Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
ClaudSkillsAuthors › wangyi0403

wangyi0403

@wangyi0403 on GitHub →

14 Claude Code skills authored by wangyi0403.

updated 2026-05-23 · showing 1–14 of 14 by quality score

Average Pro QualityScore: 67.6/100

For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.

Audit paper drafts for logical consistency, compliance, and academic integrity (Triangulation Matrix).
Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental…
Scaffold a PyTorch Lightning project for classification, regression, or timeseries research. Triggers on "新建项目", "initialize project", "scaffold", "create PL project".
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…
Get a deep critical review of research from Claude via claude-review MCP. Use when user says \"review my research\", \"help me review\", \"get external review\", or wants critical…
Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Codex-supervised…
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…
Generate and rank research ideas given a broad direction. Use when user says \"\u627eidea\", \"brainstorm ideas\", \"generate research ideas\", \"what can we work on\", or wants…
Verify research idea novelty against recent literature. Use when user says \"查新\", \"novelty check\", \"有没有人做过\", \"check novelty\", or wants to verify a research idea is novel…
Workflow 1: Full idea discovery pipeline. Orchestrates research-lit \u2192 idea-creator \u2192 novelty-check \u2192 research-review to go from a broad research direction to…
Use when experiments complete to judge what claims the results support, what they do not, and what evidence is still missing.
Autonomous multi-round research review loop. Repeatedly reviews using Claude Code via claude-review MCP, implements fixes, and re-reviews until positive assessment or max rounds…
Deploy and run ML experiments on local or remote GPU servers. Use when user says \"run experiment\", \"deploy to server\", \"\u8dd1\u5b9e\u9a8c\", or needs to launch training jobs.
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review.
Search all 14 skills by wangyi0403 →