agentleFS
mdiri-aimdiri-ai/SoduWork/skills/task/SKILL.md

task

Skill930 starsChanged 6 days agoMITView on GitHub

在 SoduWork 里管任务:把聊清楚的事建成任务、顺手派给 AI 执行机或起流程、查自己名下的任务、改状态和验收要点。当人说「帮我建个任务」「这件事交给 AI 去做」「我手上还有什么活」「把这个标成做完了」,或者你们已经把一件事聊明白、该落成一条任务时使用。

29 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use inbox, grill-me and 5 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.
  • kv0906Skill

    inbox

    Quick capture mode (with content) or batch processing mode (no content). GTD-style routing of inbox items to proper folders. Use "/inbox thought to capture" or "/inbox" to process.

    Also in 3 projects that use this

  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 5 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 4 projects that use this

  • OpenAISkill

    audit

    Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.

    Also in 3 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 3 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 3 projects that use this

The file

Files
SKILL.md

任务(task)

SoduWork 的任务能力是一组 MCP 工具,通过 mcp-tools 那座桥调。server 名叫 soduwork。

node <mcp-tools 技能目录>/scripts/mcp.mjs list soduwork            # 有哪些工具、入参是什么
node <mcp-tools 技能目录>/scripts/mcp.mjs call soduwork <工具> '<JSON>'

六个工具

工具干什么
task_options建任务前先调这个:拿到可选的 AI 执行机、流程、工程、优先级
task_propose在对话里建任务,只用它:把想好的字段提议出去,对方屏幕上长出一张可以改的卡
task_create真建(给没有界面的场合用)。对话里不要直接调
task_list我名下的任务,可按状态筛、按关键词搜
task_get一条任务的详情:说明、状态、进度、AI 执行情况
task_update改标题/说明/状态/优先级/期望完成日

建任务的规矩(不是建议,是硬要求)

① 先聊清楚,再建。 一句话通常不够建出一条像样的任务。缺什么就问什么,一次问一两个,别甩一张表格:

  • 要办的是什么——一句话说不清就让人展开;
  • 验收要点——做到哪几条才算完?这是最容易被略过、也最要命的一项;
  • 谁来办——自己办(assigneeKind:"me",只建不派),还是交给 AI("ai");
  • 在哪个工程上干——涉及改代码的必须问,从 task_options 的 repos 里选;
  • 什么时候要。

② 别自己猜 id 和名字。 agentId / flow / repoId 一律从 task_options 回的清单里挑。猜一个填进去,要么建错,要么直接失败。

③ 用 task_propose 出卡,别用文字复述。 以前的做法是把整张卡念一遍、问一句"这么建行吗"——那样人改不了字段,只能回你 "把第三条验收要点换成…",来回好几轮。现在直接 task_propose:对方屏幕上会长出 一张真正的卡,标题、说明、验收要点、交给谁、走哪个流程、什么时候要,他自己就能改。

所以:

  • 提议前别写大段确认文字——卡片本身就是确认,你只需要一句"这么建,行吗"。
  • 提议后停下来等。别重复提议,也别自己去调 task_create(人在卡上点了「创建并按流程开始」,界面会建)。
  • 人要是在对话里说"把优先级改成高",你可以重新 propose 一次(覆盖那张卡),别让他去卡上找。

④ 手上有材料就先看。 如果人提到的是这台机器上的某个工程/文件,先去读(ls/read/grep 都行),再填 repoId 和说明。看过再填的任务,和猜出来的任务,质量差得很远。

怎么选流程

task_options 的 flows 里每条都带 desc,照着挑:

  • 不用改代码的零散活(写材料、做 PPT、整理文档、查资料)→ 一般是 ai-errand;
  • 要改代码并交付→ 看工程用的是哪套(software-delivery / gerrit-autopilot / project-validation-release);
  • 只是先出个原型看看→ product-prototype;
  • 拿不准就不填(flow 留空):不走流程,直接把活派给选中的 AI。

例子

# 1. 先看有哪些选项
node .../mcp.mjs call soduwork task_options '{}'

# 2. 提议出一张卡(不写库、不派活,人能在卡上改)
node .../mcp.mjs call soduwork task_propose '{
  "title": "茶馆竞品调研:定价与功能",
  "note": "对茶馆的同类竞品做调研,重点对比定价策略和功能差异。结果要能直接发给领导看。",
  "checklist": ["列出 3-5 个主要竞品", "逐个对比定价模式和核心功能", "标出茶馆的优势与短板", "产出一份调研报告"],
  "priority": "normal",
  "due": "2026-08-13",
  "assigneeKind": "ai",
  "agentId": "local:claude",
  "flow": "ai-errand"
}'

# 3. 回头看进展
node .../mcp.mjs call soduwork task_list '{"status":"doing"}'
node .../mcp.mjs call soduwork task_get '{"id":"<任务id>"}'

回话的规矩

  • 提议完了,只需要一句「这么建,行吗」——别把卡片内容再用文字复述一遍, 他屏幕上已经有了,复述一遍只是刷屏。
  • 建完了(人点了卡上的按钮),说清楚建了什么、交给谁、什么时候要,并把任务 id 带上。
  • 返回里 warn 不为空=任务建好了但没交出去(比如那台执行机不在了)。这时候必须明说, 别让人以为已经在跑了——任务是真的建了,可以到任务详情里再派一次。
  • dispatched / flowStarted 是 false 且没有 warn,说明这条是"我自己办"的任务,没派给 AI。
  • 只说"建好了"不算交付。

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.