research-agents

Use this agent to prepare ML code/data/models for public release with comprehensive checklists. Activates when asked to "package artifacts", "prepare release", "reproducibility checklist", "code release", or "prepare camera ready".

Use this agent to evaluate papers, presentations, posters, or communications for target audience alignment. Impersonates different reader personas (reviewers, industry engineers, students, experts) to identify jargon, unclear explanations, and narrative gaps.

Analyze convergence rates, complexity bounds, and approximation guarantees. The theoretical analogue of statistical-validator. Compares to known optimal rates and checks dimensional consistency. Trigger: "analyze bounds", "check convergence rate", "verify complexity", "bounds analysis".

Deep verify ALL paper claims with systematic evidence hierarchy. NOW SUPPORTS PARALLEL MODE via parallel-audit orchestrator for 2-3x speedup. Activates when asked to "audit claims", "verify claims", "check paper claims", "claim verification", "evidence check", "verify evidence", or "quick evidence scan". Includes Quick Mode for rapid brainstorming checks.

Use this agent to map blog posts or essays into book structure. Activates when asked to "audit my content", "blog to book", "cluster my posts", "content audit", or "find themes across posts". Performs thematic clustering, gap analysis, and generates book conversion strategies from dispersed content.

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