Research skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

researching-on-the-internet

Use when planning features and need current API docs, library patterns, or external knowledge; when testing hypotheses about technology choices or claims; when verifying assumptions before design decisions - gathers well-sourced, current information from the internet to inform technical decisions

241 repo starsObserved in 2 repos
Research

equity-research-core

Run Mira's core single-equity research workflow across fundamentals, financial quality, macro context, technical pricing, events, and thesis framing.

241 repo starsObserved in 1 repos
Research

etf-listing-discovery

Discover listed, pending, filed, or newly announced ETFs and create a structured candidate watchlist for ETF listing analysis.

241 repo starsObserved in 1 repos
Research

sec-filing-analysis

Analyze SEC disclosures for lightweight fact supplements or deep filing reviews, including source gaps, accounting quality, and thesis-relevant deltas.

241 repo starsObserved in 1 repos
Research

hydraide

Conceptual and educational explanations of HydrAIDE — how the engine works internally, why it is designed the way it is, what Swamp lifecycle, addressing, query engine, msgpack patch, subscriptions, locking, and the storage engine actually do under the hood. Use when the user asks "how does X work", "why does HydrAIDE do Y", "explain the architecture of Z", or wants to understand concepts (not write implementation code). For Go SDK code, use the `hydraidego` skill. For server operations, use the `hydraidectl` skill.

239 repo starsObserved in 1 repos
Research

page-analysis

Analyze web page content, structure, and layout to understand what a page contains and how it is organized. Trigger when the user asks to: analyze a page, understand page structure, inspect a website, summarize page content, examine page layout, review a web page, or describe what is on a page.

235 repo starsObserved in 2 repos
Research

multi-ai-research

Parallel multi-AI cross-validation research workflow (大版本). Dispatch N internal sub-agents + grok + gemini in parallel, automatically cross-validate findings, tier by confidence (strong consensus / partial / conflict / insufficient), generate tiered action items with arbitration. Use when user says "多 AI 调研", "交叉验证", "独立共识", "三脑调研", "multi-ai research", "parallel research", "cross-validate", or needs deep research that benefits from internal data + external 2026 consensus. NOT for quick factual Q&A, pure code reasoning, or tasks needing deep project context.

234 repo starsObserved in 2 repos
Research

behavioral-analysis

Political psychology, cognitive biases, group dynamics, leadership analysis, decision-making patterns for Swedish political intelligence

233 repo starsObserved in 1 repos
Research

electoral-analysis

Election forecasting models, campaign analysis, coalition prediction, voter behavior analysis for Swedish elections

233 repo starsObserved in 1 repos
Research