New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Colm Supplementary

by brycewang-stanford in brycewang-stanford/Awesome-Journal-Skills

A skill your agent uses when deciding what goes into a COLM paper's appendices and supplementary material versus the strict 9-page main text — verbatim prompts, full evaluation configurations…

MITAuto-check passed

Install Colm Supplementary

skills CLI
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colm-supplementary -a claude-code

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

GitHub CLI
$ gh skill install brycewang-stanford/Awesome-Journal-Skills colm-supplementary --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/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/COLM-Skills/skills/colm-supplementary .claude/skills/colm-supplementary && 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-supplementary
GitHub stars
1.2k
Token cost
~1.7k tokens
SKILL.md length
788 words
Files
1
Skills in repo
2,387
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when deciding what goes into a COLM paper's appendices and supplementary material versus the strict 9-page main text — verbatim prompts, full evaluation configurations…

  • Works in 3 steps: The prompt appendix. Exact strings,… → The "what we tried" ledger. Prompt… → The contamination appendix. Overlap…
  • Deciding what goes into a COLM papers appendices and supplementary material versus the strict 9-page main text — verbatim prompts
  • SKILL.md covers The placement rule, LM-specific supplement content…, Anonymization of the code/data… and Referencing the supplement…, plus 4 more sections
  • Calls git

What it does

Colm Supplementary is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when deciding what goes into a COLM paper's appendices and supplementary material versus the strict 9-page main text — verbatim prompts, full evaluation configurations, per-task result tables, contamination analyses, human-evaluation protocols, and anonymized code/data packages that survive double-blind review.

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.

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

  • Deciding what goes into a COLM papers appendices and supplementary material versus the strict 9-page main text — verbatim prompts
  • Full evaluation configurations
  • Per-task result tables
  • Contamination analyses

Example prompts

  • “/colm-supplementary”

Workflow steps

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

  1. The prompt appendix. Exact strings, exemplar counts, formatting whitespace
  2. The "what we tried" ledger. Prompt variants and hyperparameters attempted
  3. The contamination appendix. Overlap statistics per evaluation set, or the

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

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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 Supplementary loads about 1.7k tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 788 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~84
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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). 788 words, ~1,691 tokens.

Download SKILL.mdSave it as .claude/skills/colm-supplementary/SKILL.md (or your agent's skills folder).
name
colm-supplementary
description
Use when deciding what goes into a COLM paper's appendices and supplementary material versus the strict 9-page main text — verbatim prompts, full evaluation configurations, per-task result tables, contamination analyses, human-evaluation protocols, and anonymized code/data packages that survive double-blind review.

COLM Supplementary Material

The 2026 format gives you a strict 9-page main text, unlimited citation pages, and appendix space whose guaranteed audience is nobody — reviewers may read it, the rebuttal may point into it, but no rule obliges anyone to open it. That asymmetry is the whole design principle: the main text carries every load-bearing element, and the supplement carries the audit trail that makes the main text checkable.

The placement rule

Ask of each artifact: is this needed to believe the claim, or to re-run it? Believe → main text. Re-run → appendix/supplement. Both → summarize in the main text, deposit fully in the appendix, and cross-reference in both directions.

ArtifactPlacementNote
Representative prompt (or skeleton)Main textReaders cannot judge an LM evaluation without seeing how the model was asked
Full prompt set, verbatim, incl. system promptsAppendixParaphrased prompts are not reproducible; include exact strings
Decoding configs per experimentAppendix tableOne row per reported table cell group (colm-experiments)
Contamination analysis method + resultsSummary in main text; full in appendixThe conclusion is load-bearing; the n-gram machinery is audit trail
Per-task / per-model full result gridsAppendixMain text shows the aggregate + the interesting slice
Human-eval protocol: instructions, pay, demographics, agreementAppendixScreenshots of annotator UI earn trust
Failure cases and transcriptsAppendix, curatedA dozen representative transcripts beat 400 raw ones
Code + data packageSupplementary upload / anonymized repoMust be anonymous at submission (see below)
Raw API responses archiveRelease artifact (acceptance)Often too large for review upload; describe it and commit to release

LM-specific supplement content reviewers actually use

Three appendix sections repeatedly decide borderline LM papers:

  1. The prompt appendix. Exact strings, exemplar counts, formatting whitespace included. Prompt paraphrase is a known variance source, so approximation here undermines every number.
  2. The "what we tried" ledger. Prompt variants and hyperparameters attempted per system — the fairness evidence for baseline comparisons.
  3. The contamination appendix. Overlap statistics per evaluation set, or the documented reason none could be computed.

Anonymization of the code/data package

COLM's instructions ban identity-revealing links, and supplements are the usual leak. Before upload, scrub: repository remotes and commit author fields (git log travels inside .git/), Hugging Face org names in from_pretrained(...) calls, W&B entity names in configs, API org IDs in cached headers, absolute paths (/home/<username>/...), and internal cluster hostnames.

bash
# Build the review package from a clean export — never zip a working directory
git archive --format=tar HEAD | (mkdir -p /tmp/colm-pkg && tar -x -C /tmp/colm-pkg)
grep -rniE 'wandb|hf_[A-Za-z0-9]{20,}|api[_-]?key|/home/[a-z]|<lab-name>' /tmp/colm-pkg | head
grep -rlE 'from_pretrained\("[^"]*/' /tmp/colm-pkg --include='*.py' | head   # org-scoped model IDs
(cd /tmp && zip -rq colm-supplement.zip colm-pkg -x '*.git*')

git archive (not cp -r) is the load-bearing choice: it cannot smuggle .git/, untracked scratch files, or environment files into the package.

Referencing the supplement from the main text

  • Point at specific anchors ("App. C.2, Table 9"), never "see appendix".
  • In the rebuttal window (May 22 - June 8 in 2026), precise anchors let you answer a reviewer in one sentence plus a pointer — the highest-leverage use of everything you deposited.
  • Do not promise supplement content that is not there; reviewers who follow a dangling pointer stop trusting the intact ones.
Show full SKILL.md (314 more words)Show less

Ordering the appendix for the reader you hope exists

Appendices get opened with a question in hand, not read linearly. Order sections by the probability of the question:

  1. A. Experimental details — models, revisions, decoding configs, harness commit: the reproduction question.
  2. B. Prompts — verbatim, grouped by experiment: the "how did you ask" question.
  3. C. Contamination analysis — the trust question.
  4. D. Full results — per-task, per-model grids: the "does it hold on X" question.
  5. E. Baseline tuning ledger — the fairness question.
  6. F. Human/judge evaluation protocol — instructions, agreement, biases.
  7. G. Failure analysis — curated transcripts.
  8. H. Compute — the cost question.

Within each, lead with a two-line summary of what the section shows — the reviewer deciding whether to trust an unread appendix trusts one with visible structure. And keep appendix numbering frozen after submission: the rebuttal will cite "App. C.2" and a renumbered revision breaks every pointer in the discussion thread.

What not to include

  • Anything load-bearing that appears only in the supplement — if the 9 pages cannot make the case alone, restructure (colm-writing-style).
  • Un-curated dumps (every transcript, every checkpoint) — volume without curation reads as evasion.
  • Data whose license or ToS forbids redistribution — describe it and state the restriction instead (colm-artifact-evaluation).
  • 待核实: no supplementary size cap was verifiable for 2026; check the OpenReview form's actual limits rather than assuming.

Timing note for the 2026-style calendar

In 2026 the supplement traveled with the paper at the March 31 deadline — no separate later upload was posted (待核实 whether future cycles add one). Plan accordingly: the anonymization sweep and package build belong in deadline week's T-3 slot (colm-submission), not in an imagined grace period. And because the May 22 - June 8 rebuttal leans on appendix anchors, whatever you deposit in March is the ammunition you will fight with in June — deposit for your future self, who will be tired and have eighteen days.

Output format

text
[Placement audit] load-bearing content in supplement? none / move up: <items>
[Prompt appendix] verbatim + system prompts ▢   [Tried-ledger] ▢   [Contamination appendix] ▢
[Anonymity scan] clean / hits: <files>
[Pointer integrity] all anchors resolve / dangling: <refs>
[Package] built via clean export ▢  size: <n> MB (cap 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 COLM-Skills/skills/colm-supplementary of brycewang-stanford/Awesome-Journal-Skills.

Open the folder on GitHubat commit 932eb23

Compare with similar skills

Colm Supplementary 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 Supplementary compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Colm Supplementary this skillbrycewang-stanford/Awesome-Journal-Skills1.2k—~1.7kAutomated safety check: PassMIT
ColmnanoAgentTeam/research-claw293—~2.2kAutomated safety check: PassMIT
Icdm Supplementarybrycewang-stanford/Awesome-Journal-Skills1.2k—~1kAutomated safety check: PassMIT
Naacl Supplementarybrycewang-stanford/Awesome-Journal-Skills1.2k—~1.3kAutomated safety check: PassMIT
Soda Supplementarybrycewang-stanford/Awesome-Journal-Skills1.2k—~1.6kAutomated safety check: PassMIT
Aaai Supplementarybrycewang-stanford/Awesome-Journal-Skills1.2k—~852Automated safety check: PassMIT

Similar skills

  • Colm

    nanoAgentTeam/research-claw

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

    293 GitHub stars~2.2k tokensUpdated 4 mo ago
    Research & ScienceAuto-check passed

  • Icdm Supplementary

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when organizing supplementary and appendix material for an ICDM (IEEE International Conference on Data Mining) paper - deciding what belongs in the body, in an appendix that…

    1.2k GitHub stars~1k tokensUpdated 13 days ago
    Auto-check passed

  • Naacl Supplementary

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when deciding what goes into the content pages, the uncounted sections, the appendix, and the optional uploads of a NAACL-bound ARR submission — allocating material by what…

    1.2k GitHub stars~1.3k tokensUpdated 13 days ago
    Auto-check passed

  • Soda Supplementary

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when organizing the back matter of a SODA (ACM-SIAM Symposium on Discrete Algorithms) submission — there is no supplementary channel, so appendix architecture inside the…

    1.2k GitHub stars~1.6k tokensUpdated 13 days ago
    Documents & OfficeAuto-check passed

  • Aaai Supplementary

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when organizing AAAI supplementary material, including the technical appendix, multimedia appendix, and code/data ZIPs, while respecting that AAAI supplements are due with…

    1.2k GitHub stars~852 tokensUpdated 13 days ago
    Auto-check passed

  • Acl Supplementary

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when organizing appendices and supplementary material for an ACL paper under ACL Rolling Review, covering the mandatory Limitations and optional ethics sections, appendices…

    1.2k GitHub stars~1.5k tokensUpdated 13 days ago
    Auto-check passed

More from brycewang-stanford/Awesome-Journal-Skills

All 2,387 skills in this repo

  • Aaag 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…

    1.2k GitHub stars~1.3k tokensUpdated 13 days ago
    Auto-check passed

  • 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…

    1.2k GitHub stars~1.3k tokensUpdated 13 days ago
    Auto-check passed

  • 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…

    1.2k GitHub stars~1.4k tokensUpdated 13 days ago
    Auto-check passed

  • 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…

    1.2k GitHub stars~1.4k tokensUpdated 13 days ago
    Auto-check passed

  • 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…

    1.2k GitHub stars~1.3k tokensUpdated 13 days ago
    Auto-check passed

  • 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…

    1.2k GitHub stars~1.6k tokensUpdated 13 days ago
    Auto-check passed

Questions about Colm Supplementary

What does Colm Supplementary do?

A skill your agent uses when deciding what goes into a COLM paper's appendices and supplementary material versus the strict 9-page main text — verbatim prompts, full evaluation configurations…. Colm Supplementary is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when deciding what goes into a COLM paper's appendices and supplementary material versus the strict 9-page main text — verbatim prompts, full evaluation configurations, per-task result tables, contamination analyses, human-evaluation protocols, and anonymized code/data packages that survive double-blind review.

When should I use Colm Supplementary?

Colm Supplementary fits situations like: deciding what goes into a COLM papers appendices and supplementary material versus the strict 9-page main text — verbatim prompts; full evaluation configurations; per-task result tables; contamination analyses.

How do I install Colm Supplementary in Claude Code?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colm-supplementary -a claude-code`. Or copy the skill folder (COLM-Skills/skills/colm-supplementary in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/colm-supplementary in your project. Claude Code loads it when a task matches its description.

How do I install Colm Supplementary in Codex?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill colm-supplementary -a codex`. Or copy the skill folder (COLM-Skills/skills/colm-supplementary in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/colm-supplementary in your project. Codex loads it when a task matches its description.

Can I use Colm Supplementary 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 colm-supplementary -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-supplementary, .gemini/skills/colm-supplementary, .github/skills/colm-supplementary and .opencode/skills/colm-supplementary in your project.

What does Colm Supplementary need to run?

Going by SKILL.md and its folder, Colm Supplementary needs the command-line tools its instructions call (git).

Does Colm Supplementary access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Colm Supplementary 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 Supplementary use?

Colm Supplementary 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 Supplementary use?

About 1.7k tokens (SKILL.md is roughly 6.8k 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 Supplementary?

Skills that share tags, products or a category with Colm Supplementary: Colm (nanoAgentTeam/research-claw, 293 stars), Icdm Supplementary (brycewang-stanford/Awesome-Journal-Skills, 1.2k stars), Naacl Supplementary (brycewang-stanford/Awesome-Journal-Skills, 1.2k stars) and Soda Supplementary (brycewang-stanford/Awesome-Journal-Skills, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Colm Supplementary?

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.