ワンクリックでManusで任意のスキルを実行

zeabur-rag-learn

スター3

フォーク0

更新日2026年4月16日 16:05

Contribute new verified knowledge to the RAG knowledge base. Use after you've solved a concrete problem, debugged a non-obvious issue, or discovered undocumented behavior that would help future agents — but only after calling zeabur-rag-search first to confirm the knowledge isn't already covered. Only contribute verified facts, not guesses or workarounds. The new chunk is marked unverified until an admin reviews it.

インストール

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。

Manusで実行

ソース

zeabur

zeabur/rag-service

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

RAG Learn

Add new knowledge to the knowledge base. The chunk is immediately searchable but marked as unverified until manually reviewed in the admin dashboard.

Base URL: $ZEABUR_RAG_URL Auth: Authorization: Bearer $RAG_API_KEY

API

curl -s -X POST "$ZEABUR_RAG_URL/api/learn" \
  -H "Authorization: Bearer $RAG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "title": "Short descriptive title",
    "content": "The knowledge content in Markdown",
    "tags": ["relevant", "tags"],
    "source_query": "original user query"
  }'

Field	Required	Description
`title`	Yes	Short descriptive title
`content`	Yes	Knowledge content (Markdown supported)
`tags`	No	Array of tag strings for categorization
`source_query`	No	Original user query that prompted this knowledge

Returns { "id": "LEARNED-...", "ids": ["LEARNED-...-0", ...], "chunk_count": N, "status": "indexed", "verified": false }.

Long content is split into multiple chunks automatically; ids[0] is the first (parent) chunk, subsequent chunks link back via parent_id. id matches ids[0] for backward compatibility.

Guidelines

Only contribute knowledge that is:

Verified correct — not a guess or workaround
General enough — useful to future users, not just this one case
Not already covered — search first to avoid duplicates

このリポジトリの他の Skills

同じリポジトリ

zeabur-rag-curate

zeabur/rag-service

Interactive knowledge base curation loop — reviews pending items (reports, unverified chunks, failed queries, negative feedback) and walks through fixes one by one. Use when asked to "maintain the knowledge base", "review pending items", "run a curation round", "process reports", "clean up the KB", or any request to improve KB quality. This is the main entry point for the expand → organize → reflect cycle, and requires admin scope.

2026-04-133

zeabur-rag-feedback

zeabur/rag-service

Send feedback on RAG search results — thumbs-up (+1) or thumbs-down (-1) to indicate whether the answer was helpful. Use after calling zeabur-rag-search when you can evaluate the quality of the results. Positive feedback reinforces good results; negative feedback flags poor matches for review. Requires write:feedback scope.

2026-04-133

zeabur-rag-inspect

zeabur/rag-service

View a single chunk's full content plus related reports, search signals, and edit history. Use when you need to understand a chunk's context before editing, when investigating why a search result appeared, or when reviewing a reported issue. Triggers on "inspect chunk SUP-1234", "show chunk DOC-xxx", "chunk history", "why did this result appear", "look at this chunk". Requires admin scope.

2026-04-133

zeabur-rag-search

zeabur/rag-service

Search the RAG knowledge base via hybrid search (semantic + BM25). Use whenever answering technical questions that may be covered in your knowledge base — even if the user doesn't explicitly ask you to search. Also use when you need to verify claims or find up-to-date information.

2026-04-133

zeabur-rag-triage

zeabur/rag-service

List pending knowledge base maintenance items — open reports, unverified learned chunks, low-score queries, and negative feedback. Use when checking KB health, reviewing the maintenance queue, or starting a curation session. Triggers on "review queue", "what needs attention in the KB", "pending reports", "unverified chunks", "failed queries", "KB health check". Requires admin scope.

2026-04-133

zeabur-rag-edit

zeabur/rag-service

Edit the content of an existing chunk in the RAG knowledge base. Use when a chunk has a typo, outdated info, wrong tags, wrong visibility, or needs its title/question/answer rewritten — and you want the fix to take effect immediately. Requires admin scope. Prefer zeabur-rag-report for surfacing issues without write access.

2026-04-113

name

zeabur-rag-learn

description

RAG Learn

Add new knowledge to the knowledge base. The chunk is immediately searchable but marked as unverified until manually reviewed in the admin dashboard.

Base URL: $ZEABUR_RAG_URL Auth: Authorization: Bearer $RAG_API_KEY

API

curl -s -X POST "$ZEABUR_RAG_URL/api/learn" \
  -H "Authorization: Bearer $RAG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "title": "Short descriptive title",
    "content": "The knowledge content in Markdown",
    "tags": ["relevant", "tags"],
    "source_query": "original user query"
  }'

Field	Required	Description
`title`	Yes	Short descriptive title
`content`	Yes	Knowledge content (Markdown supported)
`tags`	No	Array of tag strings for categorization
`source_query`	No	Original user query that prompted this knowledge

Returns { "id": "LEARNED-...", "ids": ["LEARNED-...-0", ...], "chunk_count": N, "status": "indexed", "verified": false }.

Long content is split into multiple chunks automatically; ids[0] is the first (parent) chunk, subsequent chunks link back via parent_id. id matches ids[0] for backward compatibility.

Guidelines

Only contribute knowledge that is:

Verified correct — not a guess or workaround
General enough — useful to future users, not just this one case
Not already covered — search first to avoid duplicates