メニュー
Use when setting up or configuring the RAG plugin for the first time. Use when ZEABUR_RAG_URL or RAG_API_KEY are missing or need to be updated. Use when the RAG skill fails with authentication or connection errors.
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
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.
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.
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.
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.
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.
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.
| name | zeabur-rag-setup |
| description | Use when setting up or configuring the RAG plugin for the first time. Use when ZEABUR_RAG_URL or RAG_API_KEY are missing or need to be updated. Use when the RAG skill fails with authentication or connection errors. |
Configure the required environment variables for the RAG skills.
| Variable | Description | Example |
|---|---|---|
ZEABUR_RAG_URL | RAG service base URL | https://your-rag-service.zeabur.app |
RAG_API_KEY | API key for authenticated writes (report/learn) | rak_xxxxxxxxxxxxxxxx |
RAG_API_KEYis optional for search-only use. Required for/api/reportand/api/learn.
Ask the user for ZEABUR_RAG_URL and RAG_API_KEY (or confirm existing values).
Read ~/.claude/settings.json.
Merge the env section — preserve all existing keys:
{
"env": {
"ZEABUR_RAG_URL": "<value>",
"RAG_API_KEY": "<value>"
}
}
Write the updated file back.
Tell the user to run /reload-plugins or restart Claude Code for the changes to take effect.
~/.claude/settings.json (user scope) so they apply across all projects.RAG_API_KEY can be left empty or omitted.