agon
Runs autonomous AI research from a bare topic through literature review, idea refinement and experiments, with agents working in loops so you write no experimental code by hand.
5 skills57
@autoresearch-factoryPlugins
1@autoresearch-factorySkills
5aris
Research-mindset catalog distilled from ARIS skills, for subagent Read on demand.
@autoresearch-factoryarxiv-tools
This skill should be used when the user asks to "search for papers", "get paper info", "download LaTeX source", "generate BibTeX…
@autoresearch-factorynovelty-check
Use when checking novelty of a research idea or proposal. Extract core claims, do multi-source arxiv / Scholar / S2 search, grade…
@autoresearch-factoryserver-health
Use when you need project-specific compute/server notes to pick a server or confirm a running task, if the project has filled its…
@autoresearch-factorysibyl
Research-persona catalog distilled from Sibyl prompts, for subagent Read on demand. 与 ARIS 互补 — ARIS 按阶段组织, Sibyl 按人格视角组织.
@autoresearch-factoryAgents
12deep-lit-reader
AgentRead one arXiv paper in depth, write its wiki note, and emit a deep-lit result JSON.
@autoresearch-factoryenv-validator
AgentCheck whether the system environment satisfies prerequisites for running the research system.
@autoresearch-factoryexperiment-auditor
AgentAudit the latest experiment round's key conclusions, execution consistency, and scientific validity.
@autoresearch-factoryexperiment-coder
AgentImplement, deploy, monitor, sync, and debug experiments from the STATE.md Runs table.
@autoresearch-factoryexperiment-reviewer
AgentReview an experiment workspace to top-conference standards, then write the final verdict and next phase.
@autoresearch-factoryexperiment-scientist
AgentAnalyze experiment results, respond to audits and reviews, update STATE.md, and plan the next experiment round.
@autoresearch-factoryexperiment-screener
AgentScreen experiment plans before implementation, blocking unnecessary scale and meaningless gates.
@autoresearch-factoryidea-creator
AgentResearch a topic landscape, generate and select research ideas, and save them under ideas/.
@autoresearch-factoryidea-refiner
AgentImprove an existing idea using reviewer feedback and write the next idea version.
@autoresearch-factoryidea-reviewer
AgentReview an idea for novelty and quality, write the review, and update its ideas.xml score.
@autoresearch-factoryproposal-refiner
AgentWrite a proposal from an idea, or revise the latest proposal based on a review.
@autoresearch-factoryproposal-reviewer
AgentReview a proposal across multiple dimensions, write the review, and update its proposals.xml score.
@autoresearch-factoryCommands
4deep-lit-tick
CommandRun the scoped deep literature loop until relevant papers are saturated.
@autoresearch-factoryexperiment-tick
CommandOrchestrate the experiment scientist/screener/coder/auditor/reviewer loop for a workspace.
@autoresearch-factoryidea-tick
CommandCreate or continue ideas from a topic and run create/review/refine/deep-lit to dual-gate saturation.
@autoresearch-factoryproposal-tick
CommandRun proposal refine/review/deep-lit loops in parallel until proposals are ready.
@autoresearch-factoryIs this you? Claim your profilePut a plugin at the top of Plugins, from $9