COLT Skills

A 12-skill depth pack for COLT (Conference on Learning Theory) submissions: venue fit for theorem-first papers, CMT submission checks, 12-page PMLR-format discipline, proof appendices, rebuttal strategy, proof-centric reproducibility, related-work positioning across theory communities, numerical illustration norms, workflow, and PMLR camera-ready. Grounded in the COLT 2026 CFP and PMLR proceedings

by @brycewang-stanford 11 skills

Install

npx skillmds@latest add plugin:brycewang-stanford/colt-skills

One command, no setup. In Claude Code it lands as a managed plugin you can enable, disable or remove with /plugin. On any other agent it installs the 11 skills into that agent's own folder.

Or inside Claude Code

In the Plugins tab, add this marketplace:

skillmds/skillmd
/plugin install brycewang-stanford-colt-skills@skillmd

Adds the marketplace once; later plugins need the second line only.

Or install by hand

Download the plugin and unzip its skills/ folder into your agent's skills directory. Works with every agent, no CLI needed.

Download plugin Paths per agent

Just the markdown? SKILL.md files only.

This plugin

skills: 11
authors: 1

Published by a registry member. Review its skills before installing.

Skills in this plugin

▌
Colt Submission · brycewang-stanford
Use when auditing a COLT (Conference on Learning Theory) submission for CMT readiness, the 12-page PMLR-format main body, single-PDF assembly with unlimited appendix, double-anonymous formatting, the parallel-submission ban covering journals and proceedings venues, and the ordered final-week checks before the AoE deadline.

1k repo stars
▌
Colt Experiments · brycewang-stanford
Use when deciding whether a COLT (Conference on Learning Theory) paper needs numerical content at all — COLT has no experiments requirement — and, when numerics genuinely help, designing small illustrative simulations that visualize a proved bound, a separation, or a phase transition without diluting the theory.

1k repo stars
▌
Colt Camera Ready · brycewang-stanford
Use when converting an accepted COLT (Conference on Learning Theory) paper into its PMLR proceedings version, covering de-anonymization, acknowledgements and funding restoration, appendix consolidation into the archival PDF, PMLR volume metadata and BibTeX hygiene, rebuttal-promised edits, and presentation logistics.

1k repo stars
▌
Colt Related Work · brycewang-stanford
Use when positioning a COLT (Conference on Learning Theory) submission against prior bounds and models — building the known-versus-new comparison across COLT/ALT lineage, STOC/FOCS, NeurIPS-and-ICML theory tracks, statistics journals, and arXiv concurrency, while respecting anonymity and the parallel-submission rules.

1k repo stars
▌
Colt Supplementary · brycewang-stanford
Use when structuring the appendix of a COLT (Conference on Learning Theory) submission — the unlimited-length proof appendix inside the single PDF — covering body/appendix splitting for a 12-page limit, theorem restatement discipline, lemma ordering, notation tables, and what referees expect to find where.

1k repo stars
▌
Colt Writing Style · brycewang-stanford
Use when revising a COLT (Conference on Learning Theory) paper for theorem-first exposition — formal setup before results, informal-then-formal theorem statements, proof overviews that sell the technique, quantifier and constant hygiene, and fitting the argument's spine into 12 PMLR-formatted pages.

1k repo stars
▌
Colt Review Process · brycewang-stanford
Use when reasoning about COLT (Conference on Learning Theory) peer review — the double-anonymous-with-informed-area-chair model, correctness-first evaluation by expert theorists, the rebuttal stage before decisions, single-track acceptance stakes, and how PMLR publication and the community's proof culture shape outcomes.

1k repo stars
▌
Colt Author Response · brycewang-stanford
Use when drafting a COLT (Conference on Learning Theory) rebuttal after initial reviews, handling proof-correctness objections, tightness and novelty-of-technique challenges, the area-chair identity-reveal rule, and concession strategy for theorem-first papers where one unrepaired gap outweighs every polished answer.

1k repo stars
▌
Colt Reproducibility · brycewang-stanford
Use when strengthening the reproducibility of a COLT (Conference on Learning Theory) paper, where reproducing means re-deriving — complete proofs, explicit assumptions, tracked constants, correctly invoked external results, self-contained notation — plus seeds and scripts for any numerical illustration the paper carries.

1k repo stars
▌
Colt Topic Selection · brycewang-stanford
Use when deciding whether a result is COLT-shaped (Conference on Learning Theory) — a theorem-first learning-theory contribution — versus better routed to ALT, STOC/FOCS, NeurIPS/ICML/AISTATS, JMLR, or a statistics journal, and whether the right vehicle is a full paper or a COLT open-problem piece.

1k repo stars
▌
Colt Artifact Evaluation · brycewang-stanford
Use when deciding what evidence package a COLT (Conference on Learning Theory) paper needs, given that COLT runs no artifact-evaluation track or badges — the proof appendix is the artifact. Covers proof-verification passes, optional code companions for numerics, formalization aids, and post-acceptance release of scripts.

1k repo stars