Agent skill

Okf

by serradura in serradura/okf

Be the expert on Open Knowledge Format (OKF) — portable project knowledge as a directory of markdown files with YAML frontmatter that humans and agents read from one source.

Apache-2.0Auto-check: notesDevOps & Cloud

Install Okf

skills CLI
$ npx skills add serradura/okf --skill okf -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install serradura/okf okf --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/serradura/okf.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/okf .claude/skills/okf && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
okf
GitHub stars
178
Token cost
~3.2k tokens
SKILL.md length
1,591 words
Files
28
Skills in repo
2
Repo updated
First seen
Licence
Apache-2.0

At a glance

Be the expert on Open Knowledge Format (OKF) — portable project knowledge as a directory of markdown files with YAML frontmatter that humans and agents read from one source.

  • Works in 3 steps: §11 cond. 1 every non-reserved .md file… → §11 cond. 2 every such block has a… → §11 cond. 3 every reserved file present…
  • Capturing knowledge into a bundle (a service
  • SKILL.md covers The hard rules (§11 conformance), Three lenses — hold them…, The CLI is your eyes — you are… and Orient before you touch anything, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Okf is an agent skill from serradura/okf. Be the expert on Open Knowledge Format (OKF) — portable project knowledge as a directory of markdown files with YAML frontmatter that humans and agents read from one source. Use when capturing knowledge into a bundle (a service, schema, metric, decision, runbook: "document this in OKF", "capture this as a concept"), converting existing docs into one ("migrate/OKFy our docs into a bundle"), retrieving from one without reading it whole ("what do we know about X?", "where is X documented?", "search the bundle")…

Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 30 other files (for example `playbooks/consume.md`, `playbooks/curate.md` and `playbooks/doctor.md`).

It sits in DevOps & Cloud, covering Runbooks and postmortems and Linting and formatting. It works with Docker. The repository describes itself as: OKF (Open Knowledge Format): Durable, structured memory for AI agents. Author, validate, consume, and maintain portable knowledge bundles through an ecosystem of Skills, MCP, an… The licence is Apache-2.0.

When your agent uses it

  • Capturing knowledge into a bundle (a service
  • Runbook: document this in OKF
  • Capture this as a concept)
  • Converting existing docs into one (migrate/OKFy our docs into a bundle)

Example prompts

  • “document this in OKF”
  • “capture this as a concept”
  • “migrate/OKFy our docs into a bundle”
  • “/okf”

Requirements

  • Pre-approved tools (allowed-tools): Read, Write, Edit, Grep, Glob, Bash

Workflow steps

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

  1. §11 cond. 1 every non-reserved .md file has a parseable YAML frontmatter block;
  2. §11 cond. 2 every such block has a non-empty type;
  3. §11 cond. 3 every reserved file present is well-formed — a nested index.md has

What it can do on your machine

Read from SKILL.md and the folder at commit cfb7ffa. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Grep
    • Glob
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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.

Context cost

Okf loads about 3.2k tokens when it runs. Until then it costs about 206 tokens; SKILL.md has 1,591 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~206
When it runs · the whole SKILL.md, loaded when a task matches
~3.2k

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

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Edit, Grep, Glob, Bash

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from serradura/okf at commit cfb7ffa, republished under its Apache-2.0 licence (© serradura). 1,591 words, ~3,153 tokens.

Download SKILL.mdSave it as .claude/skills/okf/SKILL.md (or your agent's skills folder). This skill also uses 27 other files; get the full folder from GitHub.
name
okf
description
Be the expert on Open Knowledge Format (OKF) — portable project knowledge as a directory of markdown files with YAML frontmatter that humans and agents read from one source. Use when capturing knowledge into a bundle (a service, schema, metric, decision, runbook: "document this in OKF", "capture this as a concept"), converting existing docs into one ("migrate/OKFy our docs into a bundle"), retrieving from one without reading it whole ("what do we know about X?", "where is X documented?", "search the bundle"), updating one after code or docs change ("update the knowledge bundle"), checking its conformance or curation quality ("validate/lint the bundle"), serving or rendering it as a graph, or working in a repo that already carries an OKF bundle — a `.okf/` directory or a root `index.md` carrying `okf_version`.
allowed-tools
Read, Write, Edit, Grep, Glob, Bash
user-invocable
true
argument-hint
[search|produce|migrate|maintain|refine|consume|curate|doctor|<okf-cli-verb>] [dir|@slug] [--flags]

Open Knowledge Format (OKF)

You are the OKF expert in this repository. OKF is knowledge as code: a directory of markdown files, each with YAML frontmatter, that both humans and agents read from the same source. It is minimal on purpose — no schema registry, no runtime, no SDK. All the power lives in conventions and judgment, not in enforcement. This skill is where that judgment lives; the okf CLI handles the mechanics.

Two ideas govern everything:

  • Dual audience. Every file must serve a human skimming it and an agent extracting from it. That is why bodies are structural markdown and links are plain markdown links — both readers already understand them.
  • The graph is emergent. Files are nodes, markdown links are edges. You never declare a graph; it arises from how you link concepts. Good linking is good knowledge modelling.

The hard rules (§11 conformance)

Three conditions, all hard — validate fails a bundle on any of them:

  1. §11 cond. 1 every non-reserved .md file has a parseable YAML frontmatter block;
  2. §11 cond. 2 every such block has a non-empty type;
  3. §11 cond. 3 every reserved file present is well-formed — a nested index.md has no frontmatter, the bundle-root index.md carries only okf_version, and log.md date headings are ISO YYYY-MM-DD.

Everything else is soft guidance, and consumers MUST tolerate missing optional fields, unknown types, and broken links — a bundle is never rejected over them.

Three lenses — hold them separate

Judging a bundle means asking three different questions. Conflating them is the most common mistake:

LensQuestionToolNature
LegalIs it conformant OKF? (§11)validateBinary, tolerant
GoodIs it navigable, complete, fresh?lintAdvisory, structural
TrueIs it consistent and current?you, over lint --jsonSemantic — needs meaning

validate is forbidden by §11 from failing a bundle for broken links or missing optional fields — that is lint's job. And neither tool can judge contradictions or semantic staleness (a concept that parses fine but no longer matches reality); only an agent reasoning over meaning can. That last lens is where you earn your keep as the expert, not the executable.

The CLI is your eyes — you are the judgment

The okf executable answers every mechanical question deterministically, and its read views show everything the browser UI does. Don't probe for it — just run the verb. A proactive command -v okf before every task spends a whole tool round proving what the next command reveals for free; the CLI's own failure is a cheaper, truer signal. (The two deliberate exceptions are menu and doctor — both decide whether to install, so they check first.) The one distinction to hold: a shell okf: command not found is the only thing that means "install it" (→ doctor); every line that starts error: is okf answering — a bundle or usage result to read and act on, never a missing toolchain to send to doctor.

Don't memorize the surface — okf --help maps every verb, okf <verb> --help its flags. The division of labour is the whole game:

  • Shell out — never eyeball — anything a verb computes: conformance (§11), what exists, what links where, where a term lives, what's stale, the map. Every read verb takes --json and the list views filter by type/dir/tag, so ask the narrow question instead of paging the bundle.
  • Skeleton first, bodies last. dirs, search, graph --minimal, and --fields projections each answer for a fraction of a dump's bytes; full bodies are the final step of a retrieval, never the first. <!-- rule:okf-skeleton-first -->
  • You judge — the CLI can't — meaning: contradictions, semantic staleness (parses fine, no longer true), whether a loose file is terminal-by-design, whether a singleton tag is a deliberate marker. Tool output is evidence, never a verdict.

The one trap worth carrying in your head: the age cutoff is off by default — a plain okf lint reports concepts past their own declared stale_after (the expired check reads the clock the CLI supplies), but never judges age; pass --stale-after <90d|12w|ISO-date> when you want anything not touched since then flagged too — the two mechanisms share a spelling and nothing else (cli/checks.md, rule okf-two-clocks).

<!-- check:stale -->

Read cli.md before interpreting a verb's output in depth. It is the index and the shared contract — refs, exit codes, --json, the filters — and its table routes to the one file the verb lives in: checks (what validate may and may not reject, lint's categories and check ids), search, map (index/dirs), views (the tag-curation views), serve (the trust boundary), registry, graph.

Orient before you touch anything

Picking up a bundle you don't already know — to consume or maintain — start with okf dirs <dir|@slug>: one row per directory, so it stays small on a bundle of any size and it names the branches every other view narrows to. Then open the one you want with okf index <dir|@slug> --dir <branch> (the §8 map: that directory's index body, rollups, and listing), and read log.md (the §9 baseline of what changed last) — all of it before greping or opening leaves. Reach for index rather than grep for the one reason that outranks convenience: grep cannot find an index entry that is missing, so enumeration drift is invisible to it — you can't search for the word that should be there but isn't. <!-- rule:okf-orient-index --> Per-verb steps are in the playbooks (the Commands table below; no okf installed? read the root index.md plus each area's index.md).

Show full SKILL.md (706 more words)Show less

The authoring verbs — the craft

produce (create or extend a bundle), maintain (sync it with reality), consume (use it as context) carry the judgment the executable can't — this is where the skill earns its keep. Each has a playbook (the Commands table below); read the modelling craft in authoring.md before producing or maintaining. When you need chapter and verse, go through spec-map.md — which § settles which question — into the verbatim SPEC.md.

No subcommand? Infer intent: "document this / capture X" → produce; "convert / migrate / OKFy these existing docs into a bundle" → migrate; "the code changed, update the docs" → maintain; "restructure / rebalance the bundle / is the structure right / get more out of it" → refine; "what do we know about X / where is X documented" → search; a repo already carrying a bundle plus a task needing its knowledge → consume; "check / graph / preview it" → run the matching CLI verb and interpret the result. When genuinely ambiguous, ask.

Which target? A leading @ is a registry ref, not a path: @slug names a bundle registered with okf registry set, bare @ the default — route it straight to okf <verb> @slug and skip the directory hunt (okf search spans several: @a @b, or @all). A @slug may instead name a group — a saved set of bundles (okf registry group backend @a @b, members nest); it resolves like any ref for the two set-taking verbs (okf search @backend, okf server @backend) and every single-bundle verb refuses it with exit 2, the message saying which two take a group. A plain path is used as given. Given no target and a cwd that carries no bundle, okf registry list is the next move, not a hunt across sibling directories. Producing a new bundle with no path? Default to .okf/ at the repo root, but first detect whether the project already keeps its bundle elsewhere (e.g. docs/) and prefer that; commit it alongside the code it describes.

Target isn't a bundle? When a verb points at a directory that holds markdown but no root index.md carrying okf_version — validate failing wholesale on missing frontmatter — don't grind through the errors: suggest migrate (OKFy it in place, bodies verbatim) and let the user pick.

Commands

The first word of the arguments picks a row. No arguments at all — someone asking "what should I do?" — is its own row: read playbooks/menu.md, orient on the signals, and recommend the highest-value move without running one. When there is wording but no matching first word, infer intent as in "No subcommand?" above. Read the referenced playbook before executing — it is the procedure.

VerbCategoryWhat it doesReference
(none)Orientrecommend the highest-value next move; never auto-runplaybooks/menu.md
searchUseanswer a question from the bundle: map → finder → only the winning bodiesplaybooks/search.md
produceAuthorcreate or extend a bundleplaybooks/produce.md
migrateAuthorconvert existing docs in place: frontmatter + reserved files, bodies verbatimplaybooks/migrate.md
maintainAuthorsync the bundle's content with reality after a changeplaybooks/maintain.md
refineAuthoroptimize the bundle's structure: evidence-driven, cohesion-first; proposes, never auto-appliesplaybooks/refine.md
consumeUseuse the bundle as context for a taskplaybooks/consume.md
curateCuratestructural upkeep as it stands: validate + lint + looseplaybooks/curate.md
doctorSetupinstall and verify the CLI, then doctor the bundleplaybooks/doctor.md
<okf-cli-verb>Readvalidate, lint, loose, index, catalog, files, tags, types, stats, graph, server, render, registry, skill — plus any verb an installed extension adds (okf help is authoritative, this list is not)okf <verb> --help + reference/cli.md

Three boundaries worth keeping sharp: curate is structural upkeep only — when the content no longer matches reality, that is maintain, and when the content is right but the shape underserves retrieval, that is refine — and doctor is the one playbook that does not assume the CLI is installed. In Claude Code with the okf plugin, /okf:gem routes these same verbs.

The lifecycle is a flywheel, not phases

produce seeds a bundle; consume reads it; maintain runs whenever reality drifts or whenever consuming teaches you something durable — that write-back reflex is what keeps a bundle alive instead of rotting into folklore. When you learn something while consuming, switch to maintain and record it. The playbooks live one per verb in playbooks/ (the Commands table above); the modelling craft (granularity, choosing type, tag vocabulary, topology, resource, links, citations) is in reference/authoring.md.

© serradura, Apache-2.0. 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 27 other files in skills/okf of serradura/okf.

  • SKILL.md
  • playbooks/consume.md
  • playbooks/curate.md
  • playbooks/doctor.md
  • playbooks/maintain.md
  • playbooks/menu.md
  • playbooks/migrate.md
  • playbooks/produce.md
  • playbooks/refine.md
  • playbooks/search.md
  • reference/APACHE-2.0.txt
  • reference/SPEC.md
  • reference/authoring.md
  • reference/cli.md
  • reference/cli/checks.md
  • reference/cli/graph.md
  • reference/cli/map.md
  • reference/cli/registry.md
  • … and 10 more

Open the folder on GitHubat commit cfb7ffa

Compare with similar skills

Okf next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Okf compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Okf this skillserradura/okf178—~3.2kAutomated safety check: NotesApache-2.0
GitHub Actions CreatorFNOSP/FlyNarwhal5091 repos~2.4kAutomated safety check: PassAGPL-3.0
Megalinter Checknvuillam/npm-groovy-lint2481 repos~3.9kAutomated safety check: NotesMIT
Rtk Skillsopaco/deepwiki-rs3.1k—~1.4kAutomated safety check: PassMIT
Session Retrowerf/werf4.7k—~1.6kAutomated safety check: PassApache-2.0
Toolchain Commandslatitude-dev/latitude-llm4.7k—~1.4kAutomated safety check: NotesMIT

Similar skills

  • GitHub Actions Creator

    FNOSP/FlyNarwhal

    A skill your agent uses when the user wants to create, generate, or set up a GitHub Actions workflow.

    509 GitHub starsUsed in 1 repo~2.4k tokens
    DevOps & CloudAuto-check passed
  • Megalinter Check

    nvuillam/npm-groovy-lint

    Collect MegaLinter lint errors for the current repository. An agent skill from nvuillam/npm-groovy-lint.

    248 GitHub starsUsed in 1 repo~3.9k tokens
    DevOps & CloudAuto-check: notes
  • Rtk Skill

    sopaco/deepwiki-rs

    A skill your agent uses when running shell commands that produce verbose output (git, test, build, lint, package managers, docker).

    3.1k GitHub stars~1.4k tokensUpdated 26 days ago
    DevOps & CloudAuto-check passed
  • Session Retro

    werf/werf

    Analyze the current session for harness-worthy lessons — repeated corrections, discovered conventions, skill bugs — and turn them into concrete repo changes: docs, skills, task targets, linter…

    4.7k GitHub stars~1.6k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Toolchain Commands

    latitude-dev/latitude-llm

    Installing dependencies, running dev/build/test/lint, filtering packages, single-test runs, git hooks, preparing a clone (.env.development / .env.test), or Docker-backed local services and dev…

    4.7k GitHub stars~1.4k tokensUpdated yesterday
    DevOps & CloudAuto-check: notes
  • Modern Web Guidance

    JetBrains/skills

    Official

    Search tool for modern web development best practices. An agent skill from JetBrains/skills.

    366 GitHub starsUsed in 3 repos~1.4k tokens
    DevOps & CloudAuto-check passed

More from serradura/okf

  • Okf Principles

    serradura/okf

    Restructure agent instruction artifacts (Claude Agent Skills, rules files, CLAUDE.md, playbooks) by applying five structural principles derived from the Open Knowledge Format - bounding the…

    178 GitHub stars~994 tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Okf

What does Okf do?

Be the expert on Open Knowledge Format (OKF) — portable project knowledge as a directory of markdown files with YAML frontmatter that humans and agents read from one source. Okf is an agent skill from serradura/okf. Be the expert on Open Knowledge Format (OKF) — portable project knowledge as a directory of markdown files with YAML frontmatter that humans and agents read from one source.

When should I use Okf?

Okf fits situations like: capturing knowledge into a bundle (a service; runbook: document this in OKF; capture this as a concept); converting existing docs into one (migrate/OKFy our docs into a bundle).

How do I install Okf in Claude Code?

Run `npx skills add serradura/okf --skill okf -a claude-code`. Or copy the skill folder (skills/okf in serradura/okf) into .claude/skills/okf in your project. Claude Code loads it when a task matches its description.

How do I install Okf in Codex?

Run `npx skills add serradura/okf --skill okf -a codex`. Or copy the skill folder (skills/okf in serradura/okf) into .agents/skills/okf in your project. Codex loads it when a task matches its description.

Can I use Okf in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add serradura/okf --skill okf -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/okf, .gemini/skills/okf, .github/skills/okf and .opencode/skills/okf in your project.

What does Okf need to run?

SKILL.md names no scripts, command-line tools or credentials: Okf is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Grep, Glob, Bash.

Does Okf access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Okf safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Okf use?

Okf is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Okf use?

About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Okf?

Skills that share tags, products or a category with Okf: GitHub Actions Creator (FNOSP/FlyNarwhal, 509 stars), Megalinter Check (nvuillam/npm-groovy-lint, 248 stars), Rtk Skill (sopaco/deepwiki-rs, 3.1k stars) and Session Retro (werf/werf, 4.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Okf?

serradura (a GitHub user) maintains it in serradura/okf, which has 178 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 6, 2026.

Source: serradura/okf on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.