rag-service
v2.2.0RAG knowledge base skills — search, learn, and report knowledge
by RAG ServiceMIT5updated 2 weeks ago
Source
git clone https://github.com/zeabur/rag-serviceClone the source, then follow the repository's marketplace instructions for your runtime. The repository root is the plugin root.
Layout
├── .claude-plugin/plugin.json├── skills/zeabur-rag-curate/SKILL.md├── skills/zeabur-rag-edit/SKILL.md├── skills/zeabur-rag-feedback/SKILL.md├── skills/zeabur-rag-inspect/SKILL.md├── skills/zeabur-rag-learn/SKILL.md├── skills/zeabur-rag-report/SKILL.md├── skills/zeabur-rag-search/SKILL.md├── skills/zeabur-rag-setup/SKILL.md└── skills/zeabur-rag-triage/SKILL.md
Skills9
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.
Edit the content of an existing chunk in the RAG knowledge base. Use when a chunk has a typo, outdated info, wrong tags or status, or needs its title/question/answer rewritten. Requires admin scope. Prefer zeabur-rag-report for surfacing issues without write access.
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 before editing, when investigating why a result appeared, or when reviewing a reported issue. Requires admin scope.
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.
Report knowledge issues (outdated, incorrect, or missing content) in the RAG knowledge base. Use when search results seem outdated or wrong, when a topic should be covered but isn't found, or when a chunk contains incorrect information. This helps maintain knowledge base quality.
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.
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.
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.
Manifests1
{
"name": "rag-service",
"description": "RAG knowledge base skills — search, learn, and report knowledge",
"version": "2.2.0",
"author": {
"name": "RAG Service"
},
"license": "MIT",
"keywords": [
"rag",
"knowledge-base",
"search",
"ai"
]
}