academic-scientific-research

Temukan, saring, dan sintesis makalah akademis, literatur ilmiah, laporan teknis, pracetak, publikasi klinis atau biomedis, dan bukti seputar…

npx skills add https://github.com/tavily-ai/use-case-skills --skill academic-scientific-research

Academic Scientific Research

Workflow

Use search to discover scholarly sources, extract to verify source content, map or crawl for known scholarly sites and collections, and research for full literature-review synthesis. Keep this skill focused on research planning, source selection, extraction targets, and evidence synthesis; execution mechanics should come from companion endpoint skills.

Treat the guidance below as base guidance; adapt it to the user's request when appropriate.

  • Translate the user's question into search terms, synonyms, key entities, and likely source domains.
  • Break broad questions into short subqueries under 400 characters: core concept, synonyms, method names, target population or data, benchmark or dataset, author/lab, and year range.
  • Prefer scholarly and official sources when available: preprint servers, PubMed/NIH pages, journals, conference proceedings, professional societies, standards bodies, and official technical reports.
  • Extract from the strongest selected pages after screening titles, snippets, source type, recency, and relevance.
  • Reserve broad research synthesis for full literature reviews, research landscapes, or multi-method comparisons.
  • Distinguish primary studies, review papers, preprints, editorials, guidelines, standards, and news coverage.

Research Budget

  • Start with a small focused search set covering the main concept, synonyms, methods, and source type.
  • Extract only the strongest scholarly sources before drafting the evidence brief.
  • Add more searches only for named gaps, such as missing review papers, missing recent work, or missing primary studies.
  • Do not use map unless a known lab, journal, conference, repository, or documentation site has buried pages.
  • Do not use crawl unless the user needs broad collection from a known proceedings, publication list, or docs section.

Capability Guidance

  • Use search first when the user needs papers, methods, benchmarks, authors, institutions, or recent work.
  • Use extract when comparing a small set of papers, reading abstracts, or verifying study claims.
  • Use map only when a known lab, journal, conference, repository, or documentation site has useful but hard-to-find pages.
  • Use crawl only when the user needs many pages from a known source, such as proceedings, a lab publication list, or a technical docs section.
  • Use research only when the user explicitly needs a full literature review or research landscape.

Query And Source Guidance

  • Pair formal terms with common synonyms and acronyms.
  • Include population, dataset, benchmark, organism, intervention, model, metric, or method terms when relevant.
  • For recent literature, include explicit year ranges or recency language in the query.
  • Prefer primary literature for claims, review papers for landscape summaries, and guidelines/standards for practice recommendations.
  • Deduplicate preprints and final publications; cite the final version when available.
  • Treat abstracts, papers, supplemental pages, tables, and official repositories as separate evidence surfaces.
  • Report failed or inaccessible sources when they affect key papers, guidelines, datasets, or primary evidence.

Output Template

Use this markdown structure and adapt sections to the user's scope:

# Evidence Brief: <topic>

## Research Question
<brief framing of the question>

## Search Strategy
- Concepts searched:
- Source types prioritized:
- Inclusion logic:
- Exclusions or limitations:

## Key Sources
| Source | Type | Why it matters | URL |
| --- | --- | --- | --- |

## Findings
### <Theme>
- Claim:
- Evidence:
- Limitations:

### <Theme>
- Claim:
- Evidence:
- Limitations:

## Consensus And Disagreement
- Consensus:
- Disagreement:
- Evidence gaps:

## Follow-Up Queries
- <query idea>

For medical, clinical, or biomedical topics, be conservative: do not provide diagnosis or treatment advice, and prioritize primary literature, systematic reviews, guidelines, and official health sources.

Lebih banyak skill dari tavily-ai

crawl
tavily-ai
Ekstrak dan simpan konten situs web sebagai file markdown untuk akses dan analisis offline. Mendukung kedalaman crawl yang dapat dikonfigurasi (1-5 level), batas luas, dan batas halaman untuk menyeimbangkan cakupan dengan kinerja. Termasuk pemfilteran jalur melalui pola regex untuk fokus pada bagian tertentu dan mengecualikan konten yang tidak relevan. Menawarkan dua mode: ekstraksi halaman penuh untuk pengumpulan data, atau pemotongan semantik dengan instruksi bahasa alami untuk memasukkan hasil ke dalam konteks LLM. Menyediakan API Peta pendamping untuk URL...
extract
tavily-ai
Ekstrak konten bersih dari URL tertentu menggunakan API ekstraksi Tavily. Mendukung hingga 20 URL per permintaan dengan peringkat ulang berbasis kueri opsional untuk fokus pada potongan konten yang relevan. Dua mode ekstraksi: dasar untuk ekstraksi teks cepat, lanjutan untuk halaman yang dirender JavaScript dan data terstruktur. Otentikasi OAuth otomatis melalui browser pada saat pertama kali dijalankan, atau konfigurasi kunci API manual di pengaturan. Mengembalikan format markdown atau teks biasa dengan URL gambar opsional dan batas waktu yang dapat dikonfigurasi hingga 60 detik.
investment-research-briefs
tavily-ai
Buat ringkasan riset investasi yang ringkas, memo perusahaan, gambaran sektor, pembaruan pemantauan portofolio, ringkasan laba/berita, ringkasan risiko dan katalis,…
product-competitor-intelligence
tavily-ai
Riset produk pesaing, SKU, harga, kemasan, positioning, perbandingan fitur, katalog produk, halaman kategori, daftar pengecer, marketplace…
research
tavily-ai
We need to translate the given English text into Bahasa Indonesia. The instruction says to preserve product names, protocol names, URLs, numbers, and technical terms. The name "research" is to be preserved if it appears in the source text, but we are not to include the name unless it appears. The source text does not contain the word "research" as a standalone name? Actually it starts with "Comprehensive research on any topic..." so "research" is part of the text. But the instruction says "Do not include the name unless it appears in the source text." So we keep it as is. Also preserve "Tavily MCP server", "OAuth", etc. Translate the rest naturally. Let me translate: "Comprehensive research on any topic with automatic source gathering, analysis, and citations." -> "Riset komprehensif tentang topik apa pun dengan pengumpulan sumber, analisis, dan kutipan otomatis." "Conducts multi-source web research with explicit citations, ideal for comparisons, current events, market analysis, and detailed reports
sales-account-intelligence
tavily-ai
Bangun intelijen akun yang siap penjualan untuk perusahaan, prospek, pelanggan, mitra, dan pembeli target. Gunakan saat pengguna meminta persiapan penjualan, ringkasan akun,…
search
tavily-ai
Pencarian web dengan hasil yang dioptimalkan untuk LLM, penilaian relevansi, dan penyaringan fleksibel. Mendukung empat mode kedalaman pencarian (ultra-cepat, cepat, dasar, lanjutan) dengan pengaturan latensi dan tradeoff relevansi yang dapat dikonfigurasi. Termasuk penyaringan domain, batasan rentang waktu, rentang tanggal, penguatan negara, dan ekstraksi konten mentah. Mengembalikan hasil dengan judul, URL, cuplikan konten, dan skor relevansi; hasil gambar opsional dan favicon. Otentikasi OAuth otomatis melalui server Tavily MCP atau konfigurasi kunci API;...
tavily-best-practices
tavily-ai
API pencarian web untuk LLM dengan akses data real-time, ekstraksi konten, perayapan situs, dan riset bertenaga AI. Lima metode inti: search() untuk hasil web, extract() untuk konten URL, crawl() untuk ekstraksi seluruh situs, map() untuk penemuan URL, dan research() untuk sintesis AI ujung-ke-ujung. Mendukung SDK Python dan JavaScript dengan klien asinkron untuk kueri paralel dan kedalaman pencarian yang dapat dikonfigurasi (ultra-cepat/cepat/dasar/lanjutan). Metode crawl menerima instruksi semantik untuk memfokuskan ekstraksi pada...