← 返回 Skills 市场
plagtech

Deep Research

作者 plagtech · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
42
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install deep-research-x402
功能描述
26-tool autonomous research agent — academic papers, arXiv, PubMed, PubChem, Census, web search, and more via x402 micropayments.
使用说明 (SKILL.md)

Deep Research

Autonomous multi-domain research agent with 26 specialized endpoints spanning academic papers, preprints, biomedical literature, chemistry, demographics, and live web search. Each call is a real x402 micropayment ($0.001–$0.03 USDC).

How to call endpoints

Use the helper script for all gateway calls:

bash {baseDir}/scripts/research.sh METHOD ENDPOINT 'JSON_BODY'

GET endpoints pass JSON as query params. POST endpoints send JSON body.

Research workflow

When the user asks you to research a topic, follow this strategy:

  1. Start broad — use web_search or web_qna to get an overview of the topic.
  2. Go deep — based on initial results, call domain-specific tools (papers, preprints, biomedical, chemistry, demographics) for authoritative sources.
  3. Extract details — use web_extract to pull full content from promising URLs found in step 1.
  4. Cross-reference — search the same topic across multiple databases (OpenAlex + Crossref + arXiv) for comprehensive coverage.
  5. Trace citations — use papers_citations or scholarly_citations_count to find influential related work.
  6. Synthesize — combine all findings into a structured, sourced answer.

Be cost-aware. Each call costs real micropayments. Don't make redundant calls, but don't skimp when thoroughness matters.

Always cite sources with DOIs, URLs, PMIDs, or arXiv IDs when available.

Available endpoints (26 tools)

Search & RAG

Web Search — $0.02 Search the live web via Tavily. Returns ranked URLs with snippets.

bash {baseDir}/scripts/research.sh POST /api/v1/search/web '{"query":"ethereum restaking 2026"}'

Web Extract — $0.02 Extract clean readable content from one or more URLs.

bash {baseDir}/scripts/research.sh POST /api/v1/search/extract '{"urls":["https://example.com/article"]}'

Web Q&A — $0.03 Question-answering over fresh web results. RAG out of the box.

bash {baseDir}/scripts/research.sh POST /api/v1/search/qna '{"query":"What is the current state of restaking?"}'

Dictionary

Define — $0.001 Dictionary definition with phonetics and examples.

bash {baseDir}/scripts/research.sh GET /api/v1/research/dictionary/define '{"word":"cryptography"}'

Synonyms — $0.001 Synonyms and antonyms for a word.

bash {baseDir}/scripts/research.sh GET /api/v1/research/dictionary/synonyms '{"word":"decentralized"}'

Phonetics — $0.001 Phonetic transcription and audio URL.

bash {baseDir}/scripts/research.sh GET /api/v1/research/dictionary/phonetics '{"word":"ethereum"}'

Academic Papers (OpenAlex — 250M+ papers)

Papers Search — $0.002 Search academic papers. Returns titles, abstracts, authors, DOIs.

bash {baseDir}/scripts/research.sh GET /api/v1/research/papers/search '{"query":"zero knowledge proofs scalability"}'

Papers by DOI — $0.001 Paper metadata by DOI.

bash {baseDir}/scripts/research.sh GET /api/v1/research/papers/by-doi '{"doi":"10.1038/s41586-021-03819-2"}'

Papers by Author — $0.002 Papers by author name or ORCID.

bash {baseDir}/scripts/research.sh GET /api/v1/research/papers/by-author '{"author":"Vitalik Buterin"}'

Papers Citations — $0.002 Citation graph — cited-by count and references.

bash {baseDir}/scripts/research.sh GET /api/v1/research/papers/citations '{"doi":"10.1038/s41586-021-03819-2"}'

Papers Trending — $0.002 Trending papers by topic in the last N days.

bash {baseDir}/scripts/research.sh GET /api/v1/research/papers/trending '{"topic":"large language models","days":7}'

Preprints (arXiv)

Preprints Search — $0.002 Search arXiv preprints by keyword and category.

bash {baseDir}/scripts/research.sh GET /api/v1/research/preprints/search '{"query":"transformer architectures","category":"cs.AI"}'

Preprints by ID — $0.001 arXiv preprint metadata by ID.

bash {baseDir}/scripts/research.sh GET /api/v1/research/preprints/by-id '{"id":"2301.07041"}'

Preprints Recent — $0.002 Latest arXiv preprints by category.

bash {baseDir}/scripts/research.sh GET /api/v1/research/preprints/recent '{"category":"cs.CR"}'

Scholarly Works (Crossref — 150M+ works)

Scholarly Search — $0.002 Search books, papers, datasets, conference proceedings, and more.

bash {baseDir}/scripts/research.sh GET /api/v1/research/scholarly/search '{"query":"decentralized finance protocols"}'

Scholarly by DOI — $0.001 Full Crossref metadata for any DOI.

bash {baseDir}/scripts/research.sh GET /api/v1/research/scholarly/by-doi '{"doi":"10.1145/3292500.3330647"}'

Scholarly Citations Count — $0.001 Citation count and reference list for a DOI.

bash {baseDir}/scripts/research.sh GET /api/v1/research/scholarly/citations-count '{"doi":"10.1145/3292500.3330647"}'

Scholarly Journal Info — $0.001 Journal metadata by ISSN.

bash {baseDir}/scripts/research.sh GET /api/v1/research/scholarly/journal-info '{"issn":"0028-0836"}'

Chemistry (PubChem)

Compound Lookup — $0.002 PubChem compound by name, formula, or CID.

bash {baseDir}/scripts/research.sh GET /api/v1/research/chemistry/compound '{"query":"aspirin"}'

Similarity Search — $0.002 Find structurally similar compounds.

bash {baseDir}/scripts/research.sh GET /api/v1/research/chemistry/similarity '{"cid":"2244"}'

Bioactivity — $0.002 Biological assay results for a compound.

bash {baseDir}/scripts/research.sh GET /api/v1/research/chemistry/bioactivity '{"cid":"2244"}'

Biomedical (PubMed — 36M+ papers)

Biomedical Search — $0.002 Search biomedical literature across PubMed.

bash {baseDir}/scripts/research.sh GET /api/v1/research/biomedical/search '{"query":"CRISPR gene therapy clinical trials"}'

By PubMed ID — $0.001 Paper metadata by PMID.

bash {baseDir}/scripts/research.sh GET /api/v1/research/biomedical/by-pmid '{"pmid":"33116299"}'

Related Articles — $0.002 Related articles for a PubMed ID.

bash {baseDir}/scripts/research.sh GET /api/v1/research/biomedical/related '{"pmid":"33116299"}'

Demographics

US Census — $0.001 US Census data by state, county, or zip code.

bash {baseDir}/scripts/research.sh GET /api/v1/research/demographics/census '{"location":"California"}'

Data.gov Datasets — $0.001 Search open government datasets by keyword.

bash {baseDir}/scripts/research.sh GET /api/v1/research/demographics/datasets '{"query":"renewable energy production"}'

Research modes

Adapt your strategy based on what the user needs:

Quick — 1-3 calls. Use web_qna for a fast answer, or one domain-specific search if the topic is clearly academic/biomedical/chemical.

Deep — 5-15 calls. Search multiple databases, cross-reference findings, trace citation graphs, extract full articles. Produce a comprehensive report with sections and citations.

Fact-check — 3-7 calls. Start with web_search to find the claim in context, then cross-reference with academic sources. Deliver a clear verdict with evidence.

Compare — 4-10 calls. Research each topic independently across the same databases, then structure findings side-by-side.

Data sources

Data sourced from OpenAlex, Crossref, PubMed, PubChem, arXiv, US Census Bureau, Data.gov, and Tavily.

安全使用建议
Install only if you are comfortable using a paid external research gateway. Treat all queries, URLs, and extracted pages as data that may be sent to the gateway and upstream providers such as Tavily or public research databases. Avoid using it for secrets, private business material, regulated personal data, or sensitive medical/legal/financial details unless you have confirmed the provider and cost controls.
能力标签
cryptofinancial-authorityrequires-walletcan-make-purchasesrequires-paid-servicerequires-sensitive-credentials
能力评估
Purpose & Capability
The skill's purpose is coherent with its behavior: it provides web, academic, biomedical, chemistry, and demographics research through a gateway, and it openly states that calls cost x402 micropayments.
Instruction Scope
The trigger is broad for general research requests, and the workflow can make multiple paid external calls, so users should understand when the skill will be invoked.
Install Mechanism
The artifact consists of SKILL.md plus a small bash helper; metadata declares the required API key, optional gateway URL, and required curl/python3 binaries.
Credentials
Network access, a research API key, and a configurable gateway are proportionate for this research service, but the skill does not prominently warn users to avoid sending confidential or personal data in queries.
Persistence & Privilege
No persistence, background execution, privilege escalation, local indexing, file mutation, or credential-store access was found.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install deep-research-x402
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /deep-research-x402 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
deep-research-x402 v1.0.0 - Initial release of the deep-research autonomous agent. - Supports 26 endpoints across academic, preprint, biomedical, chemistry, demographics, and web domains, all via x402 micropayments. - Includes structured research workflow guidance and research modes (quick, deep, fact-check, compare). - Full endpoint documentation for OpenAlex, arXiv, Crossref, PubMed, PubChem, US Census, Data.gov, and live web. - Requires API key and optionally custom gateway URL; uses bash script interface for all API calls. - Emphasizes cost-awareness and proper citation of authoritative sources.
元数据
Slug deep-research-x402
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Deep Research 是什么?

26-tool autonomous research agent — academic papers, arXiv, PubMed, PubChem, Census, web search, and more via x402 micropayments. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 42 次。

如何安装 Deep Research?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install deep-research-x402」即可一键安装,无需额外配置。

Deep Research 是免费的吗?

是的,Deep Research 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Deep Research 支持哪些平台?

Deep Research 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Deep Research?

由 plagtech(@plagtech)开发并维护,当前版本 v1.0.0。

💬 留言讨论