Akashic Knowledge Base

Query your knowledge base using AI-powered search. Combines web search with chat AI for comprehensive answers.

Security Scan

The skill is internally consistent: it is an instruction-only wrapper that calls platform-provided Akashic connectors to search a knowledge base and the web, and it does not request extra credentials or install software.

Purpose & Capability

The name/description (knowledge base + web search + synthesis) matches the instructions. Declared tools (rag_query, web_search, chat_completion, translate_content) are exactly the capabilities described. No unrelated binaries, env vars, or installs are requested.

Instruction Scope

Instructions stay on-purpose: prefer RAG for internal queries, use web_search for external/real-time info, then synthesize with chat_completion and optionally translate. They do instruct querying internal/proprietary data (rag_query), so using this skill implies the ability to read whatever documents the Akashic RAG connector can access; the SKILL.md does not instruct reading unrelated local files or env vars.

Install Mechanism

No install spec and no code files — instruction-only — so nothing is written to disk or downloaded during install.

Credentials

The skill requests no environment variables or credentials. However, it relies on platform-managed MCP connectors (Akashic, SerpApi/Tavily) to perform searches; those connectors will use whatever credentials are configured by the platform. Confirm that you trust the Akashic connector and its access scope to internal data.

Persistence & Privilege

always is false and the skill does not request system-level persistence or modify other skills. It will run via normal autonomous invocation rights, which is expected for skills.

Assessment

This skill is coherent but grants the Akashic connectors the ability to query your internal knowledge base and perform web searches on your behalf. Before enabling it: (1) Verify you trust the platform's 'mcp:akashic' integration and its access controls (what documents, indexes, or buckets the RAG can read). (2) Confirm how web-search API keys and logs are managed by the platform (SerpApi/Tavily may be used under platform credentials). (3) Test the skill with non-sensitive queries first. If you need stricter data control, restrict the RAG connector's index scope or avoid enabling the skill for sensitive workflows.

You are a knowledge assistant powered by the Akashic platform. You help users find information through web search and AI-powered analysis.

Capabilities

• RAG Query: Search the internal knowledge base using hybrid vector + BM25 search
• Web Search: Real-time search using SerpApi (Google) with Tavily fallback
• Chat AI: Multi-model AI for answering questions and analyzing search results
• Translation: Multilingual support for queries and answers

Workflow

1. Understand the question: Determine if this needs an internal knowledge base query, a web search, or can be answered directly
2. Knowledge Base Search (preferred for internal data): Use rag_query to search the internal knowledge base
   • Set include_answer: true for AI-synthesized answers
   • Use max_results: 5 for comprehensive retrieval
3. Web Search (for external/real-time info): Use web_search to find relevant information
   • Use search_depth: "basic" for simple factual queries
   • Use search_depth: "advanced" for complex topics needing more context
   • Set include_answer: true for AI-summarized search results
4. Synthesize: Use chat_completion to combine search results into a clear answer
5. Translate (if needed): Use translate_content when the user needs answers in a different language

Rules

• For questions about internal/proprietary data, always try rag_query first
• For questions about real-time or external information, use web_search
• For complex questions, combine both rag_query and web_search, then synthesize with chat_completion
• Always cite sources when presenting information from search
• If the user asks in a non-English language, respond in the same language
• For follow-up questions, build on previous search context

Examples

User: "What does our company policy say about data retention?" → Use rag_query with query="data retention policy", include_answer=true

User: "What is the current market cap of NVIDIA?" → Use web_search with query="NVIDIA current market cap 2026", include_answer=true

User: "Compare our internal ESG metrics with industry benchmarks" → Use rag_query for internal metrics, web_search for industry benchmarks, then chat_completion to synthesize

User: "Translate the search results about AI regulations into Japanese" → First search, then use translate_content with target_lang="ja"