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 Writing Style

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

A skill your agent uses when drafting or revising COLM paper prose — leading with a finding about language models rather than a leaderboard delta, scoping claims to tested models and scales, naming…

MITAuto-check passedWriting & Content

Install Colm Writing Style

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

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

GitHub CLI
$ gh skill install brycewang-stanford/Awesome-Journal-Skills colm-writing-style --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-writing-style .claude/skills/colm-writing-style && 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-writing-style
GitHub stars
1.2k
Token cost
~1.7k tokens
SKILL.md length
758 words
Files
1
Skills in repo
2,387
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when drafting or revising COLM paper prose — leading with a finding about language models rather than a leaderboard delta, scoping claims to tested models and scales, naming…

  • Works in 5 steps: Finding pass — can a reader quote the… → Scope pass — grep for "LLMs… → Pinning pass — every model name in prose… → …
  • Revising COLM paper prose — leading with a finding about language models rather than a leaderboard delta
  • SKILL.md covers Lead with the finding, not the…, Scope discipline: the "for the…, The 9-page architecture and Voice calibration, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Colm Writing Style is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when drafting or revising COLM paper prose — leading with a finding about language models rather than a leaderboard delta, scoping claims to tested models and scales, naming versions in text, keeping the 9-page main text self-sufficient, and matching the measured, analysis-forward voice of COLM's award lineage.

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 Writing & Content, covering Brand voice and tone. 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

  • Revising COLM paper prose — leading with a finding about language models rather than a leaderboard delta
  • Scoping claims to tested models and scales
  • Naming versions in text
  • Keeping the 9-page main text self-sufficient

Example prompts

  • “/colm-writing-style”

Workflow steps

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

  1. Finding pass — can a reader quote the paper's claim about language models
  2. Scope pass — grep for "LLMs are/can/cannot", "models in general", "always",
  3. Pinning pass — every model name in prose carries a version at first mention.
  4. Self-sufficiency pass — read only the 9 pages; note every claim whose
  5. Register pass — apply the voice table; delete superlatives that carry no

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

Colm Writing Style loads about 1.7k tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 758 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). 758 words, ~1,700 tokens.

Download SKILL.mdSave it as .claude/skills/colm-writing-style/SKILL.md (or your agent's skills folder).
name
colm-writing-style
description
Use when drafting or revising COLM paper prose — leading with a finding about language models rather than a leaderboard delta, scoping claims to tested models and scales, naming versions in text, keeping the 9-page main text self-sufficient, and matching the measured, analysis-forward voice of COLM's award lineage.

COLM Writing Style

COLM prose has a recognizable register, visible in the venue's Outstanding Papers: it reads like measurement, not marketing. The model under study is named precisely, the claim is scoped to what was tested, and the interesting sentence is about what was learned, not who is winning. Edit toward that register.

Lead with the finding, not the delta

The weakest COLM opening is "LLMs have shown impressive capabilities, but..." — a frame that positions the paper as a reaction to hype. The strongest openings state the phenomenon or question directly:

  • Delta-first (avoid): "We improve long-context QA by 4.2 points over strong baselines."
  • Finding-first (prefer): "Accuracy on items written before a model's data cutoff exceeds accuracy on items written after it — the gap, not the score, is what a static leaderboard measures."

If the paper's most interesting sentence is a number on a benchmark, the framing is not done; find the sentence about language models that the number supports.

Scope discipline: the "for the models tested" rule

Unscoped generalization is the most common COLM prose bug. Claims about "LLMs" must either carry coverage (multiple families, multiple scales) or shrink to their evidence:

Draft sentenceScoped rewrite
"LLMs cannot do multi-step planning.""None of the six models tested (App. A) exceeds 40% on depth-3 planning items."
"Instruction tuning destroys calibration.""Across both model families, instruction-tuned variants are less calibrated than their bases at every scale we test."
"GPT-4 solves this task.""<exact-version-string> (queried 2026-03-1x) solves 87% of instances under the App. B prompt."
"Our method generalizes to any decoder.""The method assumes access to token logprobs; it applies to open-weight decoders and APIs that expose them."

Version strings and query dates belong in the text or a footnote at first mention, not only in an appendix — at this venue they are part of the noun.

The 9-page architecture

The 2026 format is a strict 9-page main text with unlimited citation pages, and appendices that reviewers may not read closely. Structure for that reality:

  • Main text must be self-sufficient: setup, the evaluation's design logic, the contamination story, headline evidence, and limitations all inside the 9 pages.
  • Appendices hold depth, not load-bearing content: full prompt texts, per-task tables, extra ablations. If removing an appendix breaks a main-text claim, the claim's support is misplaced.
  • Prompts deserve first-class treatment: show one representative prompt (or its skeleton) in the main text so readers can judge the evaluation, and push the full set to the appendix verbatim.
  • Do not fight the cap with typography. The template is the template; win space by cutting the second-weakest experiment, merging near-duplicate tables, and turning paragraph-length related work into claims with citations.
Show full SKILL.md (317 more words)Show less

Voice calibration

text
Overclaiming register (edit away)        COLM register (edit toward)
"remarkable emergent abilities"       →  "accuracy rises from 12% to 61% between
                                          the 7B and 70B models"
"we are the first to..."              →  state the contribution; let §2 (related
                                          work) establish priority with citations
"significantly better"                →  "better by 4.1 points (95% CI ±1.3,
                                          n = 5 samples/item)" — or delete
                                          "significantly" if untested
"solves reasoning"                    →  "improves on the three reasoning suites
                                          tested; transfer beyond them is open"
"due to hallucination"                →  name the observed behavior: fabricated
                                          citation, unsupported premise, etc.

Two vocabulary cautions specific to this literature: "emergent" invites a methodological fight about metric nonlinearity — use it only if you engage that debate; "understands/knows/wants" anthropomorphize — fine informally, risky in claims; prefer behavioral statements.

Limitations as evidence of competence

COLM's culture (a venue founded partly to critique LM technology) reads a sharp limitations discussion as expertise, not weakness. Name the models you could not test and why (cost, access), the benchmarks that may be contaminated, the decoding configs not explored, and the populations your human evaluation does not represent. Specific limitations pre-empt rebuttal questions; generic ones ("more experiments needed") waste the section.

Titles and abstracts, COLM register

The title should name the finding or the object, not the aspiration: "X happens in Y models under Z conditions" outperforms "Towards better X" at a venue whose readers triage hundreds of LM papers by title alone. The abstract follows the same arc as the paper's first page — phenomenon, why existing instruments miss it, what you measured, on which (pinned) models, with what uncertainty, and the one-sentence scoped conclusion. Save the memorable system name for the second sentence; the first sentence belongs to the question. And because the March abstract deadline feeds reviewer bidding days before the paper exists (colm-submission), write the abstract as if it is the only thing a bidding reviewer will see — in March, it is.

Revision passes, in order

  1. Finding pass — can a reader quote the paper's claim about language models after page 1?
  2. Scope pass — grep for "LLMs are/can/cannot", "models in general", "always", "never"; scope or support each hit.
  3. Pinning pass — every model name in prose carries a version at first mention.
  4. Self-sufficiency pass — read only the 9 pages; note every claim whose evidence lives in an appendix, and move a summary of it up.
  5. Register pass — apply the voice table; delete superlatives that carry no information.

Output format

text
[Register] measurement-grade / marketing residue at: <locations>
[Finding sentence] "<the paper's one-line claim about LMs>"
[Scope violations] <count> — worst: <example>
[Unpinned mentions] <model names lacking versions in text>
[9-page audit] self-sufficient / load-bearing appendix content: <what>
[Edit order] <passes still to run>

© 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-writing-style of brycewang-stanford/Awesome-Journal-Skills.

Open the folder on GitHubat commit 932eb23

Compare with similar skills

Colm Writing Style 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 Writing Style compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Colm Writing Style this skillbrycewang-stanford/Awesome-Journal-Skills1.2k—~1.7kAutomated safety check: PassMIT
Avoid AI Writingconorbronsdon/avoid-ai-writing4.9k3 repos~8.1kAutomated safety check: PassMIT
BrandOhh-889/skyroc79513 repos~733Automated safety check: PassMIT
Khazix WeChat Article WriterKKKKhazix/khazix-skills21k1 repos~2.9kAutomated safety check: PassMIT
Writing Guidelinesvercel-labs/agent-skills32k7 repos~309Automated safety check: PassNone
Unslop AI Writing Cleanuptheclaymethod/unslop518—~1.7kAutomated safety check: PassMIT

Similar skills

  • Avoid AI Writing

    conorbronsdon/avoid-ai-writing

    Audit and rewrite content to remove AI writing patterns ("AI-isms").

    4.9k GitHub starsUsed in 3 repos~8.1k tokens
    Writing & ContentAuto-check passed

  • Brand

    Ohh-889/skyroc

    Brand voice, visual identity, messaging frameworks, asset management, brand consistency.

    795 GitHub starsUsed in 13 repos~733 tokens
    Writing & ContentAuto-check passed

  • Khazix WeChat Article Writer

    KKKKhazix/khazix-skills

    Writes long-form WeChat official account articles in the personal style of the Khazix account, from briefs, links, PDFs or rough notes, with a topic quality check.

    21k GitHub starsUsed in 1 repo~2.9k tokens
    Writing & ContentAuto-check passed

  • Writing Guidelines

    vercel-labs/agent-skills

    Official

    Review docs/prose for Writing Guidelines compliance. An agent skill from vercel-labs/agent-skills.

    32k GitHub starsUsed in 7 repos~309 tokens
    Writing & ContentAuto-check passed

  • Unslop AI Writing Cleanup

    theclaymethod/unslop

    Removes AI writing tells from prose through an audit-first flow, routing to a two-pass rewrite, a report-only cleanup, voice teaching or mimicry depending on the sub-command used.

    518 GitHub stars~1.7k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed

  • UX Writing

    content-designer/ux-writing-skill

    Applies UX writing practice to interface copy such as buttons, errors, forms and onboarding, using four quality standards and accessibility guidance.

    224 GitHub starsUsed in 1 repo~3.8k tokens
    Writing & ContentAuto-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 14 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 14 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 14 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 14 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 14 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 14 days ago
    Auto-check passed

Categories

Questions about Colm Writing Style

What does Colm Writing Style do?

A skill your agent uses when drafting or revising COLM paper prose — leading with a finding about language models rather than a leaderboard delta, scoping claims to tested models and scales, naming…. Colm Writing Style is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when drafting or revising COLM paper prose — leading with a finding about language models rather than a leaderboard delta, scoping claims to tested models and scales, naming versions in text, keeping the 9-page main text self-sufficient, and matching the measured, analysis-forward voice of COLM's award lineage.

When should I use Colm Writing Style?

Colm Writing Style fits situations like: revising COLM paper prose — leading with a finding about language models rather than a leaderboard delta; scoping claims to tested models and scales; naming versions in text; keeping the 9-page main text self-sufficient.

How do I install Colm Writing Style in Claude Code?

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

How do I install Colm Writing Style in Codex?

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

Can I use Colm Writing Style 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-writing-style -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-writing-style, .gemini/skills/colm-writing-style, .github/skills/colm-writing-style and .opencode/skills/colm-writing-style in your project.

What does Colm Writing Style need to run?

SKILL.md names no scripts, command-line tools or credentials: Colm Writing Style is instructions for the agent only.

Does Colm Writing Style 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 Colm Writing Style 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 Writing Style use?

Colm Writing Style 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 Writing Style 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 Writing Style?

Skills that share tags, products or a category with Colm Writing Style: Avoid AI Writing (conorbronsdon/avoid-ai-writing, 4.9k stars), Brand (Ohh-889/skyroc, 795 stars), Khazix WeChat Article Writer (KKKKhazix/khazix-skills, 21k stars) and Writing Guidelines (vercel-labs/agent-skills, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Colm Writing Style?

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.