research
Use for any research request that doesn't clearly match a research specialist ('research X', 'look into Y'). Routes with classifier.py to pulse, grants, litreview, syllabus, patent, dossier or deepread, or runs its own cited search.
Target: Learning & research. Automatically collected · unverified.
Excerpt from the author’s documentation
Extracted from a fixed version of SKILL.md in its original language. This is the author’s documentation; installation, compatibility and runtime results have not been verified by this site.
Read the original English text
Topics in the source
- Research — Hybrid Router + Fallback
- Portability
- Distinct From engineering/autoresearch-agent
- Hybrid Architecture (C)
- Specialist Registry
- Agent Integrity Rules
- Phase 1: Grill-Me Intake (2–4 Questions)
- Q1 (always) — Research question
The runtime orchestrator for the research domain. Architecture C: deterministic classification → specialist delegation OR own plan-decompose-search-synthesize-cite workflow. Requires WebSearch + WebFetch for the fallback workflow; specialist skills (pulse, grants, litreview, syllabus, patent, dossier, deepread) must be present for delegation to work. Node.js with docx package required if Q2 = document mode. Works in Claude Code CLI natively. In Claude.ai with web tools + Code Execution, the workflow is supported. These two skills share the word "research" but serve completely different use cases: research/research/ (this skill) — research-query router + fallback workflow ("Research X") engineering/autoresearch-agent/ — Karpathy's autonomous file-optimization experiment loop ("Make this code faster") No overlap. They coexist. Every invocation produces one of three outcomes: 1. Delegation — Classified as specialist-domain. Routes there. User sees the specialist's output. 2. Fallback execution — Classified as general research. Runs own plan → search → synthesize workflow. 3. Clarification request — Classification ambiguous OR a single bare-noun signal matched. Asks one forcing questio
This is an excerpt. Refer to the complete source and its current requirements.
- Source repository
- alirezarezvani/claude-skills
- Source file
- research/research/skills/research/SKILL.md
- Fixed revision
- 8f082544116fc0d014188e521ca40304cdfc86b0
Requirements
- Only the author’s Skill metadata is included. Read the full instructions to check dependencies, licensing and conditions of use.
A small first task
先阅读原作者说明，再决定是否在自己的 AI 工具中使用。
Instructions for your AI tool
- Claude Desktop: resource-specific guide not available yet
- Claude Code: resource-specific guide not available yet
- Cursor: resource-specific guide not available yet
- Codex: resource-specific guide not available yet
Author documentation is not live verification by this site. Without evidence, we do not mark a resource as compatible, safe or free.
Sources and evidence
This record was collected automatically. Its documentation, suitability and runtime behavior have not been manually verified.
Author: alirezarezvani/claude-skills · original repository metadata. Documentation review: Not reviewed. Last source check: 2026-11-09T14:01:47.597Z.
Categories are inferred from names, descriptions and paths. They do not establish compatibility.
License and attribution
MIT. Third-party content and copyright remain with their authors. Refer to the original license and terms.
Original license ↗Synchronization, copying and user-reported success do not mark a resource as runtime-tested.
Limitations and notes
- Collecting metadata does not mean this site has installed, adapted, runtime-tested or security-reviewed the resource.