Work Context logo

Work Context

Community
StringKe
work-context

长任务的执行细则和状态文件模板:开工前复述、需求清单、拆包并行、等待时做什么、验证方式、收尾核对、跨会话的 Work Context 状态文件和交接。任务预计超过半小时、跨多个模块或仓库、用户下达 /goal、ultracode 或后台无人值守任务、上下文压缩后恢复工作,或用户要求总结需求、交接时使用。

Overview

PublisherStringKe
Repositorydotfiles
Skill namework-context
Stars
93
Forks
9
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by StringKe on GitHub. Read the source before you install it.

Installation

Install the Work Context AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/StringKe/dotfiles/tree/main/ai/skills/work-context
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/StringKe/dotfiles.git /tmp/dotfiles
mkdir -p .claude/skills
cp -r /tmp/dotfiles/ai/skills/work-context .claude/skills/work-context
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Work Context in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Work Context on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Work Context is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

长任务执行细则

全局规则的「工作方式」一节规定了原则:先复述理解、范围内自己决定、做完整、验证自己做、不干等。本 skill 补充长任务里的具体做法、状态文件模板和真实例子。

开工

  1. 用自己的话复述:要交付什么、范围边界、完成条件。需求是多轮消息叠加出来的,或者刚被用户纠正过,都先复述再动手。
  2. 交互会话里,复述之后只问会改变做法的分歧点,一次问完,每个问题带推荐项。细节自己定。
  3. 无人值守的任务(/goal、ultracode、后台任务)不提问。把理解写进状态文件的 Why 和 Decision,直接做。碰到影响生产、不可逆或动共享环境的操作,跳过并写进 Next,其余部分继续做完。
  4. 读仓库规则(CLAUDE.md、AGENTS.md、memory)和相关代码。先找框架和现有代码里的做法,再考虑自己写。
  5. 把用户的全部要求编号写进 Asks。

例:用户说「先理解我说的需求是什么 为什么现在错了 等我完整的确认」。这时复述需求、说明现状错在哪里、给出方案,然后等确认,不改代码。

反例:用户已经说了「允许改数据接口,理解我的整个设计和思路」,AI 又列了 4 个问题,说「这几项确认后再动代码」。这些问题应该按推荐项自己定下来,直接做。

需求清单

  • 用户分几条消息追加要求、连续报问题、中途插入新任务时,每一条都进 Asks,标待做、进行中、完成或阻塞。
  • 插进来的提问和指令立即处理,回报一句,再回主线。处理新消息时,没做完的要求留在 Asks 里继续做。
  • 用户纠正过的做法、定下的约束和给过的授权记进 Decision,之后一直照做,不再问。
  • 用户问进度或「做完了吗」时,从 Asks 逐条给状态。

执行

  • 大改动按互斥的文件或目录拆包,派子代理并行。跨包的接口由主线先定死再分发。同时运行的子代理不超过 12 个。改动量小的任务主线自己做,不派子代理。
  • 架构、接口和语义的判断留在主线。机械性的改动、配置和测试修补交给子代理,用运行时里更便宜的档位。
  • 做的过程中发现的问题,包括不是本次引入的,在范围内直接修,并按类别扫全部同类位置。
  • 每完成一项独立的改动就 commit,只暂存本会话的文件。
  • 用项目现有的命令、部署工具、框架能力和 MCP。不写一次性的包装脚本或 Python 工具。

等待

  • 长命令放后台。等待时做不依赖它的事:改下一处代码、写文档、看日志。
  • 定期检查后台任务、子代理、部署和测试进程的真实状态。卡住就找原因处理,例如测试锁被别的进程占着;某一步验证太慢,就先优化验证本身。
  • 子代理长时间没有进展时介入,必要时收回来自己做。
  • 不可逆的操作(销毁资源、删除数据)串行执行,每一步确认结果再继续。

验证

text
PASS    已运行且通过
FAIL    已运行且失败
SKIP    明确不适用
UNKNOWN 当前环境无法验证,写明缺什么条件
  • 全部改完后统一验证。失败就修,修到通过;连续两轮没有新进展时停下,写明卡在哪里。
  • 按需求逐条核对,覆盖所有类型和配置组合。
  • UI 改动在真实浏览器里走流程时,看渲染、重叠、折行和控制台错误。
  • 能查文档或实测确认的先查,查不到才写 UNKNOWN。
  • 结论已经明确时停止测试,不重复试。

例:kxed 项目里,全部改完后先跑 fmt、clippy 和改动 crate 的测试,签名推送,再在最终 HEAD 上一次跑完项目要求的完整 gate。用户回复「后续都应该这样处理的」。

收尾

结束回合前依次检查:

  1. Asks 逐条核对,没做完的继续做。
  2. 发现的遗留问题、失败测试、过时文档都已处理,没有留 follow-up。
  3. 每项完成都有本次运行的验证证据。
  4. 提交只包含本会话的改动。rebase 到最新的目标分支,fast-forward push。部署只在用户要求过时做。
  5. 本会话开了 worktree 时运行 /worktree-done。
  6. 后台任务、测试进程和临时资源已停止或清理。

反例:AI 说「主检出的 git pull --ff-only 我这边做不了,还需要你执行」。用户回复:「我说了交给你 还有什么做不了,做完之后 git worktree 要关闭,本地 main 要是最新的啊」。

Work Context 状态文件

任务跨会话、可能被上下文压缩打断,或者需要交接时,维护一份状态快照。仓库里放 .local/work/STATE.md,并确认它被 git ignore。没有仓库时放 $CLAUDE_JOB_DIR/tmp 或 scratchpad。

markdown
# Work Context: <任务名>

## Why
## Asks
## Current
## Decision
## Proof
## Next
  • Why:目标、范围、完成条件、约束。
  • Asks:用户的全部要求和状态,用表格,包括中途插入的。
  • Current:当前事实:改了哪些文件、分支和提交、环境状态、后台任务。
  • Decision:已定的做法和依据,包括用户的纠正和授权。
  • Proof:已运行的验证和结果。
  • Next:下一步,或阻塞条件。

新证据推翻旧判断时直接改对应字段,不累积历史。单次简单任务不建文件。稳定的结论迁到代码、文档或项目规则里。上下文压缩后,先读状态文件再继续。

交接和需求总结

用户要「总结需求」「总结上下文」「交接」时,从 Asks 和 Decision 写消化后的理解:要做什么、为什么、已经定了什么、还剩什么。不复述用户原话。

Frequently asked questions

What does the Work Context AI skill do?

长任务的执行细则和状态文件模板:开工前复述、需求清单、拆包并行、等待时做什么、验证方式、收尾核对、跨会话的 Work Context 状态文件和交接。任务预计超过半小时、跨多个模块或仓库、用户下达 /goal、ultracode 或后台无人值守任务、上下文压缩后恢复工作,或用户要求总结需求、交接时使用。

Why use Work Context on TypingMind?

Because you install it once and use it with any model. Work Context is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Work Context in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/StringKe/dotfiles/tree/main/ai/skills/work-context. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Work Context?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Work Context?

As many as you like. As long as a model supports skills, you can use Work Context with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Work Context AI skill free?

It is published on GitHub by StringKe. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇