claudegoodies
Plugin

deep-research

From alirezarezvani

Disciplined, multi-source meta-research for high-stakes questions — the heavyweight alternative to the fast research router. Runs a 9-phase pipeline (reframe into falsifiable hypotheses → genre/blocks → plan → capability discovery → parallel sub-agent fan-out → score & triangulate → synthesize + adversarial pass → verify → refresh targets), triangulates every thesis against >=3 independent, differently-typed sources, saves each source to its own file with verbatim quotes, and never fabricates a citation. Output is an auditable, reusable folder with a delta-update refresh protocol. Use when a wrong answer is expensive: strategy, comparing N options, hypothesis validation, mapping a field.

Runs a 9-phase research pipeline that triangulates each hypothesis against 3+ independent sources and outputs an auditable folder.

Use it when

  • Comparing multiple strategic options where a wrong answer is costly
  • Validating a hypothesis before committing to it
  • Mapping an unfamiliar field with a source catalog and citations
  • Needing a reusable research output with delta-update refresh

Skip it if

  • Need a quick answer — this is the heavyweight alternative to a faster research router
  • Multi-source triangulation and parallel sub-agent fan-out adds overhead for simple questions
  • Relies on an external upstream catalog (references/full-catalog.md) for source coverage

Install

/plugin install deep-research

Facts

Repository
alirezarezvani/claude-skills
Status
Actively maintained
Last commit
Source file
research/deep-research/.claude-plugin/plugin.json

Source preview

The instructions Claude Code reads when this plugin runs.

{
  "name": "deep-research",
  "description": "Disciplined, multi-source meta-research for high-stakes questions — the heavyweight alternative to the fast research router. Runs a 9-phase pipeline (reframe into falsifiable hypotheses → genre/blocks → plan → capability discovery → parallel sub-agent fan-out → score & triangulate → synthesize + adversarial pass → verify → refresh targets), triangulates every thesis against >=3 independent, differently-typed sources, saves each source to its own file with verbatim quotes, and never fabricates a citation. Output is an auditable, reusable folder with a delta-update refresh protocol. Use when a wrong answer is expensive: strategy, comparing N options, hypothesis validation, mapping a field.",
  "version": "2.10.3",
  "author": {
    "name": "Alireza Rezvani",
    "url": "https://alirezarezvani.com"
  },
  "homepage": "https://github.com/alirezarezvani/claude-skills/tree/main/research/deep-research",
  "repository": "https://github.com/alirezarezvani/claude-skills",
  "license": "MIT",
  "skills": [
    "./skills/deep-research"
  ],
  "attribution": {
    "contributed_by": "Socialpranker (https://github.com/Socialpranker), PR #851",
    "upstream": "https://github.com/Socialpranker/claude-deep-research — the continuously-maintained source catalog (29 channels, 460+ statistical sources, 39 validated APIs, 103 report blocks) referenced f
View full source on GitHub →

Other plugins