Agent Claude Code
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.
Agent Claude Code
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.
Agent Claude Code
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.
Command Claude Code
Design method/analysis framework with evaluation protocol and story line.
Command Claude Code
Start a new research project — identifies domain, research type, and anchors expert persona.
Command Claude Code
Execute experiments following the frozen plan with discipline enforcement.
Command Claude Code
Write research paper with LaTeX modular structure and senior-level writing.
Cursor rule Cursor
Amplify bootstrap — activates a structured scientific research workflow with 24 skills, 4 gates, and discipline enforcement. Loaded automatically for every session.
Skill Claude CodeCodex
Use when analyzing results in Type D or Type H projects before making mechanistic or causal claims — requires systematic exclusion of confounders, batch effects, technical noise, and other alternative explanations.
Skill Claude CodeCodex
Use when designing the analysis framework for a discovery or data analysis project — defines story line, analysis dimensions, sufficiency criteria, and alternative explanations to check.
Skill Claude CodeCodex
Use when Phase 4 (experiment execution) begins — enforces complete reporting of all seeds, all results, and all failures; remains active until project end; prevents selective reporting of favorable outcomes.
Skill Claude CodeCodex
Use when integrating results into a paper or drafting any paper section — enforces that every claim maps to specific evidence before it can be written.
Skill Claude CodeCodex
Use when facing 2+ independent experiments or tasks that can be worked on without shared state or sequential dependencies.
Skill Claude CodeCodex
Use when a user describes ANY research intent, goal, or topic — this is Phase 0 and must complete before any other research skill activates.
Skill Claude CodeCodex
Use when designing the evaluation protocol for a method development project — locks primary metrics, datasets, seeds, statistical tests, and baseline list into an immutable contract.
Skill Claude CodeCodex
Use when G2 (plan freeze) and G3 (execution readiness) gates have passed — handles all implementation, baseline reproduction, experimentation, and iteration for both Type M and Type D projects; this is Phase 4.
Skill Claude CodeCodex
Use whenever generating figures or tables for a research paper — enforces publication-quality visual standards including style consistency, readability, accessibility, and venue-appropriate formatting.
Skill Claude CodeCodex
Use when research direction is validated (G1 passed) and the project needs method design, analysis framework, evaluation protocol, or story line — this is Phase 3 and must complete before any code or experiments.
Skill Claude CodeCodex
Use when evaluation metrics, protocol, datasets, or splits have been confirmed in the research plan — enforces immutability of locked evaluation components without explicit user authorization.
Skill Claude CodeCodex
Reusable protocol for multi-agent discussions that iterate until convergence. Used by results-integration (Phase 5) and paper-writing (Phase 6) to ensure discussions actually resolve issues rather than just noting them.
Skill Claude CodeCodex
Use when assessing innovation level of a research contribution — invoked after literature review (Phase 1) and after method design (Phase 3) to verify that novelty matches the target venue tier.
Skill Claude CodeCodex
Use when and ONLY when the user explicitly requests paper writing and G4 (write-ready) gate has passed — handles LaTeX structure, senior-level writing, reference verification, and iterative refinement.
Skill Claude CodeCodex
Use when 3 consecutive core experiments or optimizations fail to meet expectations — forces honest status assessment and escalates the pivot/downgrade/kill decision to the user.
Skill Claude CodeCodex
Use when Phase 1 (research-direction-exploration) is complete and G1 gate has passed — subjects the research problem to adversarial defense-style questioning, classifies project intent, re-evaluates venue target, and produces a final feasibility ruling before any method design begins.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: