skyllwtskyllwtCommunity·47 Agent Skills Included

AutoSci

AI research agent that reads, experiments, and writes papers

Automates the full scientific research lifecycle: ingesting papers into a persistent knowledge wiki, generating and validating ideas, designing and running experiments, and drafting LaTeX papers. Eliminates manual literature tracking, scattered notes, and repetitive experiment setup with a memory that compounds across projects. Includes daily arXiv recommendations, novelty checks, cross-model reviews, rebuttal drafting, and poster generation.
npx skills add skyllwt/AutoSci --all -g -y
Available:

Defines the runtime contract for the AI agent: wiki directory layout, wikilink syntax, hard rules on read-only zones and bidirectional links, and where to find schema, templates, and write-permission policies when executing skills.

All Skills in This Repository (47)

Pure Emerald Level Indicators
📦 In Repo
skyllwtskyllwt

research

Orchestrate multi-stage research workflows with resumable progress and asynchronous experiment execution.

Community
Advanced
📦 In Repo
skyllwtskyllwt

/daily-arxiv

Generate daily arXiv paper digests matched to wiki interests.

Community
Advanced
📦 In Repo
skyllwtskyllwt

/init

Orchestrate ΩmegaWiki initialization and parallel paper ingestion from raw sources.

Community
Advanced
📦 In Repo
skyllwtskyllwt

exp-design

Design end-to-end experiment suites with ablation-driven iterative refinement for wiki-based research workflows.

Community
Advanced
📦 In Repo
skyllwtskyllwt

paper-draft

Generate a compilable LaTeX paper from PAPER_PLAN and wiki pages.

Community
Advanced
📦 In Repo
skyllwtskyllwt

/discover

Rank candidate research papers from anchor, topic, wiki, or venue inputs.

Community
Intermediate
📦 In Repo
skyllwtskyllwt

ask

Retrieve and synthesize wiki pages into cited answers for research questions.

Community
Advanced
📦 In Repo
skyllwtskyllwt

/setup

Configure missing Semantic Scholar, DeepXiv, and Review LLM API keys in `.env`.

Community
Advanced
📦 In Repo
skyllwtskyllwt

/exp-pilot-run

Execute pilot experiments from Pilot Spec YAML and return raw metrics.

Community
Advanced
📦 In Repo
skyllwtskyllwt

/exp-status

Check local screen sessions and remote endpoints for experiment status anomalies.

Community
Intermediate
📦 In Repo
skyllwtskyllwt

visualize

Generate Obsidian graph configurations and Canvas knowledge maps from OmegaWiki JSONL data.

Community
Intermediate
📦 In Repo
skyllwtskyllwt

/paper-compile

Compile LaTeX papers with latexmk and generate a submission checklist.

Community
Advanced

Frequently Asked Questions

FAQPage Schema
How to install AutoSci?

Run `npx skills add skyllwt/AutoSci --all -g -y` in your terminal to install all skills in this suite globally.

What does AutoSci do for researchers?

It runs the full research pipeline: ingesting papers into a knowledge wiki, generating and scoring ideas, designing and executing experiments, and drafting submittable LaTeX papers.

Can AutoSci recommend new papers to read?

Yes. The daily-arxiv and discover skills rank fresh arXiv papers and venue proceedings against your existing wiki interests and deliver a personalized shortlist.

Does AutoSci work with Claude Code and Codex?

Yes. The main branch targets Claude Code, and separate preview branches provide Codex and OpenCode adaptations, all driven by the same bilingual skill source.

Do I need coding skills to use AutoSci?

No. You describe your research direction in plain language, and the agent handles paper ingestion, experiment code, and paper writing, asking for your confirmation at key gates.

Related Repositories in Education & Research

View All in Education & Research