Crw Research

Find ALL the arXiv papers that answer a research question, using fastCRW's Firecrawl-compatible Research API. Use when the ask is to survey a literature, enumerate papers on a topic, find what a paper compares against or builds on, list the best models on a benchmark, or recover a paper from a vague description — "papers that do X", "what does X benchmark against", "best open model on Y", "find the paper that ...". Reaches 61.0% recall on the ArXivQA benchmark vs Firecrawl's Research Index 53.3%.

1,268 stars 102 forksResearch & Science Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add fastcrw/crw

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add fastcrw/crw --skill crw-research
Manual install
git clone --depth 1 https://github.com/fastcrw/crw.git /tmp/crw
mkdir -p ~/.claude/skills
cp -r /tmp/crw/skills/crw-research ~/.claude/skills/crw-research

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# fastCRW Research

Find EVERY arXiv paper that answers a research query. Recall = union of arXiv
ids; extra ids never hurt, so cast wide but on-topic. The
[Research API](https://docs.fastcrw.com/research-api) is a live, drop-in
Firecrawl-research-compatible surface — your job is **query strategy + intent
routing**, the endpoints do the retrieval.

This skill reaches 61.0% recall on the 191-question ArXivQA benchmark, a number
fastCRW measured directly. Firecrawl publishes 53.3% for its own Research Index
on the same benchmark in their [Research Index launch
post](https://www.firecrawl.dev/blog/research-index-launch) (2026-06-17): "On
arXivQA, the index hits 53.3% recall at $0.32 per task, against 45.4% for the
next best provider."

Set `FASTCRW_API_KEY` (a `crw_live_…` key from https://fastcrw.com/dashboard).
Base URL `https://api.fastcrw.com`. Every endpoint is a GET; pull arXiv ids out
of `results[].ids.arxiv` / `results[].primaryId`.

```bash
# search: ranked papers for one query
curl -s -H "Authorization: Bearer $FASTCRW_API_KEY" \
  "https://api.fastcrw.com/v1/search/research/papers?query=$(jq -rn --arg q "QUERY" '$q|@uri')&k=40"

# references / citers / similar of a seed paper (citation graph)
curl -s -H "Authorization: Bearer $FASTCRW_API_KEY" \
  "https://api.fastcrw.com/v1/search/research/papers/arxiv:1706.03762/similar?intent=related%20work&mode=references&k=40"
```

## The whole game: classify the query, apply the matching method
Read the full skill on GitHub

Details

Skill name
crw-research
Repository
fastcrw/crw
Path
skills/crw-research/SKILL.md
License
AGPL-3.0
Repo updated
18 November 2026

FAQ

What does the Crw Research skill do?

Find ALL the arXiv papers that answer a research question, using fastCRW's Firecrawl-compatible Research API. Use when the ask is to survey a literature, enumerate papers on a topic, find what a paper compares against or builds on, list the best models on a benchmark, or recover a paper from a vague description — "papers that do X", "what does X benchmark against", "best open model on Y", "find the paper that ...". Reaches 61.0% recall on the ArXivQA benchmark vs Firecrawl's Research Index 53.3%.

How do I install the Crw Research skill?

Claude Code plugin: /plugin marketplace add fastcrw/crw. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Crw Research popular?

It lives in fastcrw/crw, which has 1,268 GitHub stars and 102 forks, and is included in 1 curated skill list.

Related skills

Crw

1.3k

fastcrw/crw

Scrape, crawl, map, and search the web using fastCRW's native /v1 API. Use when the user needs web page content, site-wide extraction, URL discovery, or web search results. Single binary, 14 MB RAM; /v2 exists separately for Firecrawl migration.

Writing & ContentIn 1 list102

Crw

1.3k

fastcrw/crw

Scrape, crawl, map, search, parse, and extract web data with fastCRW — the open-source, self-hostable Firecrawl alternative (single Rust binary, ~14 MB RAM, Firecrawl-compatible /v1 + /v2 API). Use whenever the user needs page content, site-wide extraction, URL discovery, web search, PDF parsing, structured JSON from pages, or change tracking. Also use when the user mentions Firecrawl, Tavily, Crawl4AI, or "scrape/crawl/map/fetch/get the page/read this site/search the web" — crw is a drop-in for the Firecrawl SDKs.

Data & AnalyticsIn 1 list102

Crw Best Practices

1.3k

fastcrw/crw

Reference skill for building production-ready crw integrations. Covers verb selection, call surfaces (CLI/MCP/REST), post-filtering strategies, context-window hygiene, Hybrid RAG patterns, common pitfalls, and crw-specific operational considerations (search backend limits, renderer pool, proxy rotation). Load this when writing application code that embeds crw, designing a multi-step agent workflow, or debugging an integration that isn't behaving as expected.

AI, LLMs & AgentsIn 1 list102

Vibe Check

642

TexasBedouin/vibe-check

Turn a complete beginner's app idea into a buildable plan, then keep them oriented while they build. Use it whenever someone who has never coded wants to build or "vibe code" an app, has an idea but no idea where to start, or wants it turned into a plan, MVP scope, tech stack, user flows, or blueprint. It has three on-ramps: the full journey, a validate-only pass ("is my idea worth building", "reality-check this idea"), and a plan-only path for someone arriving with validation done ("I already validated my idea", "I have the research, just plan my MVP", "skip the research"). Also for someone r

Research & ScienceIn 1 list63

Sw Genre Anatomy

2.1k

jtydhr88/screenwriting-skills

Genre anatomy from John Truby's The Anatomy of Genres (类型解剖 / 类型节拍 / 混合类型 / 超越类型) — genres as beat systems with a life philosophy underneath; three rules (hit every beat of your genre, mix three or four genres, transcend the primary genre), the ladder and families of twelve genres (Horror 恐怖, Action 动作, Myth 神话, Memoir and Coming-of-Age 回忆录与成长, Science Fiction 科幻, Crime 犯罪, Comedy 喜剧, Western 西部, Gangster 黑帮, Fantasy 奇幻, Detective and Thriller 侦探与惊悚, Love 爱情), each with its hero/opponent/world/plot-shape template, beat list, hard rules with failure conditions, subgenres and transcendent paths,

Research & Science220

Market Research

2k

xu-xiang/everything-claude-code-zh

开展市场研究、竞争分析、投资者尽职调查和行业情报收集,提供来源引用和决策导向的总结。适用于用户需要市场规模测算、竞争对手比较、基金研究、技术扫描或为业务决策提供信息支持的研究场景。

Research & Science332

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.