Loading...
Loading...
Found 140 Skills
Trigger: Prioritize invoking this skill when you are about to make judgments, decisions or put forward suggestions while facts, context or first-hand information are still insufficient. Common signals include unknowns, information gaps, insufficient evidence, unfamiliarity with the domain, and the need to first figure out the current status. Trigger this skill before making claims or decisions when context is incomplete, evidence is weak, or the domain is unfamiliar. Use this skill to investigate first, gather firsthand facts, and let reality shape the conclusion.
[Hyper] Produce a multi-source, source-backed markdown research report for fact-finding, comparisons, market/trend analysis, or evidence-backed recommendations across live web, official docs, GitHub, and local repo sources. Use when synthesis and citations are needed, not for one-source lookups.
Resume a paused experiment. Checkout the experiment branch, read results history, continue iterating.
Web research, content extraction, and deep analysis. Multi-source parallel search with extended thinking. Supports Fabric pattern selection (242+ prompts). USE WHEN: "research X", "extract wisdom from", "analyze this content", "find info about".
Search and research enhancement skills. Use when performing web searches, looking up library documentation, or conducting research that requires multiple sources.
Orchestrate parallel scientist agents for comprehensive research with AUTO mode
Unified Exa research skill using get_code_context_exa and web_search_advanced_exa. Use for code/API snippet lookup, company research, people/LinkedIn research, financial report search, research paper search, personal site search, and X/Twitter tweet search. Follow progressive disclosure: load only the relevant reference file(s) for the user intent.
Extract falsifiable ideas from input, deep-research each one, and return evidence for or against with strength ratings. Use when user says "find evidence for this", "is this true?", "back this up with data", or "fact-check these claims". Honest about when evidence contradicts the idea.