deep-research

Solid

Multi-phase structured research pipeline with citation tracking, evidence persistence, and knowledge-graph-native output. Use when the user asks for "deep research", "comprehensive analysis", "literature review", "research report", "state of the art on", "structured research pipeline", "multi-source investigation", or wants a citation-tracked report saved to the knowledge graph. Different from a single-pass web-search lookup (quick answers). this skill is for multi-phase work that needs evidence persistence, claim-level verification, and entity cross-references in the knowledge graph. 4 mode tiers (quick / standard / deep / ultradeep) with 3-8 phases each. Outputs to `pages/Research___YYYY-MM-DD___[topic-slug].md` with auto-created `Entity/` and `Source/` cross-link pages.

AI & Automation 3 stars 0 forks Updated today MIT

Install

View on GitHub

Quality Score: 79/100

Stars 20%
20
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Deep Research (knowledge-graph-adapted) Adapted from `199-biotechnologies/claude-deep-research-skill` (upstream Boris Djordjevic, MIT, ~633★). Verdict on upstream: PARK + adapt. the methodology is sound but its install pattern (`git clone main` + `cp -r`) violates the security-first no-unpinned-bootstrap rule (no unpinned bootstrap, no main-branch clones). This file is the in-tree adaptation. no clone, no external script fetching. **Distinguishes from a single-pass web-search skill**: a single-pass search skill is for quick "what's the latest on X" questions. This skill is multi-phase with critique/refine cycles and persistent evidence trails. If the question takes <5min and a single search settles it, route to the single-pass skill. If it takes >10min and needs synthesis across sources, route here. ## Decision tree ``` Request analysis ├── Simple lookup? → STOP: route to a single-pass web-search skill or WebSearch ├── Debugging? → STOP: use standard tools └── Complex multi-source needed → CONTINUE Mode selection ├── Initial exploration → quick (3 phases, 2-5 min) ├── Standard research → standard (6 phases, 5-10 min) [DEFAULT] ├── Critical decision → deep (8 phases, 10-20 min) └── Comprehensive review → ultradeep (8+ phases, 20-45 min) ``` If it's unclear which mode, default to **standard**. Surface the mode pick to the operator in 1 line before starting (e.g. "running standard, will upshift to d...

Details

Author
0xUrsanomics
Repository
0xUrsanomics/utopia-os
Created
5 days ago
Last Updated
today
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category