Skill Claude CodeCodex
Automate browser interactions, test web pages and work with Playwright tests.
11 2d ago A 19 tokens
copy · 100% MIT
Skill Claude CodeCodex
Use when an empirical paper task will run on one SSH server and the Research Assistant must prepare and verify its remote workspace before dispatching Experiment.
11 2d ago B 34 tokens
original MIT
Skill Claude CodeCodex
Use when Writing must assess, draft, revise, or audit an empirical ML/AI method paper whose claims depend on experiment-record.md and results/, including baseline fairness, multi-seed reporting, ablations, formula-rich methods, result tables, citation verification, and derived submission artifacts. Do not use its…
11 2d ago A 164 tokens
original MIT
Skill Claude CodeCodex
Use when the Research Assistant must classify and orchestrate a multi-stage paper request, continue an existing project from exact-cwd artifacts, choose between survey, empirical, or hybrid routes, acceptance-review specialist handoffs, or decide whether missing authority, access, evidence, cost, or safety requires a…
11 2d ago A 66 tokens
original MIT
Skill Claude CodeCodex
Use when Figures must create or audit a data-driven scientific chart, uncertainty or missing-data display, multi-panel plot, accessible palette, provenance manifest, or publication export rather than a Draw.io diagram.
11 2d ago A 45 tokens
original MIT
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
11 2d ago A 64 tokens
copy · 88% MIT
analyzer
31Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
11 2d ago A 0 tokens
copy · 100% MIT
comparator
32Agent
Compare two outputs WITHOUT knowing which skill produced them.
11 2d ago A 0 tokens
copy · 100% MIT
grader
33Agent
Evaluate expectations against an execution transcript and outputs.
11 2d ago A 0 tokens
copy · 100% MIT
Skill Claude CodeCodex
Use when a bundled specialist is about to finish a normal run or continuation and must leave a durable, inspectable handoff for its immediate caller.
11 2d ago A 34 tokens
original MIT
Skill Claude CodeCodex
Use when Experiment must work through a Research Assistant-verified SSH connection and exact-cwd experimentssh mount.
11 2d ago A 26 tokens
original MIT
Skill Claude CodeCodex
Use when Experiment must justify sample size, minimum detectable effect, precision, sensitivity, clustering or attrition inflation, or simulation-based power before formal evidence collection.
11 2d ago A 35 tokens
original MIT
Skill Claude CodeCodex
Use when Writing must assess, outline, draft, revise, or complete a survey, review, tutorial, or literature-synthesis paper from a verified multi-paper material package, especially when the contribution is a taxonomy, comparative synthesis, coverage map, or research agenda rather than a new experimentally evaluated…
11 2d ago A 63 tokens
original MIT