk-pickup 恢复上下文,看看上个会话卡在哪了",
    "should_trigger": true
  },
  {
    "query": "接手 .agent/handoff/261018-1420-fix-token-expiry.md 里的任务,先对齐一下状态",
    "should_trigger": true
  },
  {
    "query": "pickup 一下最新的交接快照,按里面的待办继续推进",
    "should_trigger": true
  },
  {
    "query": "读取 .agent/handoff 下的最新交接文档,确认理解后接着做",
    "should_trigger": true
  },
  {
    "query": "当前上下文太长了,跑一下 dbk-handoff 生成交接报告,我要换个窗口",
    "should_trigger": false
  },
  {
    "query": "总结一下现在的进度和踩坑点,导出 handoff 快照给下一个 agent",
    "should_trigger": false
  },
  {
    "query": "先停在这,帮我写一份交接文档放到 .agent/handoff 里",
    "should_trigger": false
  },
  {
    "query": "读一下 README.md 和 ARCHITECTURE.md,看看这个项目是怎么设计的",
    "should_trigger": false
  },
  {
    "query": "帮我 git pull 拉一下远端最新代码,看看有没有冲突",
    "should_trigger": false
  },
  {
    "query": "恢复一下刚才 git stash 暂存的改动",
    "should_trigger": false
  },
  {
    "query": "跑一下 pytest 看看现在的测试能不能过",
    "should_trigger": false
  },
  {
    "query": "看下 git log 最近三次提交都改了什么",
    "should_trigger": false
  }
]
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall