Openclaw Skills for OKF helps AI agents read, create, validate, and traverse vendor-neutral knowledge bundles stored as markdown files with YAML frontmatter.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install okf-knowledge-format
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install okf-knowledge-format using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is OKF (Open Knowledge Format) Skill?
Openclaw Skills for OKF is a developer-focused workflow for working with Google’s Open Knowledge Format (OKF), a vendor-neutral way to store knowledge as a directory tree of markdown concepts with YAML metadata. It gives AI agents a consistent structure for discovering, traversing, and maintaining knowledge bases through links, indexes, and metadata-aware conventions.
With Openclaw Skills, you can generate new concepts, validate bundle integrity, search content, inspect link graphs, and keep knowledge organized as reusable, human-readable artifacts. The result is an AI-agent-friendly knowledge system that scales from simple reference notes to operational playbooks, metrics, API documentation, and structured data assets.
OKF (Open Knowledge Format) Skill Use Cases
- Building AI-readable knowledge bases from markdown and YAML
- Traversing a bundle by starting from
index.mdand following concept links - Creating new knowledge concepts with the
okf-toolkitCLI - Validating bundle structure before committing changes
- Managing documentation for metrics, playbooks, API endpoints, and data resources
- Generating indexes, graphs, and stats for large knowledge trees
- Preserving knowledge in a vendor-neutral format that supports agentic workflows
How OKF (Open Knowledge Format) Skill Works
- Initialize or open an OKF bundle as a directory tree of markdown files.
- Start reading from
index.mdto discover top-level sections and traverse linked concepts. - Interpret each
.mdconcept file using its YAML frontmatter, especially the requiredtypefield and optional metadata such astitle,description,resource,tags, andtimestamp. - Use the concept type to infer the structure and purpose of the content, such as schemas for BigQuery tables, logic for metrics, procedures for playbooks, or request/response details for API endpoints.
- Create new concepts with
okf new <bundle-path> <concept-id>or author them manually with proper frontmatter and markdown body. - Regenerate structure artifacts with
okf index <bundle>instead of editingindex.mdorlog.mddirectly. - Validate the bundle with
okf validate <bundle-path>after changes to ensure the knowledge base remains consistent and consumable. - Use auxiliary commands like search, graph, list, and stats to inspect, audit, and maintain the bundle over time.
OKF (Open Knowledge Format) Skill Setup
- Install the CLI toolkit.
pip install git+https://github.com/akdira/okf-toolkit.git
- Initialize a new bundle when starting from scratch.
okf init <path>
- Create a new concept using the CLI.
okf new <bundle-path> <concept-id>
- Validate the bundle after edits.
okf validate <bundle-path>
- Use the core inspection commands as needed.
okf list <bundle>
okf show <bundle> <id>
okf search <bundle> <q>
okf index <bundle>
okf graph <bundle>
okf stats <bundle>
- For manual authoring, ensure each concept file uses YAML frontmatter delimited by
---, includes a meaningfultype, and follows the one-concept-per-file pattern.
OKF (Open Knowledge Format) Skill Data Schema & Taxonomy
OKF organizes knowledge as a bundle: a directory tree of markdown files with YAML frontmatter for concept files and plain markdown for navigation/history files.
| Artifact | Purpose | Format | Notes |
|---|---|---|---|
index.md |
Directory listing for a bundle | Markdown without frontmatter | Auto-generated; do not edit directly |
log.md |
Update history | Markdown without frontmatter | Auto-generated; do not edit directly |
| Concept file | One unit of knowledge | .md with YAML frontmatter + markdown body |
One concept per file |
Frontmatter type |
Core classification | String | Required; examples include BigQuery Table, Metric, Playbook, API Endpoint |
Frontmatter title |
Human-friendly label | String | Recommended |
Frontmatter description |
Short summary | String | Recommended |
Frontmatter resource |
Source or canonical link | URI string | Recommended |
Frontmatter tags |
Discovery metadata | YAML list | Recommended; examples: core, pii, deprecated |
Frontmatter timestamp |
Freshness tracking | ISO 8601 string | Recommended |
Taxonomy rules:
- Use descriptive
typevalues to preserve meaning. - Link concepts using standard markdown links to build traversable knowledge graphs.
- Unknown frontmatter keys should be tolerated by consumers, not treated as errors.
- Keep metadata concise, machine-readable, and compatible with agent traversal.
OKF (Open Knowledge Format) Skill Advanced Features
- Supports AI-agent-friendly traversal through
index.mdand linked concepts - Enables knowledge graph inspection with
okf graph - Provides full-text retrieval with
okf search - Generates bundle statistics and tag clouds with
okf stats - Enforces structural consistency through
okf validate - Supports automated index generation via
okf index - Tolerates unknown frontmatter keys for forward compatibility
- Works well for multi-domain knowledge bundles spanning metrics, APIs, playbooks, and data documentation
- Encourages scalable knowledge maintenance with one-concept-per-file architecture
SKILL.md
Loading
Related Openclaw Skills
Code Analysis Toolkit Free
A local, privacy-respecting Git history analysis and self-reflection tool that generates descriptive style and quality reports for personal developers.
GitHub Dev Standard Free
A structured 9-step development workflow and quality gate system for AI agents, preventing scope creep and ensuring tested code deliveries.
Git Toolkit (Free)
An Openclaw Skills entry offering core Git version control capabilities, including branch workflows, commit tracking, and conflict resolution via command execution.
Golang Toolkit Free
A technical reference and diagnostic skill designed to help AI coding agents identify and prevent concurrent leaks, channel deadlocks, and memory issues in Go applications.
Chat Toolkit Free
Openclaw Skills Chat Toolkit Free helps AI agents learn and apply user communication preferences from explicit feedback, storing them locally for consistent, reusable responses.
Chart Generator Free
Chart Generator Free lets you create terminal-ready ASCII, HTML, and SVG charts from a single Bash command.
Featured*
