From kokai-data
Download a single EDINET disclosure document binary (PDF / XBRL ZIP / CSV) by docID. Returns a time-limited signed URL from Kokai's private storage proxy. Use after `edinet-document-search` to retrieve the actual filing for citation or analysis. 日本語 keyword: EDINET 文書取得 / 開示書類 ダウンロード / 有価証券報告書 binary 取得 / 開示文書 PDF 取得.
How this skill is triggered — by the user, by Claude, or both
Slash command
/kokai-data:edinet-document-fetchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when:
Use this skill when:
docID from edinet-document-search and need the actual document binary.Call the kokai MCP server's get_edinet_document tool:
{
"name": "get_edinet_document",
"arguments": {
"docID": "<8-char docID from search_edinet_documents>",
"type": "2"
}
}
type parameter (FSA 公式 §3-2-1)| Code | Format | Content |
|---|---|---|
1 | ZIP | 提出本文書 + 監査報告書 (XBRL 含む) |
2 | 提出本文書 + 監査報告書 (PDF 形式、最も読みやすい) | |
3 | ZIP | 代替書面・添付文書 |
4 | ZIP | 英文ファイル |
5 | ZIP | CSV (XBRL→CSV 変換版) |
Oversize → tool returns edinet_document_too_large error with sizeBytes / maxBytes literal (Phase 2 で大型書類対応検討)。
{
"docID": "S1000001",
"type": "2",
"format": "pdf",
"storageBucket": "edinet-documents",
"storagePath": "S1000001/2/<timestamp>.pdf",
"signedUrl": "https://...supabase.co/storage/v1/object/sign/edinet-documents/...",
"sizeBytes": 1234567,
"source_authority": "official",
"attribution_text": "出典: 金融庁 EDINET",
"boundary": {
"signedUrlSource": "kokai_storage_proxy",
"signedUrlTtlSeconds": 3600,
"sourceAuthority": "edinet_official",
"kokaiModification": "none",
"canonicalSourceUrl": "https://disclosure2.edinet-fsa.go.jp"
}
}
Important: signedUrl is a Kokai Storage proxy with a 1-hour TTL. The actual document content is unmodified from EDINET (kokaiModification: "none"). For canonical citation in long-lived documents, link to canonicalSourceUrl (EDINET 閲覧サイト) instead.
source_authority: ai_summary / ai_estimate 4-layer authority strip に明示)。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.