Epic Planner logo

Epic Planner

Community
Dimon94
epic-planner

为模糊的史诗需求启动或续接战略寻路。先建立目标、迷雾与 Issue 决策票,通过内部调研、外部研究、原型和拷问厘清战略,之后形成多地图 epic-plan。

Overview

PublisherDimon94
Repositoryskills
Skill nameepic-planner
Stars
107
Forks
21
Bundled files
6
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.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Dimon94 on GitHub. Read the source before you install it.

Installation

Install the Epic Planner 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/Dimon94/skills/tree/main/skills/epic-planner
  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/Dimon94/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/epic-planner .claude/skills/epic-planner
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Epic Planner 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 Epic Planner 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 Epic Planner 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.

Epic Planner

当前任务是史诗战略寻路:把不清楚的目标、现状和取舍变成可推进的决策票。启动时地图数量、边界和并发关系都是 Unknown;代码问题的分类不能直接变成候选地图,即使冠以「初步」「暂定」或「不是最终计划」。

本 Skill 拥有史诗层的目标、深模块、共享 Interface 和拆分决定。它们经寻路解决后,才形成多地图 epic-plan,支持多个 Wayfinder 会话继续各自内部的寻路,并按 Seam 集成。

史诗索引 Issue 是跨会话入口,默认标签 epic:plan。索引从寻路开始就存在,阶段先是「寻路中」;标签不代表最终规划已完成。决策与证据由各自的寻路票拥有,索引只存摘要和指针。规划、研究、图与交接材料都存远程,产品代码保持只读。

按输入选择模式

  • 模糊需求或史诗方向,包括「先分析」「诊断架构」: 启动寻路,建立索引和当前能提出的问题。用户怀疑需要史诗重构,是待验证假设。明确只要普通诊断、不做寻路时,改用 investigate。
  • 史诗索引 URL 或编号,可附票名: 续接寻路,推进一个当前可处理的决定。
  • 已有最终计划,或下游地图带回合同冲突: 先读回索引;把失效的共享决定重新纳入寻路,只复核受影响部分。

读取目标项目的术语、约定和 tracker 配置。位置、标签、归属、发布与读回遵循 Issue 合同。依赖 Skill 按用户提供的路径或当前运行时目录定位;缺失时报告路径和受阻票,保持未解决。

史诗迷雾与循环

史诗索引是一张逐步揭开的战略迷雾地图。范围由终点固定,视野随证据与沟通扩展;开始时保持不完整,不能把未知提前切成看似确定的地图。

概念在史诗层的含义
Destination清楚的史诗战略与多地图 epic-plan:目标、范围、Module Ownership、共享 Interface、并发关系和集成验收已对齐
Fog of war范围内已察觉、但暂时还不能精确提问的未知。记在索引「待明确」,例如“授权模型也许会改变地图拆分”
决策票已能精确表述的问题,例如“组织角色是否包含项目读取权”。答案未知或被前置票阻塞,都不妨碍建票
Frontieropen、unblocked、unclaimed 的寻路票,是当前能推进的已知边缘;不是全部未完成工作
已决事项已有有效 resolution 的决定,只保留摘要和来源指针;新证据可使决定重新打开
范围外明确不属于史诗终点的工作,单独记录理由。只有用户改变范围时才重新纳入

迷雾循环:恢复索引 → 选 frontier 票 → 取证或真实沟通 → 写 resolution → 重画已知边缘 → 继续。 每次 resolution 后,复核目标、架构、地图依赖与接合处:哪些迷雾现在能问清,哪些新迷雾出现,哪些旧决定已失效?

能问清的迷雾毕业为一张或多张票并连依赖,从「待明确」移除;仍问不清的继续保留。毕业记录归新票,「待明确」不留已毕业票的历史清单。一块迷雾也可能因新证据而消失,此时记录证据与原因。不能把迷雾草率预切成固定票数,也不能静默搬到「范围外」或下游地图以宣称已清除。

循环直到全部范围内的史诗战略迷雾清除、相关决策票解决且用户确认对齐,不设固定轮数。单轮结束、当前 frontier 为空、票都已分派,都不是这个终点。下游只接收已证明不影响史诗战略或跨地图合同的内部决定,并明确其归属。

启动寻路

  1. 澄清终点。 读取 grill-with-docs/SKILL.md,按其路由用 grilling 与 domain-modeling 澄清业务结果、范围和成功标准;产物遵循票型与结论的远程覆盖。先问会改变方向的真实取舍,可查事实交给调研。痛点回答只确认痛点,不代表用户批准重构范围、共享语义或拆分。尚无答案的目标保持 proposed,并留下拷问票。
  2. 探到 frontier。 浅读目标代码路径、当前 Interface、状态 owner、测试和已有决定,找出会改变史诗拆分的问题。先覆盖整个决策空间,再深入单点。需要图时读取 show-me,用可嵌入 Issue 的调用树或 Mermaid 显示已知关系。此步完成于问题可表述,不要求一次完成架构分析。
  3. 建立索引和票。 按 票型与结论 为已能精确提问的问题建子票;即使被阻塞,只要问题清楚也建票。暂时问不清的内容留在「待明确」,范围外单列。先取得真实票 ID,再按项目 tracker 约定连阻塞边;索引阶段保持「寻路中」。没有发布授权或 tracker 不可用时,仍在对话交付同样的索引与决策票草稿,注明未发布;不退化为架构建议报告。
  4. 启动独立取证并收口。 可并发的内部调研和外部研究票,在授权及宿主能力允许时交后台 agent;先认领,再交问题和证据指针。缺少后台能力时保留在 frontier。HITL 票留给真实用户参与,不能在本轮代答后宣布完成。

完成条件: 有史诗索引、带类型/解决条件/依赖的决策票、剩余迷雾,以及下一项取证或真实待答问题;已发布则读回,否则交付可发布草稿。启动到此结束,不输出候选地图、拆分数量或并发分工。初查发现与推荐只作票的输入,研究数量和测试通过都不证明战略已清楚。

续接寻路

  1. 恢复现场。 先读索引,再查询属于该史诗的寻路票及阻塞状态。frontier 是 open、unblocked、unclaimed 的寻路票;只按需展开相关票正文与 resolution。核对代码基线和已决合同是否变化。
  2. 选票并认领。 用户指定票时先核对归属、阻塞与 claim;否则取 frontier 中按项目顺序的第一张。按 tracker 的 claim 机制认领并读回后,才读取票型 Skill、运行该票的调研、测试或原型;不能先取证后补认领。被阻塞或他人认领的票不抢做;当前没有 frontier 时报告具体阻塞或待回复,不把它当作规划完成。
  3. 按票型处理。 读取票的类型标签,再按 票型与结论 调用对应 Skill。事实由 agent 取证,取舍由用户裁决。prototype 与拷问票没有真实用户反馈就保持 open,记录等待点;研究结论也不自动授权产品决定。
  4. 结案并重画迷雾。 达到该票解决条件后,写 resolution comment,读回成功再 close;索引追加名称链接与一句结论。按「史诗迷雾与循环」复核并更新迷雾、毕业票与阻塞边。决定推翻旧结论时,重开或新增受影响票并重连依赖。越界票记录原因后关闭,只进入「范围外」。
  5. 检查是否可形成计划。 按下节检查全部史诗层待决项。未通过则保持「寻路中」,留下可续接的 frontier 或等待点;通过才读取 形成 epic-plan 并更新同一个索引。

每个会话最多解决一张非调研票;独立的 investigate、research 票可后台并发处理。跨票通信使用 Issue、resolution 和证据链接。索引由史诗 owner 汇总,worker 只写自己的票和交回结果指针。

完成条件: 本轮解决或等待的票有远程记录,claim 状态可恢复,索引反映当前决定与迷雾;下一会话能从索引继续。

epic-plan 的形成门槛

以下条件全部成立,才将索引阶段改为「规划就绪」:

  • 史诗层所有范围内的寻路票都有有效 resolution 并已关闭;「待明确」为空。frontier 为空而仍有 blocked、claimed 或待用户回复的票不满足条件。
  • 目标、关键术语、Module Ownership、跨地图 Interface、共享状态和迁移取舍都有证据;用户的真实确认覆盖当前拆分与共享合同。已有确认可引用,尚未对齐则继续拷问票。
  • 已解决会改变拆分或共享合同的未知。属于各候选地图内部、且不影响其他地图的决定明确移交下游,未决内容及归属可见。
  • 拆分决定有已解决的拷问票,能追溯各边界、共享合同和并发判断依据。不能把尚待裁决的战略问题转交下游以通过门槛。

通过门槛后才读取形成 epic-plan,整理多张候选地图;准备交接时读取交接与续接。规划就绪、下游地图路线清楚、实现完成、集成验证分别记录;不因规划完成自动关闭史诗索引。

维护验证

修改寻路生命周期、票型、完成门槛或远程产物规则时,运行 前向验证案例。格式校验只证明可加载,不能证明寻路不会提前结束。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Epic Planner AI skill do?

为模糊的史诗需求启动或续接战略寻路。先建立目标、迷雾与 Issue 决策票,通过内部调研、外部研究、原型和拷问厘清战略,之后形成多地图 epic-plan。

Why use Epic Planner on TypingMind?

Because you install it once and use it with any model. Epic Planner 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 Epic Planner in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Dimon94/skills/tree/main/skills/epic-planner. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Epic Planner?

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 Epic Planner?

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

Is the Epic Planner AI skill free?

It is published on GitHub by Dimon94. 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 👇