Stats
Actions
Tags
From kokai-data
Formats the ACBS 4-layer authority strip in Kokai-generated briefs, classifying data points into official, normalized, AI summary, and AI estimate tiers with citation requirements.
How this skill is triggered — by the user, by Claude, or both
Slash command
/kokai-data:authority-strip-formatterThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Apply this skill when generating any brief / report / output that includes Kokai data. The 4-layer authority strip is a core part of the Kokai brand promise: every data point in a brief should be classified into one of 4 authority tiers.
Apply this skill when generating any brief / report / output that includes Kokai data. The 4-layer authority strip is a core part of the Kokai brand promise: every data point in a brief should be classified into one of 4 authority tiers.
| Layer | Name | Cite requirement | Examples |
|---|---|---|---|
| 1 | 公式 (official) | cite_required | gBizINFO records, J-Grants public registry, 国税庁 法人番号 公表 |
| 2 | Kokai normalized | cite_required | Kokai-normalized records derived from official sources |
| 3 | AI summary | recommended | AI-generated summary of cited records |
| 4 | AI estimate | recommended | AI-estimated values where official data is absent |
At the footer of every Kokai brief, include:
---
出典 4 階層:
- 公式: <count> records (cite_required)
- Kokai 正規化: <count> records (cite_required)
- AI 要約: <count>
- AI 推定: <count>
詳細出典: <list of source URLs with retrieved_at>
In English:
---
Authority strip (4 layers):
- Official: <count> records (cite_required)
- Kokai normalized: <count> records (cite_required)
- AI summary: <count>
- AI estimate: <count>
Sources: <list of source URLs with retrieved_at>
npx claudepluginhub kokai-data/japan-business-dataSearches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.