colt-topic-selection
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.
Profile →npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-topic-selection --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# COLT Topic Selection Use this before writing begins. COLT solicits papers on theoretical aspects of machine learning, described in the 2026 CFP (checked 2026-07-08) as a subject at the intersection of computer science, statistics, and applied mathematics, with an explicitly inclusive view that includes theory shedding light on empirical phenomena. The practical bar: the contribution must be a theorem — a rate, a separation, a characterization, a hardness result, or an algorithm whose guarantee is the point. ## The three-question fit test 1. **Is the headline sentence a mathematical statement?** "We prove the first $O(\sqrt{T})$ regret bound for X" is COLT-shaped. "We propose a method that empirically improves X" is not, regardless of how much analysis decorates it. 2. **Would a learning theorist care before seeing experiments?** COLT reviewers evaluate the result on the model's motivation and the bound's strength alone. 3. **Does the proof carry the weight?** If the technique is assembly of known parts, the result must be strong enough to stand without technique credit; if the result is modest, the technique must be the contribution — one of the two must be true. ## Routing table
- The three-question fit test
- Routing table
- The open-problem vehicle
- Scope self-interrogation
- Vignette: three fates for one project
- Common misroutes seen at COLT
- Timing considerations
- Cycle-volatility warnings
- Output format
What does the colt-topic-selection skill do?
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.
How do I install it?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-topic-selection --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Awesome-Journal-Skills, a repository with 909 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.