# 199-biotechnologies/claude-deep-research-skill

Enterprise-grade deep research skill for Claude Code with 8-phase pipeline, source credibility scoring, and automated validation. Outperforms OpenAI, Gemini, and Claude Desktop in quality and verification.

Repository: https://github.com/199-biotechnologies/claude-deep-research-skill
Canonical: https://ross.abutalabs.com/products/claude-deep-research-skill
Language: Python
License Family: other
Last push: 2026-04-11T22:18:08+00:00

## Health v2 (maintenance only)
Score: 51/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 76, release rhythm 35, longevity 21
- inputs: {"age_days": 302, "days_push": 144, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1005, forks 110 (observed 2026-09-01T02:13:53.883742+00:00)

## What it is
A Claude Code skill (plugin) that turns the agent into an enterprise-grade deep research engine with an 8-phase pipeline covering scoping, parallel retrieval, triangulation, synthesis, and critique loop-backs. It produces citation-backed Markdown, HTML, and PDF reports with source credibility scoring and automated citation/hallucination validation.

## Use cases
- deep research a topic and get a citation-backed report
- research the current state of a technology using fresh web sources
- compare two tools or stacks with sourced, verified analysis
- generate executive-style HTML and PDF research reports automatically
- detect hallucinated citations and verify DOI/URL sources in reports
- aggregate searches across Brave, Serper, Exa, Jina, and Firecrawl
- run multi-persona red-team critique over research findings

## When to choose
- You already work in Claude Code and want automated, rigorously cited research reports
- You need long-form reports with validation loops, credibility scoring, and persistent citations that survive context compaction
- You want multi-provider search aggregation with parallel retrieval and sub-agent evidence collection

## When to avoid
- You need a standalone research tool that works without Claude Code, since this is a skill requiring that host
- You want quick one-shot answers; Deep and UltraDeep modes run 10-45 minutes
- Your use is commercial or enterprise and licensing matters, as the repository has no license
- You need general-purpose scraping or data collection rather than LLM-orchestrated research synthesis

## Facets
- artifact type: plugin
- maturity: active
- function: agent-framework, rag, prompt-engineering
- domain: artificial-intelligence, large-language-models
- platform: cli, python, cross-platform
- tags: claude-code, claude-skill, deep-research, research-pipeline, citation-verification, source-credibility-scoring, report-generation, multi-provider-search, hallucination-detection, red-teaming, ai-agents, retrieval-augmented-generation, macos

## Member repositories
- 199-biotechnologies/claude-deep-research-skill (main) score 51

## Provenance
- Observed fields: from GitHub, fetched 2026-09-01T02:13:53.883742+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:16:03.651586+00:00, confidence not recorded.
  - readme: https://github.com/199-biotechnologies/claude-deep-research-skill (fetched 2026-09-01T02:13:53.883742+00:00, sha 672adc94a9a9)
- Data as of 2026-08-30T08:39:29.467469+00:00.