scaccogatto/okf-skills
The OKF toolkit for Claude Code — author, maintain, validate & visualize Open Knowledge Format bundles. Plugin, agent skills, and a GitHub Action.
What it solves
This project provides a toolchain for the Open Knowledge Format (OKF), a vendor-neutral way to store system knowledge as a directory of Markdown files with YAML frontmatter. It allows both humans and AI agents to maintain a portable, version-controlled knowledge base that includes metadata for trust, provenance, and staleness, preventing agents from relying on outdated or unverified information.
How it works
The toolkit implements the OKF v0.2 specification. It provides tools to produce, validate, and visualize knowledge bundles. It uses a deterministic conformance checker to ensure bundles adhere to the spec. For existing projects, it can "backfill" a knowledge bundle by analyzing git history and session transcripts using a map-reduce process with specialized sub-agents.
Who it’s for
Developers and teams using AI coding agents (like Claude Code, Cursor, or Codex) who want a structured, machine-readable way to document their systems that agents can actually use and maintain.
Highlights
- Multi-channel distribution: Available as a Claude Code plugin, agent skills via skills.sh, a GitHub Action for CI validation, and a read-only MCP server.
- Deterministic Validation: Includes a standalone conformance checker that can migrate v0.1 bundles to v0.2.
- Knowledge Backfilling: Automatically reconstructs knowledge bundles from repository history using an event-analyzer and bundle-weaver agent architecture.
- Interactive Visualization: Generates a self-contained HTML graph of the knowledge bundle, computing trust tiers and staleness at render time.
- Enforced Upkeep: An optional "Stop hook" that prevents an agent from finishing a task if tracked files changed but the corresponding OKF documentation was not updated.
Related
- Project
Prorise-cool/Claude-Code-Multi-AgentClaude Code Multi‑Agent is an open‑source framework that gives Anthropic’s Claude Code project awareness and expert‑agent capabilities. It uses a Python Hook system and a locally‑run Ollama model to automatically detect the codebase type, analyse user intent, load 300+ domain‑specific “Skills” (backend, frontend, testing, security, etc.), and enforce automatic documentation (DEVELOPMENT.md, KNOWLEDGE.md, CHANGELOG.md). After cloning, installing Ollama, a model, and uv, you drop your project into the repo and Claude Code instantly knows its context, suggests appropriate tools, and can be driven with slash commands like `/backend‑specialist` or workflow commands such as `/kiro/spec`.
Key points:
- Zero‑config start; all configuration lives in `.claude/settings.json` and `prompts.json`.
- Hooks run on session start, user prompt, tool use, etc., handling project detection, intent analysis, and doc updates.
- Skills are defined by `SKILL.md` files and are auto‑discovered.
- Works entirely locally (no external API), integrates with Git, and is MIT‑licensed.
Ideal for developers or small teams who want a reproducible, on‑premise AI coding assistant.
- Project
shinpr/claude-code-workflowsA set of structured development workflows and plugins for Claude Code that ensure AI-generated code stays within scope and is verified against agreed-upon design documents.
- Project
feiskyer/claude-code-settingsA set of Claude Code plugins (skills & sub‑agents) that add brainstorming, deep research, GitHub issue/PR automation, image generation, translation, and more, with ready‑made config files for many LLM providers.
- Project
michaelshimeles/skillsA curated set of Claude Code agent skills that automate common development tasks—visual diff generation, service‑layer structuring, evidence‑driven UI testing, iterative Greptile review loops, work‑tree isolation, and prose clean‑up—plus a ready‑to‑drop workflow tying them together.
- Project
rampstackco/claude-skillsA library of 103 opinionated Claude Skills that provide a structured framework for building, launching, and growing brands and websites across any web stack.