jkroepke/okf-crossplane-v2 / .agents/skills/okf-open-knowledge-format
okf-open-knowledge-format
VerifiedCreate, validate, and enrich Open Knowledge Format (OKF) bundles — the open spec for representing organizational knowledge as markdown files with YAML frontmatter. Use when the user mentions 'OKF', 'Open Knowledge Format', 'knowledge bundle', 'OKF bundle', 'create a knowledge base for agents', 'validate OKF', 'convert to OKF', 'enrich knowledge docs', 'agent-readable knowledge', 'LLM wiki', 'knowledge catalog', 'kcmd', or wants to structure knowledge as markdown files for AI agent consumption. Also use when the user has a directory of markdown files and wants to make them interoperable or conformant with the OKF standard. Even for simple requests like 'make this folder OKF conformant' — the skill has critical structural rules the agent needs.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 15.2 KB |
| references/conversion.md | markdown | 4.3 KB |
| references/examples.md | markdown | 6.9 KB |
| references/spec-v02.md | markdown | 36.7 KB |
| scripts/validate.shexecutable | script | 3.0 KB |
scripts/validate.sh
View on GitHub#!/usr/bin/env bash
# OKF Bundle Validator v0.2
# Usage: validate.sh <bundle-path>
# Checks the three core conformance rules from OKF v0.2:
# E1: All non-reserved .md files have YAML frontmatter
# E2: All frontmatter has non-empty 'type' field
# E3: Reserved files follow structure rules
set -euo pipefail
BUNDLE="${1:-.}"
ERRORS=0
WARNINGS=0
TOTAL=0
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[0;33m'
NC='\033[0m'
if [ ! -d "$BUNDLE" ]; then
echo -e "${RED}Error: '$BUNDLE' is not a directory${NC}"
exit 1
fi
echo "Validating OKF bundle: $BUNDLE"
echo "---"
# Find all .md files
while IFS= read -r -d '' file; do
TOTAL=$((TOTAL + 1))
relative="${file#$BUNDLE/}"
basename=$(basename "$file")
# Skip reserved files (validate separately)
if [[ "$basename" == "index.md" || "$basename" == "log.md" ]]; then
# E3: Check reserved file structure
if [[ "$basename" == "index.md" ]]; then
# index.md should NOT have frontmatter (except bundle root may have okf_version)
if head -1 "$file" | grep -q "^---$"; then
# Allow only if it's bundle root and contains okf_version
if [[ "$relative" != "index.md" ]]; then
echo -e "${RED}E3: $relative — index.md should not have frontmatter${NC}"
ERRORS=$((ERRORS + 1))
fi
fi
fi
if [[ "$basename" == "log.md" ]]; then
# log.md should have date headings in YYYY-MM-DD format
if ! grep -qE "^## [0-9]{4}-[0-9]{2}-[0-9]{2}" "$file" 2>/dev/null; then
if [ -s "$file" ]; then
echo -e "${YELLOW}W: $relative — log.md has no ISO 8601 date headings${NC}"
WARNINGS=$((WARNINGS + 1))
fi
fi
fi
continue
fi
# E1: Check for YAML frontmatter
if ! head -1 "$file" | grep -q "^---$"; then
echo -e "${RED}E1: $relative — no YAML frontmatter${NC}"
ERRORS=$((ERRORS + 1))
continue
fi
# Extract frontmatter (between first --- and second ---)
frontmatter=$(sed -n '2,/^---$/p' "$file" | sed '$d')
# E2: Check for non-empty type field
type_value=$(echo "$frontmatter" | grep -E "^type:" | sed 's/^type:\s*//' | tr -d '"' | tr -d "'" | xargs)
if [ -z "$type_value" ]; then
echo -e "${RED}E2: $relative — missing or empty 'type' field${NC}"
ERRORS=$((ERRORS + 1))
continue
fi
# Warnings for recommended fields
if ! echo "$frontmatter" | grep -qE "^title:"; then
echo -e "${YELLOW}W1: $relative — missing recommended 'title' field${NC}"
WARNINGS=$((WARNINGS + 1))
fi
if ! echo "$frontmatter" | grep -qE "^description:"; then
echo -e "${YELLOW}W1: $relative — missing recommended 'description' field${NC}"
WARNINGS=$((WARNINGS + 1))
fi
done < <(find "$BUNDLE" -name "*.md" -type f -print0 | sort -z)
# Summary
echo "---"
echo "Files scanned: $TOTAL"
if [ $ERRORS -eq 0 ]; then
echo -e "${GREEN}✅ Bundle is OKF v0.2 conformant${NC}"
else
echo -e "${RED}❌ $ERRORS error(s) — bundle is NOT conformant${NC}"
fi
if [ $WARNINGS -gt 0 ]; then
echo -e "${YELLOW}⚠ $WARNINGS warning(s)${NC}"
fi
exit $ERRORS
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |