research tool agents

HughYau/AcademicForge

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

HughYau/AcademicForge

Agent

Compare two outputs WITHOUT knowing which skill produced them.

HughYau/AcademicForge

Agent

Evaluate expectations against an execution transcript and outputs.

trapoom555/claude-paperloom

Agent

Extracts atomic, testable findings from a single research paper. Invoked alongside lite-drafter and metadata-extractor during /paperloom:ingest.

trapoom555/claude-paperloom

Agent

Produces a short, triage-grade paper summary — Key Takeaways, Background, Main Idea & Summary, Critique. Invoked alongside metadata-extractor and finding-extractor during /paperloom:ingest. Returns JSON only; page assembly is handled by scripts/assemblepaper.py.

trapoom555/claude-paperloom

Agent

Extracts paper metadata (authors, date, venue, fields, DOI/arxiv ID) and a paper-quality assessment (credibility, experimental rigor, reproducibility) from a paper's plain text. Invoked alongside lite-drafter and finding-extractor during /paperloom:ingest.

EvoClaw/amplify

Agent

Use this agent to review research methodology after experiments. Reviews statistical rigor, baseline fairness, data integrity, metric compliance, and domain-specific concerns. Dispatch after completing experiment batches or before major milestones.

EvoClaw/amplify

Agent

Use this agent to proofread a paper draft. Reviews grammar, style, consistency, flow, terminology, notation, and caption quality. Dispatch after sections are assembled into a full paper draft.

EvoClaw/amplify

Agent

Use this agent to verify research reproducibility. Checks that experiments can be independently reproduced: seeds recorded, environments specified, scripts available, data versioned, raw data untouched.