Discover research academic skills, compare source repositories and read the instructions for each workflow.
[23] UNDERSTAND. Consult external AI models when internal sources are exhausted. Build quality prompts using Prompt150 formula (Context + Query + Method + Style). Use when Loop150 exhausts internal sources, nee...
Extracts wine awards from PDF documents. Use when importing competition results, processing wine ratings, or when user mentions "extract awards", "parse awards PDF", "import competition results", or "process wi...
Reads and responds to draft annotations via MCP. Use when user mentions annotations, feedback, or reviewing drafts.
Extract all Fitzgerald quotes from the metaphor analysis essay with chapter references. Use as the first step in the translation pipeline.
Phase 4 of MIP pipeline - Create detailed essay outline with thesis, word budgets, and quote assignments for each section.
Phase 5 of MIP pipeline - Write the full analytical essay following the outline, hitting word targets, and including proper MIP analysis for each quote.
Detect hints about unreleased AI research or capabilities from lab researcher communications. Use when analyzing tweets, posts, or interviews from people at major AI labs to identify signals about upcoming work...
Assess overall hype levels across AI topics by comparing lab researcher enthusiasm against critic skepticism. Use after topic synthesis to identify which topics are overhyped, underhyped, or accurately assessed...
Synthesize claims across multiple sources to identify consensus, disagreements, and emerging narratives on AI research topics. Use when you have claims from both lab researchers and critics on the same topic an...
Extract structured claims, predictions, hints, and opinions from AI research content. Use when processing tweets, blog posts, substacks, or other content from AI researchers to identify substantive assertions a...
Filter and classify AI research content for relevance, topic, and author category. Use for bulk triage of raw content before detailed claim extraction.
Manage Gemini Deep Research API quotas with rate limiting, exponential backoff, and client-side tracking. Use when handling API quota errors, implementing rate limiting, batch job submission, or when asked abou...
Generate evidence-based documentary reports by searching across Brain memory system, .agents/ artifacts, and GitHub issues. Produces investigative journalism-style analysis with full citation chains.
Research external topics, create comprehensive analysis, determine project applicability, and incorporate learnings into Brain memory system. Transforms knowledge into searchable, actionable project context.
使用Tavily API进行网络搜索，获取实时信息、回答问题或研究主题
Expertise in analytically rigorous document critique and editorial review. Use when a user asks to "critique," "review," "edit," or "check the logic" of reports, articles, or briefs, especially those requiring...
Evaluates and judges PEIL-generated prompts for quality and effectiveness. Use when assessing prompt quality, providing feedback on system prompts, rating prompts against criteria, or improving prompt engineeri...
Navigate index.md files generated by the catalogador tool to identify the minimal set of documents or sections to read. Use this skill when exploring directories that contain index.md files, when attempting to...
Fast, lightweight web search and content extraction via Brave Search (HTML scrape). Use for quick lookups, scoping, or lightweight docs/fact checks; optionally pair with exa-search for deep multi-step research...
Deep web research, structured answers, and content retrieval using Exa. Use for heavy research, multi-step synthesis, or rich structured outputs; optionally pair with brave-search for fast scoping but not requi...
Extract entities and concepts from documents using HAIOS memory system. Use when ingesting new documents, analyzing content structure, or populating the knowledge base.
HAIOS Observation Triage Cycle for processing captured observations. Use when scanning archived work items to triage and act on observations. Guides SCAN->TRIAGE->PROMOTE workflow with dimension validation.
HAIOS Investigation Cycle for structured research and discovery. Use when starting or resuming an investigation. Guides HYPOTHESIZE->EXPLORE->CONCLUDE workflow with phase-specific tooling.
Fetch and summarize authoritative external sources into actionable guidance using MCP helpers. EXCLUSIVE to researcher agent.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.