Kb logo

Kb

Organization
evidentloop
kb

Manage long-lived `.sopify/` knowledge, including bootstrap, progressive materialization, reads, retention, and knowledge_sync policy.

Overview

Publisherevidentloop
Repositorysopify
Skill namekb
Stars
368
Forks
30
Bundled files
Instructions only
LicenseApache-2.0
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 evidentloop on GitHub. Read the source before you install it.

Installation

Install the Kb 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/evidentloop/sopify/tree/main/skills/en/skills/sopify/kb
  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/evidentloop/sopify.git /tmp/sopify
mkdir -p .claude/skills
cp -r /tmp/sopify/skills/en/skills/sopify/kb .claude/skills/kb
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kb 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 Kb 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 Kb 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 Base Management

KB owns long-lived knowledge. It does not make Analyze, Design, or Develop decisions, and it does not manage the active plan, handoff, receipts, or finalize directly. Document structures come from Templates; protocol state is managed through sopify_writer.

Directory responsibilities

text
.sopify/
├── project.md              # reusable technical conventions
├── user/                   # long-term preferences and raw feedback
├── blueprint/              # long-term goals, design boundaries, open work, and index
├── plan/                   # current plan semantic files
├── history/                # archived plans and index
└── state/                  # local protocol state

blueprint/README.md keeps only status, maintenance guidance, current goal, current focus, and reading links. Put detailed content in the relevant blueprint file.

Bootstrap and progressive materialization

kb_init: full creates project.md, user/preferences.md, user/feedback.jsonl, and the four blueprint files on first use. It does not pre-create plan content, history, or empty directories.

kb_init: progressive is the default:

  • First real project use: create project.md, user/preferences.md, and blueprint/README.md.
  • First plan lifecycle: add blueprint/background.md, blueprint/design.md, blueprint/tasks.md, and the current plan directory.
  • First explicit ~go finalize: let the protocol flow create history/index.md and the archive directory.
  • First explicit long-term feedback: create user/feedback.jsonl when needed.

Knowledge context reads

The host completes the governing Protocol entry for a managed plan, handoff, and receipts before invoking KB. This section defines only KB's long-lived context order:

  1. project.md
  2. user/preferences.md
  3. blueprint/README.md
  4. Relevant parts of blueprint/background.md, design.md, and tasks.md

Consult and quick fix do not fail when deep blueprint files are absent. Read history/ only for trace-back or finalize.

Retention and updates

Keep information only when it remains useful across tasks:

  • project.md: reusable technical conventions.
  • background.md: long-term goals, scope, and non-goals.
  • design.md: module, host, directory, and consumption contracts.
  • tasks.md: unfinished long-term work and explicit deferrals with a revisit condition.
  • preferences.md: explicit long-term user preferences.

Do not store one-off implementation details, current-plan task breakdowns, temporary tradeoffs, completed tasks, or copies of history content. When code and documentation conflict, verify the code and then correct the documentation. Current user instructions override historical preferences.

knowledge_sync

yaml
knowledge_sync:
  project: skip|review|required
  background: skip|review|required
  design: skip|review|required
  tasks: skip|review|required
  • skip: do not inspect that file for this plan.
  • review: decide whether it needs an update before finalize.
  • required: update it before the delivery candidate; block finalize while incomplete.

KB applies the plan's sync policy without changing the plan lifecycle. Update the narrowest long-lived location and avoid duplicating the same content across files.

Output

After bootstrap or sync, state the actual result, list Changes, and end with Next:. Use Changes: 0 files when nothing changed.

Frequently asked questions

What does the Kb AI skill do?

Manage long-lived `.sopify/` knowledge, including bootstrap, progressive materialization, reads, retention, and knowledge_sync policy.

Why use Kb on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/evidentloop/sopify/tree/main/skills/en/skills/sopify/kb. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Kb?

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 Kb?

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

Is the Kb AI skill free?

Yes. It is published on GitHub by evidentloop under the Apache-2.0 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 👇