Knowledge Project logo

Knowledge Project

Community
briqt
knowledge-project

让知识工作项目对 Agent 自描述、跨 session 可接续,并治理项目里的规则与工作纪律。 两类场景使用:(一)项目组织——新建或初始化项目、整理或健康检查项目结构、 设计目录与导航、写 frontmatter/index/log/决策记录、把探索期的临时文件沉淀下来、 恢复一个还没有规则文件的项目的上下文;(二)工作方法论——同类问题反复出现要固化成规则、 规则太多或互相冲突要精简、新增或删除一条项目规则、给项目立检查脚本或门禁并判断它是否有效、 沉淀经验教训、回顾或改进方法论本身。触发词:新建项目、初始化文档结构、帮我整理这个项目、 项目怎么组织、健康检查、又踩坑了、固化成规则、规则太多、精简规则、门禁、检查脚本、 沉淀、蒸馏、经验教训、决策记录、回顾方法论、setup project、project health check。

Overview

Publisherbriqt
Repositoryknowledge-project
Skill nameknowledge-project
Stars
50
Forks
5
Bundled files
5
LicenseMIT
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.

  • 5 bundled files

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

  • Open source

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

Installation

Install the Knowledge Project 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/briqt/knowledge-project/tree/master/skills
  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/briqt/knowledge-project.git /tmp/knowledge-project
mkdir -p .claude/skills
cp -r /tmp/knowledge-project/skills .claude/skills/knowledge-project
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Knowledge Project 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 Knowledge Project 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 Knowledge Project 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.

Knowledge Project

将知识工作组织为自描述项目——任何 Agent 打开即可理解和继续,无需外部记忆系统;并让项目里的规则随工作演化,而不是膨胀到没人遵守。

本文件是常驻层:每次触发都成立的原则、纪律与路由。具体做法按 §路由 读 references/ 下的对应文件,只读本次意图需要的那几个。

Philosophy

核心理念:项目本身携带完整上下文,项目目录是唯一的持久化载体——换 Agent、换平台、清空记忆、本 skill 未安装,打开项目目录即可继续。

设计原则:

  1. 纯文件 + 约定:markdown + YAML frontmatter,零工具依赖,git 友好
  2. 自包含:每个文档独立可理解,不以读过别的文档为前提
  3. 最小约束:只规定互操作必需的结构,其余由项目自行演化
  4. 写的人花 2 分钟,读的人省 20 分钟:信息密度优先,格式服务检索
  5. 单一权威源:规则只在一处定义,其他文件引用不复述

格式基础:Open Knowledge Format (OKF) v0.2 —— 知识用 markdown + YAML frontmatter 目录表示,人和 Agent 用同一份文件。字段约定与有意偏离见 format.md。

硬约束

  • 项目文件即记忆:项目的所有上下文落在项目文件中(AGENTS.md、log.md、内容文件),不写入 Agent 自身的 memory。
  • 产出物不得反向依赖、不得引用本 skill:由本方法论创建或维护的项目,其自足性不得以"本 skill 在场"为前提;项目文件中不出现本 skill 的名字,也不留指向任何外部方法论的指针——无例外。判据与理由见 seed.md §关键约束。
  • 进展随工作落地:进展、决策、文件元数据随工作产生同步写入。最终检验:结束工作时,log.md 最后一条的"下一步"足以让任意 Agent 从零接手。
  • 按影响决定改进权限:项目内小范围、可回退且不改变目标或质量要求的规则调整,可自主执行并记 log;其余改进走 proposal(诊断 → 提案 → 用户确认 → 执行 → 记 log)。本 skill 方法论的修改仍走 Meta-Iteration。

Epistemics

知识工作的认知纪律。贯穿所有工作流,优先级高于具体流程步骤。第 1、3 条以精简版内联进种子、第 4 条对应种子的"感知偏差与对齐"——本 skill 未被触发时,项目照样遵守。

  1. 基于证据:判断、选择、结论须追溯到可观测的依据。没有证据时承认不确定,而非填充看似合理的假设。委派或其他 Agent 的产出同样是候选输入而非既定事实——引用它做不可逆动作(删除、归档、改权威源)前先复核源头。已核验且未改动的信息,可在实际核验范围内初步信任;需要核查时,范围限于变动内容及当前任务直接依赖的部分。
  2. 在行动点决策:不提前锁定依赖未知信息的决定。确定方向,开始行动,让工作本身产生下一个决策点。
  3. 完整执行:不跳步骤,不用"以此类推"代替实际工作。产出是做出来的,不是规划出来的。
  4. 对齐优先于执行:目标有歧义、存在矛盾、或涉及方向性取舍时,先澄清再行动。推断可以替代追问,但推断必须显式呈现供纠正——不用默认值静默填充。

路由

按意图只读需要的文件,顺序即阅读顺序:

意图读要点
创建新项目workflows.md §Initialize → structure.md → seed.md → format.md选规模、写规则文件并内联种子、建 log 与首个内容文件
恢复/继续项目本文件 §Resume已有种子的项目按它自己的 AGENTS.md 执行即可
整理、优化、健康检查workflows.md §Health Check按诊断结果转 Milestone Review 或 Distill(同文件)
日常维护:写 log、frontmatter、决策记录,关闭事项workflows.md §Daily Operations → format.md
沉淀探索期产物workflows.md §Distill
规划文件组织、判断一条信息该写在哪structure.md
新增/删除/固化规则、规则膨胀、立门禁或评估门禁governance.md
回顾或改进方法论本身governance.md §Meta-Iteration须用户显式触发

除 Resume 外,触发时顺带对照 Health Check 清单扫描项目现状,发现可改进项时向用户提出。

Resume

新 session 阅读协议:

  1. AGENTS.md → 理解项目结构和约定
  2. 任务路由表(如有)→ 按本次任务加载对应的任务层规则
  3. 定位当前事项并读取其状态,任务清单如有则用
  4. 按需查该事项的相关日志 → 补充进展与阻塞;无独立事项文件时从日志恢复
  5. 进入具体工作

若 log 描述与当前文件实际状态冲突,以文件为准,更新过时描述。

日常感知

在项目中工作时,持续感知结构摩擦并推动改进:

  • 发现规则与实际操作不一致 → 提出 AGENTS.md 修改建议
  • 发现导航不够高效 → 提出结构调整
  • 发现重复模式 → 提出新规则或模板(新增前先过 governance.md §规则的准入与退出)

何时启动正式的结构性迭代,见 governance.md §Self-Iteration。

Boundaries

本 skill 不是:

  • 记忆系统(不做向量检索、不跨项目同步状态)
  • 重编排 / 多 agent 调度器——但轻量结构化任务资产(复杂事项拆 需求/设计/实施清单/决策记录)是标准项目的一等组成,见 structure.md §Customization
  • git 的替代品(版本管理就是 git)
  • 强制模板(最小约束,项目自行演化)

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 Knowledge Project AI skill do?

让知识工作项目对 Agent 自描述、跨 session 可接续,并治理项目里的规则与工作纪律。 两类场景使用:(一)项目组织——新建或初始化项目、整理或健康检查项目结构、 设计目录与导航、写 frontmatter/index/log/决策记录、把探索期的临时文件沉淀下来、 恢复一个还没有规则文件的项目的上下文;(二)工作方法论——同类问题反复出现要固化成规则、 规则太多或互相冲突要精简、新增或删除一条项目规则、给项目立检查脚本或门禁并判断它是否有效、 沉淀经验教训、回顾或改进方法论本身。触发词:新建项目、初始化文档结构、帮我整理这个项目、 项目怎么组织、健康检查、又踩坑了、固化成规则、规则太多、精简规则、门禁、检查脚本、 沉淀、蒸馏、经验教训、决策记录、回顾方法论、setup project、project health check。

Why use Knowledge Project on TypingMind?

Because you install it once and use it with any model. Knowledge Project 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 Knowledge Project in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/briqt/knowledge-project/tree/master/skills. 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 Knowledge Project?

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 Knowledge Project?

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

Is the Knowledge Project AI skill free?

Yes. It is published on GitHub by briqt under the MIT license. 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 👇