Peer Review
spacering-net/codeg
Structured manuscript/grant review with checklist-based evaluation.
A skill your agent uses when reasoning about COLT (Conference on Learning Theory) peer review — the double-anonymous-with-informed-area-chair model, correctness-first evaluation by expert theorists…
Install Colt Review Process
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-review-process -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills colt-review-process --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/COLT-Skills/skills/colt-review-process .claude/skills/colt-review-process && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "colt-review-process" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-review-process into .claude/skills/colt-review-process/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "colt-review-process", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-review-processType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-review-process -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills colt-review-process --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/COLT-Skills/skills/colt-review-process .agents/skills/colt-review-process && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "colt-review-process" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-review-process into .agents/skills/colt-review-process/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "colt-review-process", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-review-process -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills colt-review-process --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/COLT-Skills/skills/colt-review-process .cursor/skills/colt-review-process && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "colt-review-process" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-review-process into .cursor/skills/colt-review-process/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "colt-review-process", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/brycewang-stanford/Awesome-Journal-Skills.git --path COLT-Skills/skills/colt-review-process--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-review-process -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills colt-review-process --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/COLT-Skills/skills/colt-review-process .gemini/skills/colt-review-process && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "colt-review-process" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-review-process into .gemini/skills/colt-review-process/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "colt-review-process", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills colt-review-processInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-review-process -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/COLT-Skills/skills/colt-review-process .github/skills/colt-review-process && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "colt-review-process" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-review-process into .github/skills/colt-review-process/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "colt-review-process", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-review-process -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills colt-review-process --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/COLT-Skills/skills/colt-review-process .opencode/skills/colt-review-process && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "colt-review-process" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-review-process into .opencode/skills/colt-review-process/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "colt-review-process", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
colt-review-process- GitHub stars
- 1.2k
- Token cost
- ~1.7k tokens
- SKILL.md length
- 819 words
- Files
- 1
- Skills in repo
- 2,387
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when reasoning about COLT (Conference on Learning Theory) peer review — the double-anonymous-with-informed-area-chair model, correctness-first evaluation by expert theorists…
- Reasoning about COLT (Conference on Learning Theory) peer review — the double-anonymous-with-informed-area-chair model
- SKILL.md covers The 2026 pipeline, Who reviews a COLT paper, What the scores actually track and Decision dynamics, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Correctness-first evaluation by expert theorists
What it does
Colt Review Process is an agent skill from brycewang-stanford/Awesome-Journal-Skills. 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.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Research & Science, covering Peer review. The repository describes itself as: Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. ｜ 覆盖主流期刊的… The licence is MIT.
When your agent uses it
- 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
Example prompts
- “/colt-review-process”
What it can do on your machine
Read from SKILL.md and the folder at commit 932eb23. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Colt Review Process loads about 1.7k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 819 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from brycewang-stanford/Awesome-Journal-Skills at commit 932eb23, republished under its MIT licence (© brycewang-stanford). 819 words, ~1,739 tokens.
Download SKILL.mdSave it as
.claude/skills/colt-review-process/SKILL.md (or your agent's skills folder).- name
- colt-review-process
- description
- 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.
COLT Review Process
Use this to plan around COLT's review pipeline. Process facts below were verified against the COLT 2026 CFP on 2026-07-08; mechanics are re-decided by each edition's program chairs, so reconfirm in the cycle you are in.
The 2026 pipeline
- Submission via Microsoft CMT by February 4, 2026 (AoE) for the 39th edition.
- Double-anonymous refereeing with a twist: reviewers do not see author names, but the area chair handling the paper does, and may reveal identities to a reviewer during the rebuttal period on request when needed for a proper review.
- Initial reviews go to authors before decisions; a rebuttal window follows.
- Accepted papers appear in PMLR (v291 carried COLT 2025; the 2026 volume number is assigned at publication).
- COLT is run by the Association for Computational Learning, with program chairs rotating yearly; the 2026 chair names were not published in a form verifiable at the access date (待核实 — check learningtheory.org/colt2026/).
Who reviews a COLT paper
The pool is learning theorists: statistical learning, online learning and bandits, optimization theory, RL theory, privacy, and adjacent CS theory. Practical consequences:
- Expect at least one reviewer working within epsilon of your subfield who will actually verify proofs, not skim them.
- "Standard techniques" claims get adjudicated by people who know the standard techniques' exact reach — bluffing about novelty of technique fails here faster than anywhere else in ML.
- Empirical framing earns nothing by itself; a reviewer may value an illustrative experiment, but no reviewer will accept one in lieu of a proof.
What the scores actually track
| Dimension | Raises it | Sinks it |
|---|---|---|
| Correctness | Complete proofs, tracked constants, checked external results | One irreparable gap — usually terminal regardless of other strengths |
| Significance | Resolving a known open question; improving a known rate; a clean new model | A bound in a model nobody asked about, unmotivated |
| Novelty of technique | An argument that visibly cannot be assembled from known parts | A reduction the reviewer completes in the margin |
| Tightness / completeness | Matching upper and lower bounds; explicit regime coverage | Upper bound only, gap to the known lower bound unexamined |
| Clarity | Formal setup early, roadmap per proof, stable notation | Definitions scattered; appendix required to parse the theorem |
Decision dynamics
- One sustained correctness objection outweighs any number of enthusiasm points; the AC's first job is deciding whether the proofs close.
- Because the AC knows author identities, arguments in rebuttal should stand on mathematics alone — appeals to seniority or track record are visible and land badly.
- Significance disputes ("who cares about this model?") are where rebuttals genuinely move decisions: a crisp paragraph tying the model to a named prior line, an open problem, or an empirical phenomenon can flip a fence-sitter.
- COLT is single-track and relatively small; acceptance implies your talk enters the entire community's field of view, and the bar reflects that.
- Some editions have used an "accept with minor revisions verified by the AC" flavor of shepherding for fixable issues; whether the current cycle does is announced with decisions (待核实).
Show full SKILL.md (328 more words)Show less
Reading a COLT review
Review anatomy — where the decision signal lives:
1. Summary paragraph -> did the reviewer parse the model correctly?
If not, your rebuttal's first job is the misread.
2. "Detailed comments" -> line-numbered proof remarks; each is a verification
trace. Silence about App. C means C was not read.
3. Questions to authors -> the actual decision hinges; answer these first.
4. Typo list -> free labor; acknowledge briefly, fix silently.Reviews that engage deeply with the proofs are good news even when negative — the paper was taken seriously, and precise objections are answerable. The dangerous review is the short, high-level one; it signals the significance case never landed, and that is a framing problem the rebuttal must solve.
After the decision: reading the outcome
- Accept: the reviews still matter — camera-ready promises made in rebuttal are
expected in the final PDF, and the AC may check (
colt-camera-readykeeps the ledger). - Reject with proof-level reviews: you received a free verification report from three experts. Patch the mathematics, then choose between the next COLT, ALT (the same community's sister venue, roughly anti-phased deadline), or a journal if the fixed version grew.
- Reject with significance objections only: the theorems survived; the framing died. Rebuild the known-vs-new ledger and the model-motivation paragraph before resubmitting anywhere — the same reviewers may see it again in a small community.
- Reject you believe is wrong: there is no formal appeals process to rely on; the productive channel is a stronger paper, since the community re-reviews resubmissions on their mathematics.
Confidentiality and conduct
- Submissions are confidential; reviewers may not use or share the results before publication.
- COLT publishes a code of conduct for participants (a 2026 page exists at learningtheory.org); professional-conduct expectations extend to the rebuttal tone.
- Reviewer conflicts run through CMT domain and coauthor declarations — enter them completely, since the informed-AC model depends on accurate conflict data.
- Discussing your submission publicly (talks, social media) during review is not forbidden by anonymity rules aimed at reviewers, but volume-seeking publicity during the review window is poor form in a community this small.
Cycle-volatility warnings
- Portal, anonymity mechanics, rebuttal format, shepherding, and decision timeline are annual decisions. Decision dates for 2026 were not on the pages checked (待核实).
- Reviewer-volunteering expectations for submitting authors have not been a stated COLT policy in the verified material; do not assume one either way without the current CFP.
Output format
[Stage] pre-submission / under review / rebuttal / decision
[Score driver] correctness / significance / technique / tightness / clarity
[Reviewer engagement] deep proof-level / shallow-summary (framing failed)
[Rebuttal leverage] <the one thread that can move the decision>
[Process facts to reconfirm] <current-cycle items still 待核实>© brycewang-stanford, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in COLT-Skills/skills/colt-review-process of brycewang-stanford/Awesome-Journal-Skills.
Open the folder on GitHubat commit 932eb23
Compare with similar skills
Colt Review Process next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Colt Review Process this skillbrycewang-stanford/Awesome-Journal-Skills | 1.2k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Peer Reviewspacering-net/codeg | 3.9k | 17 repos | ~5.9k | Automated safety check: Notes | MIT | |
| Scholar Evaluationspacering-net/codeg | 3.9k | 11 repos | ~3.2k | Automated safety check: Pass | MIT | |
| Academic Paper Writing PipelineImbad0202/academic-research-skills | 51k | — | ~16k | Automated safety check: Pass | Custom licence | |
| Academic Paper ReviewerImbad0202/academic-research-skills | 51k | — | ~11k | Automated safety check: Pass | Custom licence | |
| Peer ReviewK-Dense-AI/claude-scientific-writer | 2.4k | 2 repos | ~3.1k | Automated safety check: Notes | MIT |
Similar skills
Scholar Evaluation
spacering-net/codeg
Systematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem formulation, methodology, analysis, and…
Academic Paper Writing Pipeline
Imbad0202/academic-research-skills
Runs a 12-agent pipeline that plans, drafts, cites, reviews and formats academic papers, with modes for revision, rebuttals, abstracts and citation checks.
Academic Paper Reviewer
Imbad0202/academic-research-skills
Simulates a journal peer review of a manuscript with a five-seat reviewer panel, an editorial synthesizer and several review modes.
Peer Review
K-Dense-AI/claude-scientific-writer
Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments.
Academic Research Pipeline
Imbad0202/academic-research-skills
Orchestrates a ten-stage academic workflow from research to finished manuscript, including integrity checks, two rounds of peer review and revision.
More from brycewang-stanford/Awesome-Journal-Skills
All 2,387 skills in this repoAaag Data Analysis
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when running and reporting the analysis for an Annals of the American Association of Geographers manuscript — spatial statistics and modeling, remote-sensing accuracy, or…
Aaag Literature Positioning
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when positioning an Annals of the American Association of Geographers manuscript in the literature — engaging geographic scholarship across the relevant area and the…
Aaag Rebuttal
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when responding to an Annals of the American Association of Geographers decision letter (major/minor revision) — building a point-by-point response to the subject editor and…
Aaag Research Design
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when defending the research design of an Annals of the American Association of Geographers manuscript — spatial/quantitative analysis and GIScience, remote-sensing and…
Aaag Review Process
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when you need to understand how the Annals of the American Association of Geographers evaluates a manuscript — double-anonymous review routed through a subject editor by…
Aaag Submission
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when running the final pre-submission preflight for the Annals of the American Association of Geographers via ScholarOne Manuscripts — area/article-type selection…
Related
Categories
Questions about Colt Review Process
What does Colt Review Process do?
A skill your agent uses when reasoning about COLT (Conference on Learning Theory) peer review — the double-anonymous-with-informed-area-chair model, correctness-first evaluation by expert theorists…. Colt Review Process is an agent skill from brycewang-stanford/Awesome-Journal-Skills. 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.
When should I use Colt Review Process?
Colt Review Process fits situations like: 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.
How do I install Colt Review Process in Claude Code?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-review-process -a claude-code`. Or copy the skill folder (COLT-Skills/skills/colt-review-process in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/colt-review-process in your project. Claude Code loads it when a task matches its description.
How do I install Colt Review Process in Codex?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-review-process -a codex`. Or copy the skill folder (COLT-Skills/skills/colt-review-process in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/colt-review-process in your project. Codex loads it when a task matches its description.
Can I use Colt Review Process in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-review-process -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/colt-review-process, .gemini/skills/colt-review-process, .github/skills/colt-review-process and .opencode/skills/colt-review-process in your project.
What does Colt Review Process need to run?
SKILL.md names no scripts, command-line tools or credentials: Colt Review Process is instructions for the agent only.
Does Colt Review Process access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Colt Review Process safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Colt Review Process use?
Colt Review Process is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Colt Review Process use?
About 1.7k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Colt Review Process?
Skills that share tags, products or a category with Colt Review Process: Peer Review (spacering-net/codeg, 3.9k stars), Scholar Evaluation (spacering-net/codeg, 3.9k stars), Academic Paper Writing Pipeline (Imbad0202/academic-research-skills, 51k stars) and Academic Paper Reviewer (Imbad0202/academic-research-skills, 51k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Colt Review Process?
brycewang-stanford (a GitHub user) maintains it in brycewang-stanford/Awesome-Journal-Skills, which has 1,231 GitHub stars. The repository holds 2,387 skills in this directory. The repository was last updated on September 27, 2026.
Source: brycewang-stanford/Awesome-Journal-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.