experiment
01Agent
Experiment agent that implements reproducible baselines and proposed methods, runs controlled local or validated-remote trials, records every run, and promotes formal evidence.
11 3d ago A 32 tokens
original MIT
11Stars on the repository
37Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
figures
02Agent
Figures agent that creates evidence-grounded, editable publication figures and verified exports under figures/.
11 3d ago A 20 tokens
original MIT
Agent
Research Assistant that classifies paper routes, inspects evidence, dispatches specialists including independent Review, acceptance-reviews artifacts, performs authorized remote experiment preflight, and advances within existing authority without creating specialist artifacts or running experiments.
11 3d ago A 48 tokens
original MIT
review
04Agent
Independent source-based reviewer that inspects accepted Markdown and TeX against evidence, writes immutable timestamped reports, and assigns findings to artifact owners without editing specialist sources.
11 3d ago A 34 tokens
original MIT
search
05Agent
Search agent that retrieves candidates, verifies metadata, acquires permitted PDFs, converts readable text, and produces the refpapers material package with a durable per-paper factual handoff.
11 3d ago A 37 tokens
original MIT
writing
06Agent
Writing agent that applies empirical or survey readiness, drafts and revises the authoritative Markdown manuscript, verifies citations, creates LaTeX, and compiles the PDF.
11 3d ago A 34 tokens
original MIT
analyzer
07Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
11 3d ago A 0 tokens
copy · 100% MIT
comparator
08Agent
Compare two outputs WITHOUT knowing which skill produced them.
11 3d ago A 0 tokens
copy · 100% MIT
grader
09Agent
Evaluate expectations against an execution transcript and outputs.
11 3d ago A 0 tokens
copy · 100% MIT