Skill Claude Code
A patent-examiner-style review of a patent application’s claims and description. It examines the application using information about the invention and known prior art.
not rated 2 3mo ago A 50 tokens
copy · 94% MIT
2Stars on the repository
175Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
pixel-art
50Skill Claude Code
A generator for pixel-art SVG illustrations for READMEs, documentation, or slides. SVG is an image format that can be scaled without becoming blurry.
not rated 2 3mo ago A 48 tokens
copy · 100% MIT
Skill Claude Code
A search workflow for finding earlier patents and academic papers related to an invention. Prior art means earlier public work that may affect whether an invention is considered new.
not rated 2 3mo ago A 52 tokens
copy · 100% MIT
Skill Claude Code
A workflow for checking mathematical proofs in LaTeX, finding gaps, fixing the derivations, and reviewing the revised proof again. It also produces an audit report of the checking process.
not rated 2 3mo ago A 90 tokens
original MIT
proof-writer
53Skill Claude Code
A rigorous proof-writing workflow for theorems, lemmas, propositions, and corollaries in machine-learning and AI theory. It can also explain when a claim cannot be proved under its stated assumptions.
not rated 2 3mo ago A 73 tokens
copy · 100% MIT
qzcli
54Skill Claude Code
A command-line tool for managing GPU compute jobs on the Qizhi platform. GPU compute jobs use graphics processors to run demanding workloads such as machine-learning training.
not rated 2 3mo ago A 82 tokens
original MIT
rebuttal
55Skill Claude Code
Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says "rebuttal", "reply to reviewers", "ICML rebuttal", "OpenReview response", or wants to answer external reviews safely.
not rated 2 3mo ago A 73 tokens
original MIT
research-lit
56Skill 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.
not rated 2 3mo ago B 48 tokens
original MIT
Skill Claude CodeCodex needs its repo
An end-to-end workflow for turning a research idea into experiments, reviews, and optionally a finished PDF paper. It connects idea discovery, implementation, automated review, and paper writing.
not rated 2 3mo ago A 83 tokens
original MIT
Skill Claude Code needs its repo
An end-to-end workflow that turns a rough research direction into a focused proposal and a detailed experiment roadmap. It first refines the method, then plans tests tied to the paper’s claims.
not rated 2 3mo ago A 73 tokens
copy · 97% MIT
Skill Claude Code needs its repo
A workflow that turns a rough research direction into a focused, implementation-ready method plan. It keeps the central research problem fixed while refining the technical approach through review.
not rated 2 3mo ago A 101 tokens
copy · 95% MIT
Skill Claude Code
Get a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
not rated 2 3mo ago A 50 tokens
original MIT
Skill Claude Code
A persistent research knowledge base for storing papers, ideas, experiments, and scientific claims and the links between them. It keeps this information across the research project instead of treating each literature search as a separate task.
not rated 2 3mo ago A 73 tokens
copy · 88% MIT
Skill Claude Code
Workflow 5: orchestrate a text-only resubmit of a polished paper to a different venue under hard constraints (no new experiments, no bib edits, no framework changes, never overwrite prior submissions). Phase 0 physical isolation, Phase 0.5 health + anonymity check, Phase 1 audit (proof / claim / citation), Phase 2…
not rated 2 3mo ago A 176 tokens
copy · 94% MIT
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.
not rated 2 3mo ago A 63 tokens
original MIT
Skill Claude Code needs its repo
Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /arxiv (preprints) with citation counts, venue metadata, and TLDR. Use when user says "search semantic scholar", "find IEEE papers", "find journal papers", "venue papers", "citation search", or wants published literature…
not rated 2 3mo ago B 80 tokens
original MIT
Skill Claude Code needs its repo
Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says "modal run", "modal training", "modal inference", "deploy to modal", "need a GPU", "run on modal", "serverless GPU", or needs remote GPU compute.
not rated 2 3mo ago A 79 tokens
copy · 95% MIT
Skill Claude Code
A workflow for writing a complete patent specification from patent claims and an invention disclosure. A patent specification is the detailed description that explains and supports what the claims seek to protect.
not rated 2 3mo ago A 49 tokens
copy · 91% MIT
Skill Claude Code
Profile a target (script, process, GPU, memory, interconnect) using external tools and code instrumentation. Produces structured performance reports with actionable recommendations. Use when user says "profile", "benchmark", "bottleneck", or wants performance analysis.
not rated 2 3mo ago A 54 tokens
copy · 95% MIT
Skill Claude Code
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
not rated 2 3mo ago A 35 tokens
copy · 100% MIT
vast-gpu
69Skill Claude Code needs its repo
Rent, manage, and destroy GPU instances on vast.ai. Use when user says "rent gpu", "vast.ai", "rent a server", "cloud gpu", or needs on-demand GPU without owning hardware.
not rated 2 3mo ago A 46 tokens
copy · 91% MIT
Skill Claude Code
A paragraph-level writing guide for systems research papers aimed at conferences such as OSDI, SOSP, and NSDI. It lays out section sizes, paragraph roles, and patterns for explaining a computer system.
not rated 2 3mo ago A 84 tokens
copy · 98% MIT
Skill Claude Code
Per-page Codex review + targeted python-pptx / Beamer fixes for academic talk slides. Use AFTER /paper-slides (or any externally generated PPTX/Beamer) when the deck looks 'mostly OK' but the user wants a final pass that aligns visual weight with a reference, bumps PPTX fonts to projector-readable size, kills italic…
not rated 2 3mo ago A 136 tokens
copy · 94% MIT
Skill Claude CodeCodex
Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules. Maintains a worklog and snapshots each iteration so revert is real, not symbolic. TRIGGER when the orchestrator delegates Step 5…
not rated 2 3mo ago A 104 tokens
copy · 97% MIT
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: