Experiment Plan
appleweiping/WEIPING_WIKI
Rigorous experiment planning that produces a complete, auditable experiment plan with blocks, baselines, milestones, decision gates, and compute estimates.
A skill your agent uses when planning a COLT (Conference on Learning Theory) submission calendar backward from the single AoE paper deadline — proof-completion and verification milestones, writing…
Install Colt Workflow
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-workflow -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills colt-workflow --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-workflow .claude/skills/colt-workflow && 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-workflow" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-workflow into .claude/skills/colt-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "colt-workflow", 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-workflowType 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-workflow -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills colt-workflow --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-workflow .agents/skills/colt-workflow && 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-workflow" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-workflow into .agents/skills/colt-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "colt-workflow", 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-workflow -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills colt-workflow --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-workflow .cursor/skills/colt-workflow && 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-workflow" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-workflow into .cursor/skills/colt-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "colt-workflow", 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-workflow--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-workflow -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills colt-workflow --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-workflow .gemini/skills/colt-workflow && 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-workflow" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-workflow into .gemini/skills/colt-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "colt-workflow", 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-workflowInstalls 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-workflow -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-workflow .github/skills/colt-workflow && 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-workflow" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-workflow into .github/skills/colt-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "colt-workflow", 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-workflow -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-workflow --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-workflow .opencode/skills/colt-workflow && 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-workflow" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/COLT-Skills/skills/colt-workflow into .opencode/skills/colt-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "colt-workflow", 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-workflow- GitHub stars
- 1.2k
- Token cost
- ~1.7k tokens
- SKILL.md length
- 792 words
- Files
- 1
- Skills in repo
- 2,387
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when planning a COLT (Conference on Learning Theory) submission calendar backward from the single AoE paper deadline — proof-completion and verification milestones, writing…
- Writing and appendix-assembly passes
- SKILL.md covers Stage map, Backward plan from the deadline, Verification is the critical… and Team coordination template, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- The rebuttal window
What it does
Colt Workflow is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when planning a COLT (Conference on Learning Theory) submission calendar backward from the single AoE paper deadline — proof-completion and verification milestones, writing and appendix-assembly passes, CMT logistics, the rebuttal window, decision aftermath, and PMLR camera-ready with conference presentation in early summer.
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 Product & Project Management, covering Project management. 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
- Writing and appendix-assembly passes
- The rebuttal window
- Decision aftermath
- PMLR camera-ready with conference presentation in early summer
Example prompts
- “/colt-workflow”
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 Workflow loads about 1.7k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 792 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). 792 words, ~1,733 tokens.
Download SKILL.mdSave it as
.claude/skills/colt-workflow/SKILL.md (or your agent's skills folder).- name
- colt-workflow
- description
- Use when planning a COLT (Conference on Learning Theory) submission calendar backward from the single AoE paper deadline — proof-completion and verification milestones, writing and appendix-assembly passes, CMT logistics, the rebuttal window, decision aftermath, and PMLR camera-ready with conference presentation in early summer.
COLT Workflow
Use this as the project-management layer for a COLT paper. Anchor everything to the live timetable: for the 39th edition the CFP (checked 2026-07-08) set one submission deadline — February 4, 2026, Anywhere on Earth, via CMT — for a conference running June 29 to July 3, 2026 in San Diego. Notification and camera-ready dates were not on the checked pages (待核实); take them from the CFP and acceptance email of your cycle.
Stage map
- Fit decision: confirm the contribution is a theorem a learning theorist wants
(see
colt-topic-selection); if the result is 80% proved, the clock question is whether the remaining 20% is verification or invention — only the first is schedulable. - Result freeze: theorem statements stop moving. At COLT this is the single most important date you control, because every downstream artifact (proof appendix, overviews, comparisons) quotes the statements.
- Verification: independent re-derivation of every load-bearing proof
(
colt-reproducibility). Schedule it as real work with an owner per theorem — it finds bugs at a rate authors never want to believe. - Writing: body-first is a mistake here; write the appendix proofs first, then distill overviews into the body, so the body never promises what the appendix cannot deliver.
- Submission week: CMT record early, anonymity sweep, single-PDF assembly
(
colt-submission). - Rebuttal: reviews arrive before decisions; block calendar capacity for the
window even before you know its dates (
colt-author-response). - Aftermath: acceptance → PMLR camera-ready and talk prep (
colt-camera-ready); rejection → triage between fix-and-resubmit (next COLT / ALT) and re-routing.
Backward plan from the deadline
| Weeks before deadline | Milestone | Failure smell |
|---|---|---|
| 10+ | All main results proved at whiteboard level | "The lower bound should follow" — it does not, yet |
| 8 | Theorem statements frozen; ledger of claims opened | Statements still absorbing scope changes |
| 6 | Full proofs written in LaTeX, appendix-structured | Proofs alive only in notebooks and heads |
| 4 | Independent verification pass complete; bugs triaged | "We'll verify while writing" (you will not) |
| 3 | Body drafted: setup, results, proof overviews, known-vs-new table | Overview promises diverging from actual proofs |
| 2 | Internal mock review by an uninvolved theorist | No one external has read the model section |
| 1 | Anonymity sweep, notation audit, cross-reference check | Renumbering theorems this late |
| 0 | Upload, re-download, verify the stored PDF; stop editing | Compiling at the AoE boundary |
Weeks are heuristics; the deadline is not. AoE means when it is February 4 anywhere on Earth — compute your local cutoff and subtract a safety day.
Verification is the critical path
For a theory paper the long pole is never the writing; it is discovering at week 2 that Lemma 6 is false. Mitigations:
- Verify in dependency order, most-load-bearing first — a bug in the master lemma invalidates weeks of downstream polishing.
- When a bug appears, immediately re-derive the weakest still-true statement and check whether the paper survives with it; many COLT papers ship the weaker constant that week-3 debugging forced.
- Maintain the claim ledger (see
colt-artifact-evaluation) as the single source of verification status; standups read the ledger, not vibes.
Show full SKILL.md (307 more words)Show less
Team coordination template
# colt-plan.txt
DEADLINE (AoE): 2026-02-04 -> local cutoff 2026-02-05 11:59 UTC-12
RESULT FREEZE: 2025-12-10 owner: all
PROOF APPENDIX DRAFT: 2025-12-22 owner: A (Thm 1), B (Thm 2, lower bound)
VERIFICATION PASS: 2026-01-09 owner: swap (B checks Thm 1, A checks Thm 2)
BODY + OVERVIEWS: 2026-01-16 owner: A
MOCK REVIEW: 2026-01-21 reader: C (not a coauthor)
ANONYMITY + PDF QA: 2026-01-28 owner: B
UPLOAD TARGET: 2026-02-02 (two days of slack, CMT record made 01-25)
REBUTTAL WINDOW: dates TBA with reviews -> block capacity on releaseWorkflow failure modes specific to theory papers
- The moving theorem: a coauthor strengthens a statement during the writing phase without re-opening its ledger entry; the appendix now proves the old claim. Rule: statement edits after freeze require a ledger re-verification, no exceptions.
- The optimistic lower bound: upper bound done, lower bound "clearly similar to [X]" and scheduled for week 2. Lower bounds are inventions, not chores — either prove it before freeze or descope the paper to the upper bound honestly.
- The single-verifier trap: the only person who checked Theorem 2 is the person who proved it. Swap verification assignments explicitly (the plan file above does).
- The deadline compile: first full single-PDF build in the final 48 hours, discovering the restatement macros and cross-references were never wired. Build the full document skeleton — body, appendix, references — by week 3 even while proofs are placeholders.
After the decision
- Accepted: camera-ready per instructions; book San Diego-style summer logistics early (single-track conference, one venue hotel); decide who talks.
- Rejected with deep reviews: the reviews are a free verification report — patch and target the next cycle or ALT (deadline typically in autumn; verify).
- Rejected for significance: the mathematics may be sound but mis-framed; rework the motivation and known-vs-new ledger before blaming the result.
- Either way, reconcile the arXiv version with what review taught you.
- Debrief the ledger: which claims did reviewers actually verify, and did your internal verification pass catch what they caught? Calibrating that gap improves the next paper's schedule more than any template.
Cycle-volatility warnings
- Every date above except the verified 2026 deadline and conference dates is cycle-specific; notification, rebuttal window, camera-ready, and registration timing are 待核实 until announced.
- Whether an Open Problems track (with its own deadline) runs in your cycle: check the CFP; the 2025 edition ran one with a later, non-anonymous, 4-page format.
Output format
[Stage] proving / freeze / verification / writing / submitted / rebuttal / decision
[Critical path] <the unverified claim or unwritten proof gating everything>
[Calendar] <next official date + source, or 待核实>
[Owner map] <theorem/task -> person>
[Slack] <days between planned upload and AoE cutoff>© 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-workflow of brycewang-stanford/Awesome-Journal-Skills.
Open the folder on GitHubat commit 932eb23
Compare with similar skills
Colt Workflow 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 Workflow this skillbrycewang-stanford/Awesome-Journal-Skills | 1.2k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Experiment Planappleweiping/WEIPING_WIKI | 119 | — | ~1k | Automated safety check: Pass | MIT | |
| Translational Study Blueprintaipoch/medical-research-skills | 2k | — | ~3.7k | Automated safety check: Pass | MIT | |
| CCPM Project Managementautomazeio/ccpm | 8.4k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Uvastral-sh/claude-code-plugins | 313 | 2 repos | ~980 | Automated safety check: Pass | Apache-2.0 | |
| Project Managementkunchenguid/firstmate | 7.7k | — | ~2.1k | Automated safety check: Pass | MIT |
Similar skills
Translational Study Blueprint
aipoch/medical-research-skills
Designs a translational blueprint for moving a biomedical finding toward diagnosis, prognosis, treatment response prediction, patient stratification, or therapeutic development, with explicit…
CCPM Project Management
automazeio/ccpm
Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.
- Official
Uv
astral-sh/claude-code-plugins
Guide for using uv, the Python package and project manager. An agent skill from astral-sh/claude-code-plugins.
Project Management
kunchenguid/firstmate
Agent-only procedure for Firstmate project management. An agent skill from kunchenguid/firstmate.
Hivemind Goals
activeloopai/hivemind
Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/.
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
Questions about Colt Workflow
What does Colt Workflow do?
A skill your agent uses when planning a COLT (Conference on Learning Theory) submission calendar backward from the single AoE paper deadline — proof-completion and verification milestones, writing…. Colt Workflow is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when planning a COLT (Conference on Learning Theory) submission calendar backward from the single AoE paper deadline — proof-completion and verification milestones, writing and appendix-assembly passes, CMT logistics, the rebuttal window, decision aftermath, and PMLR camera-ready with conference presentation in early summer.
When should I use Colt Workflow?
Colt Workflow fits situations like: writing and appendix-assembly passes; the rebuttal window; decision aftermath; PMLR camera-ready with conference presentation in early summer.
How do I install Colt Workflow in Claude Code?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-workflow -a claude-code`. Or copy the skill folder (COLT-Skills/skills/colt-workflow in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/colt-workflow in your project. Claude Code loads it when a task matches its description.
How do I install Colt Workflow in Codex?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colt-workflow -a codex`. Or copy the skill folder (COLT-Skills/skills/colt-workflow in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/colt-workflow in your project. Codex loads it when a task matches its description.
Can I use Colt Workflow 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-workflow -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-workflow, .gemini/skills/colt-workflow, .github/skills/colt-workflow and .opencode/skills/colt-workflow in your project.
What does Colt Workflow need to run?
SKILL.md names no scripts, command-line tools or credentials: Colt Workflow is instructions for the agent only.
Does Colt Workflow 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 Workflow 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 Workflow use?
Colt Workflow 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 Workflow use?
About 1.7k tokens (SKILL.md is roughly 6.9k 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 Workflow?
Skills that share tags, products or a category with Colt Workflow: Experiment Plan (appleweiping/WEIPING_WIKI, 119 stars), Translational Study Blueprint (aipoch/medical-research-skills, 2k stars), CCPM Project Management (automazeio/ccpm, 8.4k stars) and Uv (astral-sh/claude-code-plugins, 313 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Colt Workflow?
brycewang-stanford (a GitHub user) maintains it in brycewang-stanford/Awesome-Journal-Skills, which has 1,228 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.