メニュー
Create or update canonical OKF concept documents from repository evidence without inventing numeric market facts.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Fetch and validate OHLCV market data, score and rank instruments, generate structured analysis artifacts and Hugo reports, and send analysis workflow notifications.
Maintain OKF indexes, logs, tags, cross-links, duplicate consolidation, and stale concept cleanup.
Fetch validated evidence bundles and event calendars, generate the grounded AI qualitative analysis artifact with one capped Claude API call, and validate and gate it before any rendering.
Create or update data/cfd_instruments.csv from GMO Click Securities and Rakuten Securities CFD lineup pages, including ticker symbols.
Review changes touching OKF, generated knowledge content, adapter code, skills, docs, or CI.
Generate Hugo shadow content from OKF and troubleshoot Hugo publication.
| name | aims-okf-author |
| description | Create or update canonical OKF concept documents from repository evidence without inventing numeric market facts. |
| disable-model-invocation | false |
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.
okf/content/knowledge/content/results/data/analysis/*.jsonuv run python tools/okf_hugo_adapter.py --src okf --dst content/knowledge --cleanuv run python tools/okf_hugo_adapter.py --src okf --dst content/knowledge --checkhugo --gc --minifycontent/knowledge/; regenerate it from okf/.