論文

Use xAI Grok API with Agent Tools for real-time web and X (Twitter) search and synthesis. Requires XAI_API_KEY.

Developer reporting skill for work documentation and communication. Use when writing journals, devlogs, status updates (22A/22B), progress reports, or documenting development work. Generates reports from git history or manual input.

Use when encountering any bug, test failure, or unexpected behavior - IMMEDIATELY enter on first error. Four-phase framework (basic checks, root cause, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

Initialize session as ORCHESTRATOR agent with multi-agent coordination capability. Use for complex tasks requiring parallel agent spawning and result synthesis.

Conduct user research and validation. Use when discovering user needs, validating assumptions, creating personas, or understanding pain points. Covers interviews, surveys, analysis, and synthesis.

Synthesizes research findings into coherent narratives with uncertainty quantification. Use when integrating findings from multiple sources, creating research summaries, drawing conclusions from evidence, or communicating research results. Triggers on phrases like "synthesize", "integrate findings", "what's the conclusion", "summarize research", "overall picture", "bring together".

Invoke deep sequential thinking for complex problem-solving. Use when the user says 'use ultrathink', 'ultrathink', or when tackling problems that require careful step-by-step reasoning, planning, hypothesis generation, or multi-step analysis.

Use Perplexity Sonar API for real-time, citation-backed answers. Ideal for up-to-date information and quick synthesis. Requires PERPLEXITY_API_KEY

Find web content similar to a given URL using AI-powered similarity matching. Use when you have an example page and want to discover related articles, papers, or websites with similar content, style, or topic.

Synthesize research findings for OAK planning using the oak.plan-research workflow. Use when consolidating findings from codebase exploration, comparing approaches, or creating research/*.md documents.

Auto-applies MECE/BFO framework (thesis, Mermaid TD/LR, numbered sections, Ground Truth) to ANY .md file creation.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

Validates messaging consistency across website, GitHub repositories, and local documentation. Generates comprehensive read-only discrepancy reports showing where messaging conflicts or inconsistencies exist. Activates when user mentions "consistency check", "validate documentation", "check for mixed messaging", "audit content consistency", or before updating internal paperwork.

Use when encountering any bug, test failure, or unexpected behavior (including race conditions, deadlocks, concurrency issues) - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) with specialized techniques for deep call stack tracing and concurrency debugging

Help with paper references using paperpipe (papi). Use when user asks about papers, wants to verify code against a paper, needs paper context for implementation, or asks about equations/methods from literature.

Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields.

Search the web for content matching a query with AI-powered semantic search. Use for finding relevant web pages, research papers, news articles, code repositories, or any web content by meaning rather than just keywords.

Generate answers to questions with structured output using AI search and synthesis. Use when you need factual answers with citations from web sources, or when you want to extract specific structured information in response to a query.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

Hypothesis-driven hunt plan for suspicious PowerShell, plus query snippets for common telemetry.