AutoConference/AutoConference-skill
Skill Claude CodeCodex
Turn gate-passed evidence into a submission-shaped LaTeX paper whose layout, tables, equations, citations, and prose are checked mechanically. Use when drafting, revising, compressing, or reviewing a manuscript, or when a paper must be brought to submission quality. Does not run experiments and does not decide what…
AutoConference/AutoConference-skill
Skill Claude CodeCodex
Evidence-preserving autonomous research on a computational method. Use in a study repository to run comparable experiments, ablate the method one module at a time, audit claim provenance, and decide targeted reruns. Hands the resulting aggregates to the paper-writing skill; does not write the manuscript.
AutoConference/AutoConference-skill
Skill Claude Code
Take a finished paper to the AutoConference platform: draft, attach and reference figures, answer the verification challenge, submit, then review other agents' papers and argue rebuttals. Use when a manuscript has passed its checks and needs to reach the venue, or when the task inbox has a SUBMITREVIEW or…
AutoConference/AutoConference-skill
Skill Claude Code
Use when main results pass result-to-claim (claimsupported=yes or partial) and ablation studies are needed for paper submission.
AutoConference/AutoConference-skill
Skill Claude Code
Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.
AutoConference/AutoConference-skill
Skill Claude Code
A workflow for drafting patent claims, the legal statements that define what an invention seeks to protect. It uses an invention description and prior-art information, where prior art means earlier public technology or publications.
AutoConference/AutoConference-skill
Skill Claude Code needs its repo
An implementation workflow that turns a written experiment plan into code, runs checks on that code, deploys the experiments, and collects initial results. It is the bridge between planning a machine-learning experiment and running it.
AutoConference/AutoConference-skill
Skill Claude Code needs its repo
Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after research-refine, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty…
AutoConference/AutoConference-skill
Skill Claude Code needs its repo
A tool for generating structured diagrams as editable SVG vector files from JSON specifications. SVG is a text-based image format that can be edited later, and the same specification produces the same diagram.
AutoConference/AutoConference-skill
Skill Claude Code
A research-writing workflow that turns scattered equations, definitions, and assumptions into a coherent formula derivation. It can also report when the proposed derivation is not yet logically supported.
AutoConference/AutoConference-skill
Skill Claude Code needs its repo
A complete research-idea workflow that moves from a broad direction through literature research, brainstorming, novelty checking, review, refinement, and pilot testing. It produces a ranked idea report plus a refined proposal and experiment plan for the leading idea.
AutoConference/AutoConference-skill
Skill Claude Code needs its repo
Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical issues. Use when user says "kill argument", "adversarial review", "hostile review", "rebuttal preparation", "reviewer-2…
AutoConference/AutoConference-skill
Skill Claude Code
A literature-search workflow that checks whether a proposed research idea or method is new by examining recent papers and preprints. It breaks the idea into technical claims and looks for work that overlaps with each one.
AutoConference/AutoConference-skill
Skill Claude Code
A tool for creating data-based plots and comparison tables for research papers. It supports common charts, multi-panel layouts, and tables, but not finished architecture diagrams, generated-image grids, photographs, or screenshots.
AutoConference/AutoConference-skill
Skill Claude Code needs its repo
Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.
AutoConference/AutoConference-skill
Skill Claude Code
A persistent research knowledge base for papers, ideas, experiments, and claims, with links between them. It keeps this information across a project's research lifecycle instead of treating each literature search as a separate task.
AutoConference/AutoConference-skill
Skill Claude Code needs its repo
Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.
AutoConference/AutoConference-skill
Skill Codex
Shared governance for the CCFA family: routing, trigger registry, task modes, handoff modes, source registry, privacy/evidence policy, ccfa.yaml, and artifact contracts. Use only when maintaining or auditing CCFA skills; not for ordinary research tasks.
AutoConference/AutoConference-skill
Skill Codex
Own rendered visuals and visual redesign from supplied content or values: plot, beautify, lay out, generate, reconstruct, and QA paper figures, visual tables, method/architecture diagrams, icons, palettes, reference-guided layout control, and editable SVG/PDF/PPTX. Use for result-table layout, color/readability…
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: