# Research Agents

> A Claude skill from rpatrik96/research-agora.

- **Type:** Skill
- **Install:** `agentstack add skill-rpatrik96-research-agora-research-agents`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [rpatrik96](https://agentstack.voostack.com/s/rpatrik96)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [rpatrik96](https://github.com/rpatrik96)
- **Source:** https://github.com/rpatrik96/research-agora/tree/main/plugins/research-agents
- **Website:** https://rpatrik96.github.io/research-agora/

## Install

```sh
agentstack add skill-rpatrik96-research-agora-research-agents
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Research Agents

Specialized research analysis agents for critical thinking, evidence verification, synthesis, and parallel paper analysis.

## Features

- **Parallel Execution**: Fan-out/fan-in pattern for 2-3x speedup on large papers
- **Research State**: Structured JSON intermediate representation for caching
- **Evidence Hierarchy**: L1-L6 evidence grading with venue-specific standards

## Components

### Agents (14)
- `claim-auditor` - Verify all paper claims systematically
- `devils-advocate` - Adversarial analysis of arguments
- `evidence-checker` - Verify evidence backing claims
- `perspective-synthesizer` - Synthesize multiple viewpoints
- `audience-checker` - Evaluate audience alignment
- `clarity-optimizer` - Improve writing readability
- `figure-storyteller` - Assess figure narratives
- `latex-debugger` - Debug LaTeX compilation errors
- `statistical-validator` - Verify statistical rigor
- `artifact-packager` - Prepare code/data for release
- `reviewer-response-generator` - Generate rebuttals
- `co-author-sync` - Multi-author coordination
- `discussion-monitor` - Track citations and discussions
- `state-generator` - Generate research-state.json

### Micro-Skills (8)
Atomic, parallelizable operations for paper analysis.

### Orchestrators (2)
- `parallel-audit` - Parallel claim verification
- `parallel-review` - Comprehensive multi-perspective review

### Helpers (3)
- `batch-arxiv` - Batched arXiv searches
- `prefetch-evidence` - Pre-fetch evidence
- `context-compactor` - Compress context for efficiency

## Installation

```bash
/plugin install research-agents@research-agora
```

## License

MIT

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [rpatrik96](https://github.com/rpatrik96)
- **Source:** [rpatrik96/research-agora](https://github.com/rpatrik96/research-agora)
- **License:** MIT
- **Homepage:** https://rpatrik96.github.io/research-agora/

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-rpatrik96-research-agora-research-agents
- Seller: https://agentstack.voostack.com/s/rpatrik96
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.
