Okf Generator

What it does

When your agent uses it

• The user wants to: index a codebase
• Generate OKF bundles
• Extract code knowledge into structured markdown
• Convert codebases into training data

Example prompts

• “index my code”
• “generate knowledge bundle”
• “extract codebase concepts”
• “/okf-generator”

Requirements

• Python 3
• A credential in SYNTH_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 5fb73be. 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/, which the agent can run.

  Shell commands in SKILL.md call:

  • pip

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

• Network

  No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

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

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • SYNTH_API_KEY

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

Context cost

Okf Generator loads about 1.7k tokens when it runs, and up to ~7.2k if it reads all its reference files. Until then it costs about 157 tokens; SKILL.md has 427 words of instructions outside code blocks.

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

~157

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

~1.7k

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

~7.2k

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 UmairBaig8/okf-generator at commit 5fb73be, republished under its MIT licence (© UmairBaig8). 427 words, ~1,670 tokens.

name

okf-generator

description

Generate OKF (Open Knowledge Format) v0.2 knowledge bundles from codebases, and look up exact concepts for AI agent context injection. Use this skill whenever the user wants to: index a codebase, generate OKF bundles, extract code knowledge into structured markdown, convert codebases into training data, look up functions/classes/modules by name, prime an AI agent with codebase context, or integrate codebase knowledge with OpenCode or other AI coding agents. Also trigger for phrases like "index my code", "generate knowledge bundle", "extract codebase concepts", "what does X class do", or "look up X in OKF".

codebase
   |
   v
okf generate  -->  okf_bundle/          (domain/resource-path layout)
                       |
                okf lookup               (zero-LLM concept search)
                       |
                okf pairs          -->  okf_pairs.jsonl  (training data)

pip install okf-generator
# With LLM enrichment:
pip install "okf-generator[llm]"

okf generate <source_dir> <output_dir>

okf generate <source_dir> <output_dir> --enrich
# or run enrichment standalone on an existing bundle:
okf enrich <output_dir>

// .okfconfig
{
  "llm": { "enabled": true, "base_url": "http://localhost:8080/v1", "api_key": "llamabarn" },
  "providers": {
    "default": { "model": "ggml-org/gemma-3-4b-it-qat-GGUF:Q4_0", "max_workers": 2 }
  }
}

okf_bundle/
├── SUMMARY.md              <- bird's-eye view for AI agents
├── index.md                <- root index
├── log.md                  <- generation history
└── <domain>/
    └── <module>/
        ├── index.md        <- lists all concepts in folder
        ├── <module>.md     <- Module concept
        └── <ClassName>.md  <- Class / Function concepts

# Full detail — signature, docstring, params, returns, related
okf lookup WorldBankConnector

# All concepts from one source file
okf lookup --file StockAI/RnD/python/connectors/economic_data.py

# Filter by type
okf lookup --type Class connector

# Filter by tag
okf lookup --tag lang:python --tag type:Function fetch

# Compact list (many results)
okf lookup --compact connector

# JSON output (programmatic / agent use)
okf lookup --json WorldBankConnector

# Custom bundle path
okf lookup --bundle ./Knowlege/okf_bundle WorldBankConnector

# Static only (instant, no LLM)
SKIP_SYNTH=1 okf pairs <bundle_dir> output.jsonl

# With LLM (QA, doc, summarize pairs)
SYNTH_BASE_URL="http://localhost:8080/v1" \
SYNTH_API_KEY="llamabarn" \
SYNTH_MODEL="ggml-org/gemma-3-4b-it-qat-GGUF:Q4_0" \
MAX_WORKERS=2 \
QA_PER_CONCEPT=3 \
okf pairs <bundle_dir> output.jsonl

# Specific pair types only
PAIR_TYPES="codegen,qa" okf pairs <bundle_dir> output.jsonl

okf summarize <bundle_dir>

# 1. Add to AGENTS.md (auto-loaded by OpenCode)
echo "OKF bundle at ./okf_bundle — use: okf lookup <Name>" >> AGENTS.md

# 2. Add lookup command
mkdir -p .opencode/commands
echo "RUN okf lookup --bundle ./okf_bundle \$NAME" \
  > .opencode/commands/lookup.md

© UmairBaig8, 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 481 other files (scripts, references) in the repository root of UmairBaig8/okf-generator.

• SKILL.md
• .cursorrules
• .devcontainer/devcontainer.json
• .dockerignore
• .github/ISSUE_TEMPLATE/bug_report.md
• .github/ISSUE_TEMPLATE/feature_request.md
• .github/PULL_REQUEST_TEMPLATE.md
• .github/copilot-instructions.md
• .github/workflows/ci.yml
• .github/workflows/demo-viz.yml
• .github/workflows/deploy-docs.yml
• .github/workflows/docker-publish.yml
• .github/workflows/okf-bundle.yml
• .github/workflows/publish.yml
• .gitignore
• .opencode/commands
• … and 466 more

Open the folder on GitHubat commit 5fb73be