wanshuiyin
Showing 61–82 of 82 skills · Page 2 of 2
wanshuiyin / monitor-experiment
18.5kMonitor running experiments, check progress, collect results
wanshuiyin / paper-write
18.5kDraft LaTeX paper section by section from an outline
wanshuiyin / pixel-art
18.5kGenerate pixel art SVG illustrations for READMEs, docs, or slides
wanshuiyin / arxiv
18.5kSearch, download, and summarize academic papers from arXiv
wanshuiyin / embodiment-description
18.5kWrite detailed embodiment descriptions for patent specifications
wanshuiyin / exa-search
18.5kAI-powered web search via Exa with content extraction
wanshuiyin / jurisdiction-format
18.5kCompile patent application into jurisdiction-specific filing format
wanshuiyin / keenable-search
18.5kKeyless web search and page fetch via Keenable
wanshuiyin / paper-compile
18.5kCompile LaTeX paper to PDF, fix errors, and verify output
wanshuiyin / Auto-claude-code-research-in-sleep
18.7kARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
wanshuiyin / auto-review-loop
18.5kAutonomous multi-round research review loop. In Copilot CLI it defaults to the native complementary rubber-duck subagent with host-event model evidence; elsewhere it uses Codex, while explicit external reviewer overrides remain available.
wanshuiyin / prior-art-search
18.5kSearch patent databases and academic literature for prior art relevant to an invention
wanshuiyin / proof-checker
18.5kRigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (external reviewer backend, ultra reasoning), fixes each gap with full derivations, re-reviews, and generates an audit report
wanshuiyin / claims-drafting
18.5kDraft patent claims for an invention
wanshuiyin / novelty-check
18.5kVerify research idea novelty against recent literature
wanshuiyin / comm-lit-review
18.5kCommunications-domain literature review with Claude-style knowledge-base-first retrieval
wanshuiyin / auto-paper-improvement-loop
18.5kAutonomously improve a generated paper via GPT-6-Astra xhigh review → implement fixes → recompile, for 2 rounds
wanshuiyin / paper-writing
18.5kWorkflow 3: Full paper writing pipeline that goes from a narrative report to a polished, submission-ready PDF
wanshuiyin / proof-writer
18.5kWrites rigorous mathematical proofs for ML/AI theory
wanshuiyin / research-lit
18.5kSearch and analyze research papers, find related work, summarize key ideas
wanshuiyin / patent-novelty-check
18.5kAssess patent novelty and non-obviousness against prior art
wanshuiyin / system-profile
18.5kProfile a target (script, process, GPU, memory, interconnect) for performance analysis