Bilibili RAG turns videos saved in a Bilibili collection into a searchable, source-traceable knowledge base by transcribing their audio and indexing the resulting text. It is for reviewing interviews, lectures, courses, technical videos, and other saved content through retrieval and chat-based questions. The catalogue skill connects a locally running service to OpenClaw so an agent can search and question that knowledge base.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add via007/bilibili-rag --skill bilibili-rag-localgit clone --depth 1 https://github.com/via007/bilibili-ragWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/via007/bilibili-rag/bilibili-rag-local)<a href="https://agentmods.dev/skills/via007/bilibili-rag/bilibili-rag-local"><img src="https://agentmods.dev/badge/skills/via007/bilibili-rag/bilibili-rag-local/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/via007/bilibili-rag/bilibili-rag-local"><img src="https://agentmods.dev/badge/skills/via007/bilibili-rag/bilibili-rag-local.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.00660 |
| Opus 5 | $0.00036 | $0.00330 |
| Sonnet 5 | $0.00014 | $0.00132 |
| Haiku 4.5 | $0.00007 | $0.00066 |
Grade A, and why
bilibili-rag-local scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Bilibili RAG Local
面向本地运行的 bilibili-rag 服务（默认 http://127.0.0.1:8000）。
执行前检查
- 检查服务可达：优先调用
GET /knowledge/stats。 - 若不可达，明确提示“本地服务未启动或端口不是 8000”，不要编造结果。
会话与范围（关键）
- 执行
/chat/ask前，先确保拿到session_id。 - 使用
GET /knowledge/folders/status?session_id=<session_id>获取可用media_id列表，并作为folder_ids传入。 - 内容类问题调用
/chat/ask时，默认必须传：question + session_id + folder_ids，不要传空folder_ids。 - 若缺少
session_id或folder_ids，先向用户索取或先查状态接口，不要直接调用无范围问答。
主要能力
- 检索片段：调用
POST /chat/search?query=<问题>&k=5。 - 问答总结：调用
POST /chat/ask，请求体优先包含：question、session_id、folder_ids。 - 入库状态：调用
GET /knowledge/folders/status?session_id=<session_id>。
返回格式要求
- 先给结论，再给证据。
- 证据优先来自接口返回的
sources或search results。 - 每条证据给出
title + url，必要时补充bvid。 - 当
/chat/ask返回sources=[]或无召回时，明确说明可能是会话无范围或未入库，并提示检查session_id/folder_ids与同步状态。
交互策略
- 用户是闲聊或无关问题时，简短回复后再引导回收藏夹知识问答。
- 用户问题具体且与视频内容相关时，优先调用“带范围参数”的
/chat/ask，不要只按标题猜测回答。 /chat/search仅用于补充证据或列候选，不要替代最终问答结论。
安全边界
- 不输出任何 Cookie、Token、SESSDATA 等敏感信息。
- 不执行与本地
bilibili-rag无关的高风险系统命令。 - 仅使用用户本机可访问的服务地址，不主动访问未知公网接口。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 47 lines · 72 tokens per session scan A 5f347b28d5b8
bilibili-rag-local is a skill published in the GitHub repository via007/bilibili-rag (1,321 stars, last pushed 4d ago), licensed Apache-2.0. It adds 72 tokens to every session and 660 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
azure-search-documents-dotnet
Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.