deep-researcher
Skill1 starsChanged 49 days agoApache-2.0View on GitHub
Investigasi mendalam multi-sumber, triangulasi data faktual (Rule of 3), pembongkaran release notes/changelog resmi, dan verifikasi silang (cross-verification) sebelum mengambil keputusan teknis, arsitektural, atau akademis. Mengekstrak informasi berdensitas tinggi dari dokumentasi resmi, RFC, paper ilmiah, dan repositori open-source.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- Karanjot786/agent-skills-clitheir own version, first seen Oct 13, 2026
- yasdelayu/agent-x-cctheir own version, first seen Oct 13, 2026
- nimbalyst/skillstheir own version, first seen Feb 16, 2026
- JohnJBoren/claude-skills-ecosystemtheir own version, first seen Dec 26, 2025
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- Karanjot786/agent-skills-cli★ 182same name
- nimbalyst/skills★ 28same name
- JohnJBoren/claude-skills-ecosystem★ 2same name
- yasdelayu/agent-x-cc★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- min-tokSkill
- academic-scholarSkill
- agent-mcp-craftSkill
- anti-overengineeringSkill
- api-security-reviewerSkill
- data-verifySkill
- design-no-slopSkill
- enterprise-teamSkill
- git-craftSkill
- human-codingSkill
- laravel-architectSkill
- markdown-docSkill
- modern-stack-horizonSkill
- modern-web-guidanceSkill
- omni-pilotSkill
- perf-benchmarkSkill
- python-bug-fixerSkill
- react-ui-architectSkill
- reverse-engineer-anythingSkill
- typescript-nodeSkill
- tyw-auditSkill
The file
Files
Deep Researcher (Triangulasi Fakta & Investigasi Multi-Sumber)
Skill ini memandu agen untuk melakukan riset komprehensif, kritis, dan berbasis data faktual—menghilangkan ketergantungan pada artikel opini dangkal, forum usang, atau halusinasi token AI.
1. Hukum Triangulasi Fakta (The Rule of 3)
Sebelum menyatakan sebuah fakta teknis baru, statistik, atau kesimpulan analitis sebagai kebenaran mutlak:
- Wajib Diverifikasi oleh Minimal 3 Sumber Independen Berbeda:
- Sumber Primer 1: Dokumentasi resmi, RFC, spesifikasi standar, atau rilis repositori resmi (GitHub Releases).
- Sumber Primer 2: Artikel teknis dari insinyur utama, benchmark resmi, atau commit log upstream.
- Sumber Pendukung: Artikel peer-reviewed, diskusi issue tracker terverifikasi, atau panduan arsitektur kredibel.
- Jika ketiga sumber memberikan data yang bertentangan, paparkan kontradiksi tersebut secara transparan ("Sumber A menyatakan X karena pertimbangan Y, sedangkan Sumber B menyatakan Z").
2. Alur Investigasi Dokumen & Repository
Ketika menyelidiki masalah kompleks atau update teknologi:
Langkah 1: Penelusuran Hulu (Upstream Source Tracing)
- Jangan hanya membaca tutorial sekunder di Medium atau dev.to.
- Lacak langsung repositori resminya di GitHub.
- Periksa
CHANGELOG.md,releases, atauissue trackeruntuk melihat breaking changes dan migration guides yang sebenarnya.
Langkah 2: Ekstraksi Dokumen Padat (High-Density Extraction)
- Gunakan
search_webuntuk menemukan URL dokumentasi resmi yang paling relevan. - Gunakan
read_url_contentuntuk menyedot konten mentah tanpa markup iklan atau noise UI. - Ekstrak bagian spesifik: nama fungsi, parameter, tipe data return, dan contoh implementasi minimum.
Langkah 3: Sintesis & Verifikasi Kausal (Causal Synthesis)
- Pahami mengapa teknologi atau metode tersebut diubah (causal rationale).
- Jelaskan keuntungan performa, implikasi keamanan, dan potensi breaking changes bagi sistem yang ada.
3. Gaya Laporan Riset (Zero Marketing Fluff)
Laporan riset harus to-the-point, padat data, dan bebas basa-basi:
- Tabel Perbandingan Obyektif: Membandingkan metrik kuantitatif (latensi, bundle size, footprint memori, dukungan runtime).
- Kutipan & Tautan Sumber: Setiap klaim teknis penting wajib menyertakan link sumber rujukan resmi.
- Rekomendasi Aksi Konkret: Berikan rekomendasi langkah demi langkah (actionable steps) berdasarkan hasil temuan.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.