via007/bilibili-rag-local
skills/bilibili-rag-local/SKILL.md
使用本地 Bilibili RAG 服务进行检索与问答。用户询问 B 站收藏夹内容、视频要点总结、来源追溯、入库状态时使用。内容问答时优先通过 session_id 与 folder_ids 限定范围，避免空范围导致 fallback。
$ install --global
skillsauthnpx skillsauth add via007/bilibili-rag bilibili-rag-localInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 22, 2026, 4:39 AM139.1s1 file scanned
SKILL.md
- name:
- bilibili-rag-local
- description:
- 使用本地 Bilibili RAG 服务进行检索与问答。用户询问 B 站收藏夹内容、视频要点总结、来源追溯、入库状态时使用。内容问答时优先通过 session_id 与 folder_ids 限定范围，避免空范围导致 fallback。
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。
Related Skills
openclaw/taskflow-inbox-triage
data-ai
VerifiedTrustedCommunity
Example TaskFlow authoring pattern for inbox triage. Use when messages need different treatment based on intent, with some routes notifying immediately, some waiting on outside answers, and others rolling into a later summary.
357,764SKILL.mdUpdated Apr 10, 2026
steipete/taskflow-inbox-triage
data-ai
VerifiedTrustedCommunity
Example TaskFlow authoring pattern for inbox triage. Use when messages need different treatment based on intent, with some routes notifying immediately, some waiting on outside answers, and others rolling into a later summary.
356,423SKILL.mdUpdated Apr 13, 2026
steipete/prose
data-ai
VerifiedTrustedCommunity
OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.
356,423SKILL.mdUpdated Apr 13, 2026
openclaw/prose
data-ai
VerifiedTrustedCommunity
OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.
353,662SKILL.mdUpdated Apr 10, 2026