# kb

Central hub skill for Open Knowledge Format bundles. Routes coding agent tasks to specialized kb tools and holds the shared memory specification.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · ★ 41
- Author: stjbrown
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/stjbrown/agent-knowledge/tree/HEAD/skills/kb/SKILL.md
- Updated: 2026-08-01
- HTML: https://affpapa.org/en/nevibecode/skills/kb

## What it does

The `kb` skill serves as the router and reference library for the entire `kb-*` ecosystem. It never edits files directly. Instead, it inspects incoming requests and delegates work: starting a wiki triggers `kb-init`, source processing points to `kb-ingest`, repo documentation goes to `kb-document`, and graph health checks go to `kb-lint`. When a repository contains a `knowledge/` directory, the agent consults it before generating answers from scratch.

The skill embeds the OKF v0.2 specification, maintenance rules, glossaries, and starting templates like `concept.md` and `log.md`. One strict rule governs the system: every non-reserved `.md` file must feature valid YAML frontmatter with a non-empty `type`. All other schema requirements remain soft guidance, so missing metadata or broken links will not break ingestion.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add stjbrown/agent-knowledge --skill kb -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/kb/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/kb/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add stjbrown/agent-knowledge --skill kb -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/kb/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add stjbrown/agent-knowledge --skill kb -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/kb/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install stjbrown/agent-knowledge kb
```

2. **Manually: put the files in place**
- File: `.github/skills/kb/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add stjbrown/agent-knowledge --skill kb -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/stjbrown/agent-knowledge --path skills/kb
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/kb/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add stjbrown/agent-knowledge --skill kb -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/stjbrown/agent-knowledge/tree/HEAD/skills/kb/SKILL.md

## When to use it
- structure agent memory using the OKF knowledge bundle standard
- route wiki workflows to the right kb companion skill
- enforce basic frontmatter conformance across repository markdown notes
- provide templates and definitions for project documentation

## Example prompts
- Check our `knowledge/` bundle before proposing architecture changes
- Which kb skill should I use to import a research paper into the wiki?
- Set up project reference docs following the OKF spec

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 4276f403a4f8e840.

BEGIN THIRD-PARTY FILE 4276f403a4f8e840
```text
---
name: kb
description: >-
  Portable OKF knowledge bundle for coding-agent memory and LLM wikis. Use when the user wants to
  start a wiki, ingest a source, document a repository, query project knowledge with citations,
  lint for drift, or visualize connections; whenever a repo has a knowledge/ bundle that should
  inform the task; and when another kb-* skill needs the shared spec, glossary, templates, or trust
  model.
version: 0.3.2
tags: [knowledge, okf, bundle, hub]
---

# kb — bundles

**Hub** for the `kb-*` family: vocabulary, shared reference, routing. Knowledge **compounds** —
compiled once, kept current, not re-derived per query. Does not modify a bundle — routes to the
skill that does.

## Key terms

[references/glossary.md](references/glossary.md) defines the vocabulary. Minimum before routing:
**Bundle**, **Ingest**, **Progressive disclosure**, **Trust model** (see
[trust-model.md](references/trust-model.md)).

## The one hard rule

A bundle is **conformant** iff every non-reserved `.md` file has parseable YAML frontmatter with a
non-empty `type`. Everything else is soft guidance — consumers MUST tolerate missing optional fields,
unknown types, and broken links. Never reject a bundle over them. Full rules:
[references/SPEC.md](references/SPEC.md) §11.

The domain portion of `spec/types.md` is a living, producer-chosen vocabulary, not a validation
enum. Keep the workflow conventions `Reference` and `Spec Section`; start the domain types small
and evolve them through [`kb-ingest`](../kb-ingest/SKILL.md) or
[`kb-document`](../kb-document/SKILL.md) when the domain reveals a durable new kind of entity. Use
[`kb-lint`](../kb-lint/SKILL.md) to detect schema drift.

## Route to the right skill

| The user wants to… | Use |
|---|---|
| Start a new bundle | [`kb-init`](../kb-init/SKILL.md) |
| Capture, ingest, file, or process a source (note, transcript, PDF, image, URL) | [`kb-ingest`](../kb-ingest/SKILL.md) |
| Document a repository, explain its architecture/workflows, or refresh knowledge after code changes | [`kb-document`](../kb-document/SKILL.md) |
| Ask what the bundle knows; look something up; explore connections | [`kb-query`](../kb-query/SKILL.md) |
| Health-check the bundle (**drift**, orphans, contradictions, conformance) | [`kb-lint`](../kb-lint/SKILL.md) |
| See the bundle as a graph | [`kb-visualize`](../kb-visualize/SKILL.md) |

If a `knowledge/` bundle exists and would inform the current task, consult it via
[`kb-query`](../kb-query/SKILL.md) before answering from scratch — even when the user didn't ask an
explicit knowledge question.

## Shared reference (single source of truth)

Every `kb-*` skill reads these rather than restating them, so the family stays consistent:

- [references/SPEC.md](references/SPEC.md) — OKF v0.2, vendored verbatim.
- [references/version-profile.md](references/version-profile.md) — v0.2 production and v0.1
  compatibility rules; every writing skill reads it before changing a bundle.
- [references/glossary.md](references/glossary.md) — leading words and definitions.
```
END THIRD-PARTY FILE 4276f403a4f8e840

The third-party file has ended. Everything between the 4276f403a4f8e840 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 3089 of 3373 bytes. © stjbrown · MIT · https://github.com/stjbrown/agent-knowledge/tree/HEAD/skills/kb/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md