Plugin Claude Code
Plugin marketplace listing 1 plugin: ml-intern.
3 14d ago A
tokens not measured
original MIT
ml-intern
02Plugin Claude Code
Paper-grounded ML research and open-problem attack for Claude Code. Crawls arXiv and citation graphs, reads whole papers in parallel subagents, mechanically verifies every quote, archives a model's real code locally and grounds later sessions in it, and runs falsifiable attacks on hard unsolved problems.
3 14d ago A
tokens not measured
original MIT
huggingface
03MCP server Claude CodeCodexCursor +2
MCP server "huggingface", hosted remotely at huggingface.co, as configured in infiniV/ultra-ml-intern.
3 14d ago A
tokens not measured
original MIT
Agent
Single-paper deep reader. Fetches ONE paper's full text to disk and reads it directly, returning a digest in which every quoted line is text copied out of the file and every section reference is a heading that exists in it. Designed for parallel fan-out from /ml-research-ultra, isolating a paper's full text from the…
3 14d ago A 93 tokens
original MIT
Agent
ML literature crawler. Use when the main task needs a methodology-grounded recipe drawn from multiple papers — e.g., "find the best recipe for math reasoning fine-tuning", "what dataset and method does the GRPO follow-up work use", "literature review for sparse-attention long-context training". Returns a structured…
3 14d ago A 108 tokens
original MIT
Command
Deep literature crawl. Many query angles, 2-hop citation graph, full-text paper reads in parallel subagents, cross-paper synthesis grounded in verified quotes.
3 14d ago A 31 tokens
original MIT
ml-research
07Command
Run a literature review for an ML task — finds landmark paper, crawls citation graph, extracts recipe.
3 14d ago B 21 tokens
original MIT
grounding
08Skill Claude CodeCodex
Use before writing, reviewing, or debugging any code that uses a specific ML model (DINOv3, SAM 2, Whisper, Qwen3-Embedding, SigLIP 2…), whenever a model-provenance archive for it exists locally. Loads that archive's real source — checkpoint ids, API signatures, preprocessing constants, training recipe — so the code…
3 14d ago A 147 tokens
original MIT
ml-intern
09Skill Claude CodeCodex
Use when the user wants ML literature grounded in actual papers — a landmark paper for a task, a citation-graph crawl, an extracted training recipe (dataset + method + hyperparameters + reported metric), a field survey, or a gap to advance current work. Triggers include "literature review for X", "best recipe for X"…
3 14d ago B 131 tokens
original MIT
Skill Claude CodeCodex
Use when the user names a specific ML model (e.g. DINOv3, SAM 2, Whisper, Qwen2-VL) and wants its real/official code, training recipe, or papers found, verified, or archived locally for grounded coding. Triggers include "find the real code for this model", "harvest DINOv3", "store the model's code and papers locally"…
3 14d ago B 134 tokens
original MIT
open-problem
11Skill Claude CodeCodex
Use when the user points at a hard, unsolved, or open problem in any field — mathematics, physics, biology, ML, engineering — and wants a real attack on it. Runs a sustained multi-agent assault: establishes the state of play from primary sources, hunts for the two literatures nobody has combined, generates and kills…
3 14d ago A 141 tokens
original MIT