ragoraUse Ragora MCP tools and REST API to discover, search, and synthesize answers from knowledge bases. Trigger when the user asks for grounded answers from Ragora collections, cross-collection comparison, source-backed summaries, due diligence research, or verification using marketplace data.
Install via ClawdBot CLI:
clawdbot install mregmi/ragoraGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://api.ragora.app/v1/searchCalls external URL not in known-safe list
https://github.com/velarynai/ragora-openclawUses known external API (expected, informational)
raw.githubusercontent.comAI Analysis
The skill's external API calls (api.ragora.app) are consistent with its stated purpose of retrieving data from Ragora knowledge bases and are documented in the skill definition. While it sends user queries to an external service, this is an expected and authorized function for a search/retrieval skill, not unauthorized exfiltration. The primary risk is standard third-party data handling, not hidden malicious behavior.
Generated Mar 21, 2026
Law firms use Ragora to search across collections of contracts, regulations, and case law to verify compliance and identify risks during mergers or audits. They apply filters by jurisdiction and tags like 'MSA' to retrieve relevant clauses and precedents.
Consultants leverage Ragora to compare data from multiple marketplace collections, such as industry reports and competitor analyses, to generate source-backed summaries for strategic recommendations. They use versioning to track trends over time.
Engineering teams query versioned API documentation collections to troubleshoot issues or integrate systems, using semantic search to find specific code snippets or configuration details. They narrow results with custom tags like 'deprecated'.
Financial institutions employ Ragora to cross-reference internal policy collections with external regulatory updates, ensuring adherence to standards like GDPR or SOX. They filter by region and department to validate procedures.
Researchers use Ragora to discover and synthesize answers from academic paper collections, comparing findings across studies to support hypotheses. They apply iterative queries to build comprehensive, attributed summaries.
Ragora operates a marketplace where third-party sellers offer specialized knowledge bases, charging users credits per retrieval based on pricing tiers. Revenue is generated from transaction fees on credit purchases and top-ups.
Organizations subscribe to premium collections or unlimited access to their own curated knowledge bases, paying recurring fees. This model ensures predictable revenue from enterprise clients and ongoing usage.
Ragora licenses its MCP and REST API to developers and platforms, charging based on usage volume or tiered plans. Revenue comes from API calls, with higher tiers offering advanced features like custom filters.
💬 Integration Tip
Always start with discover_collections() to identify available knowledge bases before querying, and use environment variables to securely manage API keys without hardcoding.
Scored Jun 19, 2026
Audited Apr 16, 2026 · audit v1.0
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Check Antigravity account quotas for Claude and Gemini models. Shows remaining quota and reset times with ban detection.
使用豆包(火山引擎)语音合成大模型 API 将文本转换为语音音频文件。支持声音复刻音色(S_ 开头的音色ID)和官方预置音色。当用户要求"语音合成"、"文字转语音"、"TTS"、"朗读文本"、"生成语音"、"用我的声音读"、"豆包语音"、"声音复刻合成"等相关请求时,务必使用此 skill。即使用户只是说"帮我把...
Intelligent model routing for sub-agent task delegation. Choose the optimal model based on task complexity, cost, and capability requirements. Reduces costs...
自动生成科技新闻摘要。从多个来源(RSS、Twitter、GitHub、Web Search)抓取科技新闻,整合后生成摘要。
让 AI 代理根据对话内容自动选择最合适的模型。四层识别(系统过滤→关键词→指示词→语义相似度),四池架构(高速/智能/人文/代理),五分支路由,全自动 Fallback 回路。支持 trigger_groups_all 非连续词组命中。