Authors, maintains, and consumes OKF knowledge bundles (markdown + YAML frontmatter) for project knowledge like services, APIs, schemas, metrics, and decisions. Use when capturing or updating project knowledge.
How this skill is triggered — by the user, by Claude, or both
Slash command
/okf:okf [produce|maintain|consume] [path][produce|maintain|consume] [path]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
OKF represents knowledge as a directory of markdown files with YAML frontmatter.
OKF represents knowledge as a directory of markdown files with YAML frontmatter. It is minimal by design: no schema registry, no runtime, no SDK. Your job is to produce, maintain, and consume OKF bundles conformant with the spec, not your memory of it.
Always read the canonical spec before non-trivial work: reference/SPEC.md. It is the verbatim OKF v0.1 specification and the source of truth for every rule below.
A bundle is conformant (§9) iff: every non-reserved .md file has a parseable
YAML frontmatter block, and every such block has a non-empty type field.
Everything else is soft guidance. Consumers MUST tolerate missing optional
fields, unknown types, and broken links — never reject a bundle over them.
.md) is the concept ID.type is required. Add title, description, tags,
timestamp (ISO 8601) when they aid consumption; add resource (a canonical
URI) only for concepts bound to a real asset — omit it for abstract concepts.# Schema, # Examples, # Citations./services/auth-api.md). A link asserts a relationship; its kind lives
in the surrounding prose, not the link.index.md (directory listing, no frontmatter — except the
bundle-root index may carry only okf_version) and log.md (ISO-dated change
history, newest first). Never use these names for concepts.Templates to copy: concept, index, log.
Use .okf/ at the repository root unless the project already uses another
location. Commit it alongside the code it describes — knowledge as code.
# Citations), manual (decisions, playbooks, metrics).services/, datasets/,
decisions/). One concept per file.type, fill recommended fields, cross-link related concepts.index.md per directory (and okf_version: "0.1" in the root
index). Append a dated entry to log.md.resource, path, or
topic). This bookkeeping is exactly what agents are good at — touch every
affected file in one pass.timestamp; fix or add cross-links; create new concepts
for new assets; mark removed assets (**Deprecation**) rather than silently
deleting context.index.md files and append a dated log.md entry
describing what changed.index.md first for progressive disclosure, then follow
links only into the concepts relevant to the task.Never eyeball conformance — run the deterministic checker. Invoke the companion
validate skill (/okf:validate <bundle-dir> --strict), which ships the
checker. If that skill is not installed, run it directly:
uv run "${CLAUDE_SKILL_DIR}/../validate/scripts/okf_validate.py" <bundle-dir> --strict
Resolve every ERROR (hard §9 failures). Warnings are soft; fix them when cheap,
but they never block.
npx claudepluginhub scaccogatto/okf-skills --plugin okfAssesses, validates, and adopts the Open Knowledge Format (OKF) for markdown+frontmatter knowledge bases. Scans repos for frontmatter consistency, validates bundles, and identifies good adoption candidates.
Navigates OKF-documented project knowledge (schemas, metrics, APIs) by reading Markdown files with YAML frontmatter. Activates on `<mega-brain>` blocks or queries about documented concepts.
Maintains Markdown docs under Google's Open Knowledge Format (OKF) with YAML frontmatter as single source of truth. Finds docs, lints pointers, scaffolds ADRs/chapters.