COLM (Conference on Language Modeling) paper formatting — activate when the user wants COLM template setup, migration, or formatting/compilation fixes.

MITAuto-check passedResearch & Science

Install Colm

skills CLI
$ npx skills add nanoAgentTeam/research-claw --skill colm -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nanoAgentTeam/research-claw colm --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nanoAgentTeam/research-claw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/config/.skills/colm .claude/skills/colm && rm -rf skills-src

Use ~/.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/

Facts

Skill name
colm
GitHub stars
293
Token cost
~2.2k tokens
SKILL.md length
859 words
Files
10
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

COLM (Conference on Language Modeling) paper formatting — activate when the user wants COLM template setup, migration, or formatting/compilation fixes.

  • Works in 6 steps: Confirm target year and stage… → Check whether TEMPLATES_DIR exists and… → Use local built-in template only when… → …
  • Wants COLM template setup
  • SKILL.md covers Execution Protocol and Format Reference
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Colm is an agent skill from nanoAgentTeam/research-claw. COLM (Conference on Language Modeling) paper formatting — activate when the user wants COLM template setup, migration, or formatting/compilation fixes.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files (for example `templates/colm2025/README.md`).

It sits in Research & Science, covering LaTeX. The repository describes itself as: A self-hosted AI assistant for academic research — manages your papers, searches literature, tracks deadlines, and answers you on the channels you already use. The licence is MIT.

When your agent uses it

  • Wants COLM template setup
  • Formatting/compilation fixes

Example prompts

  • “/colm”

Requirements

  • Pre-approved tools (allowed-tools): read_file, write_file, str_replace, bash, latex_compile

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Confirm target year and stage (submission, preprint, or final). Default to latest available year if user does not specify.
  2. Check whether TEMPLATES_DIR exists and includes required files: colm2025_conference.sty, colm2025_conference.bst, colm2025_conference.tex…
  3. Use local built-in template only when BOTH conditions hold
  4. If either condition fails (target year is not 2025 OR local template files are missing/incomplete), execute this workflow
  5. Confirm paper type/page policy from current CFP before edits (common baseline in recent years: main text up to 9 pages, references…
  6. Filename substitution rule for all steps below

What it can do on your machine

Read from SKILL.md and the folder at commit ce3a4ac. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • read_file
    • write_file
    • str_replace
    • bash
    • latex_compile

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are latex).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • colmweb.org

    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

Colm loads about 2.2k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 859 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

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 nanoAgentTeam/research-claw at commit ce3a4ac, republished under its MIT licence (© nanoAgentTeam). 859 words, ~2,168 tokens.

Download SKILL.mdSave it as .claude/skills/colm/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.
name
colm
description
COLM (Conference on Language Modeling) paper formatting — activate when the user wants COLM template setup, migration, or formatting/compilation fixes.
allowed-tools
read_file, write_file, str_replace, bash, latex_compile

[SKILL: COLM PAPER FORMAT]

Activate when: user mentions COLM, Conference on Language Modeling, or asks to use/fix the COLM template.

Execution Protocol

After this skill is activated, select the matching scenario based on user intent.

Shared Common Workflow

Before venue-specific template steps, also load and follow ml-paper-writing skill.

At minimum, apply these shared references:

  • writing-guide.md (narrative and clarity)
  • citation-workflow.md (verified citations; no hallucinations)
  • reviewer-guidelines.md (reviewer-facing quality checks)
  • checklists.md (pre-submission gates)

Built-in template: templates/colm2025/ (referred to as TEMPLATES_DIR below), targeting COLM 2025. Contents: colm2025_conference.sty, colm2025_conference.bst, colm2025_conference.tex, colm2025_conference.bib, colm2025_conference.pdf, fancyhdr.sty, natbib.sty, math_commands.tex.

Pre-step: Year Confirmation & Template Acquisition

This step MUST be completed before any scenario below.

  1. Confirm target year and stage (submission, preprint, or final). Default to latest available year if user does not specify.
  2. Check whether TEMPLATES_DIR exists and includes required files: colm2025_conference.sty, colm2025_conference.bst, colm2025_conference.tex, fancyhdr.sty, natbib.sty.
  3. Use local built-in template only when BOTH conditions hold:
    • target year = 2025
    • files in TEMPLATES_DIR are complete
  4. If either condition fails (target year is not 2025 OR local template files are missing/incomplete), execute this workflow:
    • Inform user local built-in template is unavailable or year-mismatched
    • Open official COLM site: http://www.colmweb.org/
    • Find target-year CFP/submission page and locate "Author Kit", "Style Files", or template links
    • If official site has no direct files, check target-year OpenReview submission page for template links
    • Download official target-year template package (.zip or repository snapshot)
    • Unzip downloaded files directly into <PROJECT_CORE>.
    • Continue all remaining steps with downloaded year-specific filenames
  5. Confirm paper type/page policy from current CFP before edits (common baseline in recent years: main text up to 9 pages, references unlimited).
  6. Filename substitution rule for all steps below:
    • Treat colm2025_conference in commands/examples as a placeholder for the resolved style basename from the selected .sty file.
    • Example: if the downloaded file is colm2026_conference.sty, replace colm2025_conference with colm2026_conference in \\usepackage, \\bibliographystyle, copy commands, and checks.
Scenario Routing
  • User says "create / new COLM paper" → Scenario 1
  • User says "switch to COLM format" / "apply COLM template" → Scenario 2
  • User says "COLM format issue" / "compile error" → Scenario 3
  • User says "check format" / "prepare for submission" → Scenario 4
Scenario 1: Create a New COLM Project

Step 1 — Copy template files to project core directory using bash:

bash(command="cp TEMPLATES_DIR/colm2025_conference.sty TEMPLATES_DIR/colm2025_conference.bst TEMPLATES_DIR/fancyhdr.sty TEMPLATES_DIR/natbib.sty <PROJECT_CORE>/")

Step 2 — Read TEMPLATES_DIR/colm2025_conference.tex with read_file for canonical preamble and document structure.

Step 3 — Create main.tex using write_file:

  • \documentclass{article}
  • Submission mode by default: \usepackage[submission]{colm2025_conference}
  • Keep core packages from template (microtype, hyperref, url, booktabs, lineno)
  • Keep line-number block:
    • \ifcolmsubmission
    • \linenumbers
    • \fi
  • Use \bibliography{references} (or project bib file)
  • Use \bibliographystyle{colm2025_conference}

Step 4 — Run latex_compile; if errors occur, fix and recompile.

Scenario 2: Switch an Existing Project to COLM Template

Step 1 — Read current main.tex with read_file to analyze current preamble.

Step 2 — Read TEMPLATES_DIR/colm2025_conference.tex with read_file as migration reference.

Step 3 — Copy style files using bash (do NOT overwrite paper content):

bash(command="cp TEMPLATES_DIR/colm2025_conference.sty TEMPLATES_DIR/colm2025_conference.bst TEMPLATES_DIR/fancyhdr.sty TEMPLATES_DIR/natbib.sty <PROJECT_CORE>/")

Step 4 — Update preamble using str_replace:

  • Set \documentclass{article}
  • Set mode package per stage:
    • Submission: \usepackage[submission]{colm2025_conference}
    • Preprint: \usepackage[preprint]{colm2025_conference}
    • Camera-ready: \usepackage[final]{colm2025_conference}
  • Remove conflicting layout/font overrides (geometry, manual margins, external Palatino/Times overrides that conflict with template)

Step 5 — Align submission/final behavior:

  • Submission must keep anonymity and line numbers
  • Final mode can expose author information
  • Do not include identifying acknowledgements in anonymous submission

Step 6 — Fix bibliography setup:

  • \bibliographystyle{colm2025_conference}
  • \bibliography{references} (or existing bib file)

Step 7 — Run latex_compile and resolve remaining issues.

Show full SKILL.md (319 more words)Show less
Scenario 3: Fix COLM Format Issues

Step 1 — Run latex_compile to capture errors/warnings.

Step 2 — Read preamble in main.tex and compare with TEMPLATES_DIR/colm2025_conference.tex.

Step 3 — Check common COLM failures:

  • Missing colm2025_conference.sty / .bst in project root
  • Wrong mode (using final or preprint during anonymous submission)
  • Missing line-number block in submission mode
  • Wrong bibliography style (not colm2025_conference)
  • Manual margin/font overrides that break template geometry

Step 4 — Apply fixes with str_replace.

Step 5 — Re-run latex_compile until clean.

Scenario 4: Pre-submission Format Compliance Check

Step 1 — Read full main.tex with read_file.

Step 2 — Verify checklist items:

  • \usepackage[submission]{colm2025_conference} is used for review submission
  • No identifying author info or acknowledgements in anonymous submission
  • Line numbers enabled for submission (\ifcolmsubmission ... \linenumbers ... \fi)
  • Main text page count follows current CFP (commonly 9 pages; references unlimited)
  • Paper size/layout not overridden (template targets US Letter, 8.5x11 in)
  • Bibliography uses colm2025_conference style
  • Optional sections (ethics statement, appendix) placed after main text according to CFP

Step 3 — Report and fix issues one by one with str_replace.

Step 4 — Run final latex_compile verification.


Format Reference

⚠️ Reference only — always verify: COLM policies can change by year. Always prioritize the target year's CFP and author kit over defaults in this skill.

Template Download
Setup: Unzip Location

Unzip into project root (same folder as main.tex):

project/
├── main.tex
├── colm2025_conference.sty
├── colm2025_conference.bst
├── colm2025_conference.tex
├── fancyhdr.sty
└── natbib.sty
Read These Files First
  1. colm2025_conference.tex — canonical setup and usage
  2. colm2025_conference.pdf — formatting instructions
  3. colm2025_conference.sty — option behavior (submission, preprint, final)
Template Setup in main.tex
latex
\documentclass{article}
\usepackage[submission]{colm2025_conference}

\usepackage{microtype}
\usepackage{hyperref}
\usepackage{url}
\usepackage{booktabs}
\usepackage{lineno}

\ifcolmsubmission
\linenumbers
\fi
Key Format Rules
ItemRequirement
Submission modeUse [submission] for blind review
LayoutSingle-column, US Letter dimensions (set by style)
Page limitTypically 9 pages main text + unlimited references (verify CFP)
Bibliography\bibliographystyle{colm2025_conference}
Camera-readySwitch to [final] only after acceptance
Common Pitfalls
  • Using wrong mode option for review (final instead of submission)
  • Missing colm2025_conference.sty or .bst in root
  • Overriding margins/fonts with geometry or custom hacks
  • Forgetting submission line numbers
  • Using non-COLM bibliography style

© nanoAgentTeam, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files in config/.skills/colm of nanoAgentTeam/research-claw.

  • SKILL.md
  • templates/colm2025/README.md
  • templates/colm2025/colm2025_conference.bib
  • templates/colm2025/colm2025_conference.bst
  • templates/colm2025/colm2025_conference.pdf
  • templates/colm2025/colm2025_conference.sty
  • templates/colm2025/colm2025_conference.tex
  • templates/colm2025/fancyhdr.sty
  • templates/colm2025/math_commands.tex
  • templates/colm2025/natbib.sty

Open the folder on GitHubat commit ce3a4ac

Compare with similar skills

Colm 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.

Colm compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Colm this skillnanoAgentTeam/research-claw293—~2.2kAutomated safety check: PassMIT
Academic Paper Writing PipelineImbad0202/academic-research-skills51k—~16kAutomated safety check: PassCustom licence
Scientific Venue Templatesdavila7/claude-code-templates32k9 repos~5.1kAutomated safety check: NotesMIT
Econ Writehanlulong/econ-writing-skill6462 repos~14kAutomated safety check: PassMIT
NSFC Budget Justification Writerhuangwb8/ChineseResearchLaTeX2.9k2 repos~1.4kAutomated safety check: PassMIT
NSFC Grant Rationale Writerhuangwb8/ChineseResearchLaTeX2.9k—~945Automated safety check: PassMIT

Similar skills

  • 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.

    51k GitHub stars~16k tokensUpdated 4 days ago
    Research & ScienceAuto-check passed
  • Scientific Venue Templates

    davila7/claude-code-templates

    Supplies LaTeX templates and formatting rules for journals, conferences, posters, and grant proposals, then can check a draft against them.

    32k GitHub starsUsed in 9 repos~5.1k tokens
    Research & ScienceAuto-check: notes
  • Econ Write

    hanlulong/econ-writing-skill

    Expert economics paper writing assistant synthesizing advice from 50+ top guides by Cochrane, McCloskey, Shapiro, Head, Bellemare, Goldin, Glaeser, Kremer, and other leading economists.

    646 GitHub starsUsed in 2 repos~14k tokens
    Research & ScienceAuto-check passed
  • NSFC Budget Justification Writer

    huangwb8/ChineseResearchLaTeX

    Writes a submission-ready NSFC budget justification as a LaTeX project and renders budget.pdf from your grant proposal text and supporting materials.

    2.9k GitHub starsUsed in 2 repos~1.4k tokens
    Research & ScienceAuto-check passed
  • NSFC Grant Rationale Writer

    huangwb8/ChineseResearchLaTeX

    Writes, restructures, reviews and polishes the rationale section of NSFC research grant applications in LaTeX, with backups and a diff before every write.

    2.9k GitHub stars~945 tokensUpdated 4 days ago
    Research & ScienceAuto-check passed
  • Backward Traceability

    lingzhi227/agent-research-skills

    Makes each number in a LaTeX paper link back to the code line that produced it, using hypertarget and hyperlink tags and compile-time `\num` formulas.

    384 GitHub stars~802 tokensUpdated 7 mo ago
    Research & ScienceAuto-check passed

More from nanoAgentTeam/research-claw

All 14 skills in this repo
  • Aaai

    nanoAgentTeam/research-claw

    AAAI paper formatting — activate when the user wants AAAI template setup, migration, or formatting/compilation fixes.

    293 GitHub stars~2.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Acl Venues

    nanoAgentTeam/research-claw

    ACL-family venue paper formatting (ACL, EMNLP, NAACL, EACL, AACL, COLING, ARR, Findings) — activate when the user wants any ACL-series template setup, migration, or format fixes.

    293 GitHub stars~2.3k tokensUpdated 4 mo ago
    Auto-check passed
  • Conference Research

    nanoAgentTeam/research-claw

    Academic venue paper discovery — activate when you need to find papers accepted at specific conferences or journals (ACL, EMNLP, NeurIPS, ICML, ICLR, MLSys, etc.), analyze venue acceptance…

    293 GitHub stars~823 tokensUpdated 4 mo ago
    Auto-check passed
  • Cvpr Iccv Eccv

    nanoAgentTeam/research-claw

    CVPR / ICCV / ECCV paper formatting — activate when the user wants to submit to CVPR, ICCV, or ECCV, follow their template, or fix format issues for these computer vision conferences.

    293 GitHub stars~3.2k tokensUpdated 4 mo ago
    Auto-check passed
  • Iclr

    nanoAgentTeam/research-claw

    ICLR (International Conference on Learning Representations) paper formatting — activate when the user wants to submit to ICLR, follow ICLR template, or fix ICLR format issues.

    293 GitHub stars~2.7k tokensUpdated 4 mo ago
    Auto-check passed
  • Icml

    nanoAgentTeam/research-claw

    ICML (International Conference on Machine Learning) paper formatting — activate when the user wants to submit to ICML, follow ICML template, or fix ICML format issues.

    293 GitHub stars~2.4k tokensUpdated 4 mo ago
    Auto-check passed

Questions about Colm

What does Colm do?

COLM (Conference on Language Modeling) paper formatting — activate when the user wants COLM template setup, migration, or formatting/compilation fixes. Colm is an agent skill from nanoAgentTeam/research-claw. COLM (Conference on Language Modeling) paper formatting — activate when the user wants COLM template setup, migration, or formatting/compilation fixes.

When should I use Colm?

Colm fits situations like: wants COLM template setup; formatting/compilation fixes.

How do I install Colm in Claude Code?

Run `npx skills add nanoAgentTeam/research-claw --skill colm -a claude-code`. Or copy the skill folder (config/.skills/colm in nanoAgentTeam/research-claw) into .claude/skills/colm in your project. Claude Code loads it when a task matches its description.

How do I install Colm in Codex?

Run `npx skills add nanoAgentTeam/research-claw --skill colm -a codex`. Or copy the skill folder (config/.skills/colm in nanoAgentTeam/research-claw) into .agents/skills/colm in your project. Codex loads it when a task matches its description.

Can I use Colm 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 nanoAgentTeam/research-claw --skill colm -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/colm, .gemini/skills/colm, .github/skills/colm and .opencode/skills/colm in your project.

What does Colm need to run?

SKILL.md names no scripts, command-line tools or credentials: Colm is instructions for the agent only. Its frontmatter pre-approves these tools: read_file, write_file, str_replace, bash, latex_compile.

Does Colm access the network?

SKILL.md names 1 domain. As links in the text: colmweb.org. This is read from the text; nothing was executed.

Is Colm 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 Colm use?

Colm 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 Colm use?

About 2.2k tokens (SKILL.md is roughly 8.7k 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 Colm?

Skills that share tags, products or a category with Colm: Academic Paper Writing Pipeline (Imbad0202/academic-research-skills, 51k stars), Scientific Venue Templates (davila7/claude-code-templates, 32k stars), Econ Write (hanlulong/econ-writing-skill, 646 stars) and NSFC Budget Justification Writer (huangwb8/ChineseResearchLaTeX, 2.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Colm?

nanoAgentTeam (a GitHub organization) maintains it in nanoAgentTeam/research-claw, which has 293 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on June 8, 2026.

Source: nanoAgentTeam/research-claw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.