Recursive Research
Skill Verified ActiveInvestigación recursiva profunda con loop auto-regulado hasta nivel PhD. Aplicable a cualquier dominio (ciencia, tecnología, negocio, arte, humanidades). Usa WDM + Inversión Munger para decisiones autónomas, tiering de fuentes confiables, y checkpointing a disco para sobrevivir límites de contexto.
To empower users to conduct in-depth, expert-level research across any domain, systematically identifying reliable information and knowledge gaps.
Features
- Recursive research up to PhD level
- Auto-regulated research cycles with progress checkpointing
- Transparent source tiering (Tier 1-3, Rejected)
- WDM + Munger Inversion for autonomous decisions
- Proactive context limit management and session resume
- Cross-domain applicability (science, tech, arts, business, humanities)
Use Cases
- Deeply understanding a new subject area
- Preparing technical documents, papers, or studies
- Identifying the state-of-the-art and knowledge gaps in a field
- Performing comprehensive literature reviews
Non-Goals
- Performing simple keyword searches
- Generating creative content without rigorous sourcing
- Replacing direct human expert consultation
- Operating without user guidance on research seeds and parameters
Installation
First, add the marketplace
/plugin marketplace add Anjos2/recursive-research/plugin install recursive-research@recursive-researchQuality Score
VerifiedSimilar Extensions
External Context
100Invoke parallel document-specialist agents for external web searches and documentation lookup
ARA Research Manager
100Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.
Rag Architect
100Use when the user asks to design RAG pipelines, optimize retrieval strategies, choose embedding models, implement vector search, or build knowledge retrieval systems.
Oraclaw Decide
100Decision intelligence for AI agents. Analyze options, map decision dependencies with PageRank, detect when information sources conflict, and find the choices that matter most.
Acquisition Channel Advisor
100Evaluate acquisition channels using unit economics, customer quality, and scalability. Use when deciding whether to scale, test, or kill a growth channel.
Hard Call
100/em -hard-call — Framework for Decisions With No Good Options