How do I install the Aims Okf Author skill?

Run npx skillmds@latest add dceoy/aims-okf-author in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Aims Okf Author skill do?

Create or update canonical OKF concept documents from repository evidence without inventing numeric market facts. It is listed under Coding & Dev Tools on SkillMD.

Is Aims Okf Author safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Aims Okf Author?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Aims Okf Author free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Aims Okf Author?

dceoy (@dceoy) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Aims Okf Author by dceoy — Agent Skill

Name: Aims Okf Author
Author: dceoy

File contents

AIMS OKF authoring

Author only okf/ files first. Use data/analysis/*.json for numeric facts and cite generated reports only as publication outputs, not canonical facts. Regenerate content/knowledge/ with the adapter before finishing.

AIMS paths and commands

Canonical OKF source: okf/
Generated Hugo shadow content: content/knowledge/
Daily report output: content/results/
Numeric analysis artifacts: data/analysis/*.json
Generate: uv run python tools/okf_hugo_adapter.py --src okf --dst content/knowledge --clean
Check: uv run python tools/okf_hugo_adapter.py --src okf --dst content/knowledge --check
Build: hugo --gc --minify

Guardrails

Do not let LLM-authored OKF prose become the source of truth for scores, ranks, dates, prices, risk gates, or data availability.
Author OKF v0.2 metadata: use generated: { by, at }, front matter sources, and lifecycle status values draft, stable, or deprecated.
Do not use legacy timestamp, structured self-referential resource mappings, or body-level # Citations sections.
Do not hand-edit content/knowledge/; regenerate it from okf/.
Keep custom code small and deterministic.

OKF primary references

Google Cloud announcement: https://cloud.google.com/blog/products/data-analytics/how-the-open-knowledge-format-can-improve-data-sharing
OKF v0.2 specification: https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md

Frequently asked questions

Aims Okf Author