search▌

AI-powered web search with real-time information and source citations via Perplexity models. \n \n Access five Perplexity models through a single OpenRouter API key, ranging from cost-effective Sonar to advanced Sonar Pro Search for complex multi-step analysis \n Ideal for finding current information beyond model knowledge cutoff, recent scientific literature, clinical trials, and domain-specific research with peer-reviewed sources \n Includes comprehensive query design guidance covering specifi

Search your personal knowledge base to surface relevant past insights, decisions, and solutions. \n \n Proactively searches durable knowledge and conversation history when context suggests prior work would improve the response \n Distinguishes between memory searches ( nmem m search ) for stored breakthroughs and thread searches ( nmem t search ) for exact session history \n Recognizes trigger patterns: user references to prior fixes, resumed features, debugging similarities, requests for ration

Local metasearch engine aggregating results from multiple sources with JSON output and package repository support. \n \n Supports 20+ search categories including general web, Cargo/crates.io, npm, GitHub repositories, IT resources, academic papers, news, images, and videos \n Returns structured JSON with result metadata (title, URL, content, engines, score, publish date) plus answer boxes, suggestions, and infoboxes \n Auto-detects podman or docker, starts SearXNG on localhost:8888 with minimal

Discover existing cloud resources using declarative queries and generate configuration for bulk import into Terraform state.

This skill provides guidance for effectively searching Slack to find messages, files, and information.

Similarity Search Patterns \n Patterns for implementing efficient similarity search in production systems. \n Use this skill when \n \n Building semantic search systems \n Implementing RAG retrieval \n Creating recommendation engines \n Optimizing search latency \n Scaling to millions of vectors \n Combining semantic and keyword search \n \n Do not use this skill when \n \n The task is unrelated to similarity search patterns \n You need a different domain or tool outside this scope \n \n Instruc

Web search using the agent's built-in WebSearch tool, no API key required. \n \n Accepts simple query strings and returns relevant web results; best for current information, recent events, fact verification, and real-time research \n Effective queries benefit from specificity, year inclusion for recency, and domain-specific terminology; iterative refinement recommended for broad or multi-perspective searches \n Results cannot access paywalled content and depend on the agent's WebSearch implement

Search WeChat public account articles by keyword with title, summary, publish time, and source information. \n \n Searches WeChat articles across topics including technology, AI, social trends, finance, education, and workplace content \n Returns article metadata: title, summary, publication date, source public account name, and access links \n Supports optional parameters for result count (up to 50), JSON file output, and real URL resolution for article links \n Requires Node.js with the cheeri

Parallel multi-topic research with independent agents generating structured knowledge bases from any input material. \n \n Launches dedicated research agents for each topic in parallel, each conducting 4–6 rounds of deep retrieval with deduplication checks to avoid keyword overlap \n Accepts three input modes: file-based ( /multi-search @path.md ), direct paste, or explicit topic specification with custom research directions \n Generates structured output with a research overview document, indiv

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.