Open Knowledge Format

What it does

When your agent uses it

• The user mentions OKF
• Open Knowledge Format
• Googles knowledge format
• LLM wiki bundles

Example prompts

• “/open-knowledge-format”

Requirements

• Python 3
• Compatibility (from SKILL.md): Portable across any AgentSkills-compatible harness. The validation script requires Python 3.8+ with PyYAML (pip install PyYAML). All examples use standard markdown — readable in any editor or terminal.

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1Every non-reserved .md file contains parseable YAML frontmatter
2. 2Every frontmatter block contains a non-empty type field
3. 3Reserved filenames (index.md, log.md) follow their defined structure

What it can do on your machine

Read from SKILL.md and the folder at commit 96fbe07. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python3
  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • cloud.google.com
  • gist.github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Portable across any AgentSkills-compatible harness. The validation script requires Python 3.8+ with PyYAML (pip install PyYAML). All examples use standard markdown — readable in any editor or terminal.

  From compatibility in the SKILL.md frontmatter.

Context cost

Open Knowledge Format loads about 2k tokens when it runs, and up to ~5.7k if it reads all its reference files. Until then it costs about 99 tokens; SKILL.md has 704 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~99

When it runs · the whole SKILL.md, loaded when a task matches

~2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~5.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from magnus919/agent-skills at commit 96fbe07, republished under its MIT licence (© magnus919). 704 words, ~2,019 tokens.

name

open-knowledge-format

description

Define knowledge bundles with Google's Open Knowledge Format (OKF) v0.1. Use when the user mentions OKF, Open Knowledge Format, Google's knowledge format, LLM wiki bundles, agent knowledge packs, creating OKF bundles, validating OKF documents, or converting knowledge into the OKF standard. Do not use this skill for unrelated requests; route to the nearest named specialist.

compatibility

Portable across any AgentSkills-compatible harness. The validation script requires Python 3.8+ with PyYAML (pip install PyYAML). All examples use standard markdown — readable in any editor or terminal.

license

MIT

metadata.spec-version

1.0

metadata.skills

okf, open-knowledge-format, knowledge-format, agent-knowledge, llm-wiki

metadata.tags

okf, knowledge-format, google, ai-agents, markdown, knowledge-management

path/to/bundle/
├── index.md                      # Optional. Directory listing for progressive disclosure.
├── log.md                        # Optional. Chronological update history.
├── <concept>.md                  # A concept at the bundle root.
└── <subdirectory>/               # Subdirectories organize concepts into groups.
    ├── index.md
    ├── <concept>.md
    └── <subdirectory>/
        └── …

---
type: <Type name>                  # REQUIRED
title: <Optional display name>
description: <Optional one-line summary>
resource: <Optional canonical URI for the underlying asset>
tags: [<tag>, <tag>, …]            # Optional
timestamp: <ISO 8601 datetime>     # Optional last-modified time
# … other producer-defined key/value pairs
---

# 1. Create a bundle directory
mkdir my-knowledge && cd my-knowledge

# 2. Create a concept file
cat > datasets/sales.md << 'EOF'
---
type: BigQuery Dataset
title: Sales
description: All sales-related tables for the retail business.
tags: [sales]
timestamp: 2026-06-18T00:00:00Z
---
The sales dataset contains [orders](/tables/orders.md) and [customers](/tables/customers.md).
EOF

# 3. Add an index for navigation
cat > index.md << 'EOF'
# Knowledge Bundle

* Sales Dataset (`datasets/sales.md`) - Retail sales data in an example OKF bundle
EOF

# 4. Validate your bundle
python3 scripts/okf-bundle-validate.py .

© magnus919, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 13 other files (scripts, references, assets) in open-knowledge-format of magnus919/agent-skills.

• SKILL.md
• README.md
• assets/concept-template.md
• assets/example-bundle/datasets/index.md
• assets/example-bundle/datasets/sales.md
• assets/example-bundle/index.md
• assets/example-bundle/tables/customers.md
• assets/example-bundle/tables/index.md
• assets/example-bundle/tables/orders.md
• evals/evals.json
• references/bundle-architecture.md
• references/spec-summary.md
• references/use-cases.md
• scripts/okf-bundle-validate.py

Open the folder on GitHubat commit 96fbe07