Research skills

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

sift-kg

Use sift-kg as an AI second brain — a persistent knowledge graph your agent operates from across sessions. Use proactively at session start to orient, when answering questions about the user's projects or domain, when generating ideas or suggestions, when user asks "what do I know about X", "how does X connect to Y", "find connections", "what should I work on", "give me ideas", or when you need to understand the structure of the user's knowledge. Not needed for one-off document analysis — sift's CLI commands work fine on their own for that.

661 repo starsObserved in 1 repos

Research

quantitative-research

量化因子研究、数据清洗与对齐、Alpha 评估（IC/IR）、过拟合与稳健性检验。在用户讨论因子挖掘、截面/时序信号、机器学习特征或量化研报框架时启用。

657 repo starsObserved in 1 repos

Research

openloomi-feature-guide

Use this when users ask about openloomi features, capabilities, or how to use it. Examples: 'openloomi 怎么用', '你能做什么', 'What can you do?', 'How does openloomi work?', 'Tell me about openloomi features', 'What platforms does openloomi support?', 'How do I use scheduled tasks?', 'What is Insights system?', 'How do I connect Telegram?', 'How to create automation?', '什么是 openloomi 事件?'

656 repo starsObserved in 1 repos

Research

audience-intelligence

Research target audiences. Use when: buyer personas, segmentation, Jobs-to-Be-Done, psychographic profiling, audience deep-dive.

652 repo starsObserved in 2 repos

Research

crawlberg

Crawl, scrape, and convert websites to Markdown using the local crawlberg CLI and its MCP server. Use when the user wants to fetch a page, follow links across a domain, enumerate URLs, or drive a real browser. Covers installation, the subcommands (scrape, crawl, map, interact, batch-scrape, batch-crawl, download, citations, version, mcp, serve), output formats (JSON + Markdown), browser fallback, and when to prefer the MCP server over shelling out.

652 repo starsObserved in 2 repos

Research

crawling-a-site

Use when the user wants to follow links across a domain and capture every reachable page as Markdown. Covers `crawlberg crawl` with depth, page caps, concurrency, rate limiting, domain scoping, robots, and output selection.

652 repo starsObserved in 2 repos

Research

headless-fallback

Use when a static fetch returns nothing useful and the page needs a real browser. Covers `--browser-mode auto|always|never`, external CDP via `--browser-endpoint`, symptoms of JS-only pages and WAF blocks, and the performance cost.

652 repo starsObserved in 2 repos

Research

nullcost-search

MUST use for developer provider discovery involving free tier, free trial, cheap, pricing, hosting, Node, Next.js, auth, Postgres, database, email API, SaaS stacks, GPU compute, remote MCP endpoints, APIs, or low setup friction. Auto-trigger for normal discovery questions and explicit `/nullcost-search`. Do not use for domains, registrars, TLDs, or exact domain availability.

652 repo starsObserved in 2 repos

Research

panews-web-viewer

Read public PANews website pages as Markdown. Use for homepage, article-page, and column-page reads.

652 repo starsObserved in 2 repos

Research

research-briefing

Build a focused literature and citation briefing from PapersFlow. Use when the user wants paper search, citation verification, related-paper discovery, or citation graph exploration.

652 repo starsObserved in 2 repos

Research