Research skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
theorem-proving
Construct and verify mathematical proofs using LaTeX typesetting and computational verification via jupyter_execute. Use when the user asks to prove a theorem, verify a mathematical argument, construct a formal proof, or check proof correctness computationally.
tavily-usage
This skill should be used when user asks to "search the web", "fetch content from URL", "extract page content", "use Tavily search", "scrape this website", "get information from this link", or "web search for X".
blind-spot-pass
Use *before* starting work in a domain you don't know well, to surface the "unknown unknowns" — the things you don't even know to ask about — and learn just enough to prompt and decide well. Implements the "blind spot pass" pattern from Anthropic's Fable "finding your unknowns" field guide. Triggers when you say "I'm new to this", "I don't know what to ask", "teach me before we start", "blind spot pass", "unknown unknowns", "find my unknowns", or the Korean "내가 뭘 모르는지 알려줘" / "이 분야 처음인데" / "먼저 가르쳐줘" / "블라인드 스팟", or when you hand off a task while admitting you're a non-expert in that field (color grading, video editing, legal, tax, finance, design, an unfamiliar codebase, etc.). Do NOT use for simple factual questions, domains you already know, or directly-actionable work — answer those directly or route to planner / architect.
source-explorer
Read a product's source code and build a plain-language summary of its public surface — flags, options, API endpoints, states, defaults, and constraints. Stays interactive so writers can ask follow-up questions about how the product works before writing or auditing docs. Consumes the same manifest as docs-drift but produces no structured output and runs no diff. Use when a writer wants to understand an unfamiliar codebase, calibrate a new docs-drift manifest, or answer "what does this flag actually do?" questions. Trigger phrases: "explore the source", "understand the source for X", "summarize the codebase", "explain the source surface", "what does X's source do", "source summary for X".
eino-guide
Eino framework overview, concepts, and navigation. Use when a user asks general questions about Eino, needs help getting started, wants to understand the architecture, or is unsure which Eino skill to use. Eino is a Go framework for building LLM applications with components, orchestration graphs, and an agent development kit.
stats-integrity
Use whenever you run statistical analysis for the social sciences (regression, hypothesis tests, econometrics) or read Stata (.dta) / SPSS (.sav) data in this workspace. Enforces an execute-don't-interpret boundary (surface estimates, don't volunteer causal claims), checks the analysis against a preregistration plan for HARKing, verifies reproducible seeds, and reproduces .dta/.sav estimates via R. Flags integrity risks; never certifies the analysis is sound.
analyzing-malware-family-relationships-with-malpedia
Use the Malpedia platform and API to research malware family relationships, track variant evolution, link families to threat actors, and integrate YARA rules for detection across malware lineages.
idea-check
Pre-build reality check. Scans GitHub, HN, npm, PyPI, and Product Hunt for existing competitors before you build. Use when starting a new project, evaluating a side project idea, or doing a build-vs-buy decision.