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

Corl Writing Style

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

A skill your agent uses when writing or revising a CoRL paper's prose — leading with the embodied task and the learned component, calibrating claims to evaluation scale, writing the mandatory…

MITAuto-check passedWriting & Content

Install Corl Writing Style

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

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

GitHub CLI
$ gh skill install brycewang-stanford/Awesome-Journal-Skills corl-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/CoRL-Skills/skills/corl-writing-style .claude/skills/corl-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
corl-writing-style
GitHub stars
1.2k
Token cost
~1.6k tokens
SKILL.md length
708 words
Files
1
Skills in repo
2,387
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when writing or revising a CoRL paper's prose — leading with the embodied task and the learned component, calibrating claims to evaluation scale, writing the mandatory…

  • Works in 4 steps: What does the robot do that it couldn't… → What is learned, and what is engineered… → What is the evidence scale? (tasks ×… → …
  • Revising a CoRL papers prose — leading with the embodied task and the learned component
  • SKILL.md covers The opening contract, Claim calibration — the…, The Limitations section: write… and Structure for an 8-page body, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Corl Writing Style is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when writing or revising a CoRL paper's prose — leading with the embodied task and the learned component, calibrating claims to evaluation scale, writing the mandatory Limitations section as a scored asset, fitting the argument into 8 pages, and satisfying a dual reviewer audience of ML and robotics readers.

Its SKILL.md is about 1.6k 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 a CoRL papers prose — leading with the embodied task and the learned component
  • Calibrating claims to evaluation scale
  • Writing the mandatory Limitations section as a scored asset
  • Fitting the argument into 8 pages

Example prompts

  • “/corl-writing-style”

Workflow steps

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

  1. What does the robot do that it couldn't before? (task family, concrete)
  2. What is learned, and what is engineered around it? (policy? reward?
  3. What is the evidence scale? (tasks × seeds × episodes; sim, real, or both)
  4. Why does this generalize beyond the demo? (the transferable insight)

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

Corl Writing Style loads about 1.6k tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 708 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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). 708 words, ~1,603 tokens.

Download SKILL.mdSave it as .claude/skills/corl-writing-style/SKILL.md (or your agent's skills folder).
name
corl-writing-style
description
Use when writing or revising a CoRL paper's prose — leading with the embodied task and the learned component, calibrating claims to evaluation scale, writing the mandatory Limitations section as a scored asset, fitting the argument into 8 pages, and satisfying a dual reviewer audience of ML and robotics readers.

CoRL Writing Style

A CoRL paper is read by two audiences at once: reviewers fluent in learning methods who will probe the algorithmic claim, and reviewers fluent in robots who will probe the physical claim. Prose that serves only one of them loses the other's score. The style guidance here is about keeping both readers oriented inside 8 pages — with a mandatory Limitations section spending part of that budget (CoRL 2026 instructions, corl.org, read 2026-07-08).

The opening contract

By the end of page 1, both audiences should be able to answer four questions:

  1. What does the robot do that it couldn't before? (task family, concrete)
  2. What is learned, and what is engineered around it? (policy? reward? representation? data?)
  3. What is the evidence scale? (tasks × seeds × episodes; sim, real, or both)
  4. Why does this generalize beyond the demo? (the transferable insight)

A reliable abstract shape: task problem → why existing learning approaches fall short → the idea in one sentence → headline evidence with its scale attached ("across 8 manipulation tasks, 5 seeds, 50 evaluation episodes each, on a real UR5") → the takeaway for the field.

Claim calibration — the venue's core stylistic norm

Robot-learning results are stochastic and setup-dependent; the writing must carry those qualifiers without drowning in them. Calibrate at the sentence level:

OverclaimedCalibrated
"Our policy solves kitchen manipulation""Our policy reaches 76% mean success on the 6-task kitchen suite"
"Transfers seamlessly to the real world""Transfers with an 11-point average sim-to-real drop (Table 4)"
"Generalizes to unseen objects""Maintains 61% success on 10 held-out objects (vs 78% on training objects)"
"Runs in real time""Runs at 15 Hz on the onboard Orin"
"Robust to disturbances""Recovers from 8 of 12 scripted pushes (protocol in §5.3)"

The pattern: attach the number, the scale, and the pointer. This is also rebuttal insurance — precise claims are defensible in one page; vibes are not.

The Limitations section: write it as an asset

CoRL makes Limitations mandatory and counts it inside the page limit, which changes its rhetorical status: reviewers treat it as part of the argument, not boilerplate. A strong one:

  • Names specific failure modes observed ("fails on transparent objects; the depth camera returns holes"), matching what the supplementary video shows.
  • States the boundary of the claim ("evaluated on a single embodiment; no cross-robot claim"), which preempts the corresponding review objection.
  • Proposes concrete paths forward, not "future work will explore."

Weak versions — generic ("more experiments needed"), disguised advertising ("limited only by compute"), or contradicted by the video — actively cost points with this reviewer pool.

Show full SKILL.md (285 more words)Show less

Structure for an 8-page body

text
1  Introduction          1.00 pp   the four-question contract
2  Related work          0.75 pp   three-lane positioning (corl-related-work)
3  Method                2.00 pp   one architecture figure; learned vs engineered
                                   boundary drawn explicitly
4  Experimental setup    1.25 pp   tasks, robot/sim, data, baselines, protocol —
                                   the reproducibility spine lives HERE, not appendix
5  Results               2.25 pp   claims in subsection headers; per-axis analysis
6  Limitations           0.50 pp   mandatory; specific; video-consistent
7  Conclusion            0.25 pp   one paragraph
   (references + appendix follow, uncounted)

Adjust the split, but defend two invariants: the setup section is generous (robotics readers judge rigor there), and Limitations is protected (it is mandatory and cutting it to reclaim space is not an option).

Serving the dual audience in the method section

  • Open the method with the interface: observation space, action space, control frequency. ML readers get the problem formalized; robotics readers learn what the policy actually commands.
  • Draw the learned/engineered boundary in one explicit paragraph ("grasp proposals are scripted; the insertion policy is learned"). Blurring this line is the most common honesty complaint in reviews of systems-flavored papers.
  • Prefer one strong figure per idea: an execution filmstrip with per-frame annotations often communicates a robot result faster than any paragraph — but every figure claim needs its number in a table too; filmstrips are anecdotes.
  • Keep notation light and standard (states, actions, observations, policy); a CoRL paper rarely needs custom operator symbols, and every nonstandard symbol taxes half your audience.

Sentence-level habits that survive review

  • Present tense for the method, past tense for the runs you did.
  • "We find" for empirical observations, "we prove/show" reserved for what is actually established at that strength.
  • Numbers with dispersion wherever a mean appears; captions state k seeds × n episodes so tables stand alone when skimmed.
  • Kill demo adjectives ("impressive," "remarkable," "highly robust") — the video either shows it or it isn't so.
  • Acronym hygiene: define at first use; the field's alphabet soup (BC, RL, VLA, MPC, SDF) is not universal across your two audiences.

Revision pass checklist

text
[ ] Page-1 contract: task, learned component, evidence scale, insight
[ ] Every abstract claim → number + scale + section pointer
[ ] Learned vs engineered boundary stated explicitly
[ ] Setup section carries protocol detail (not deferred to appendix)
[ ] Limitations: specific, video-consistent, claim-bounding
[ ] Captions self-contained with seeds × episodes
[ ] No demo adjectives; no uncalibrated robustness language
[ ] Both audiences can follow §3 (interface first, standard notation)

Style norms are community culture; recalibrate against recent accepted papers in the newest PMLR volume (v305 for CoRL 2025) and the live author instructions at corl.org each cycle.

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

Open the folder on GitHubat commit 932eb23

Compare with similar skills

Corl 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.

Corl Writing Style compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Corl Writing Style this skillbrycewang-stanford/Awesome-Journal-Skills1.2k—~1.6kAutomated 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 Corl Writing Style

What does Corl Writing Style do?

A skill your agent uses when writing or revising a CoRL paper's prose — leading with the embodied task and the learned component, calibrating claims to evaluation scale, writing the mandatory…. Corl Writing Style is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when writing or revising a CoRL paper's prose — leading with the embodied task and the learned component, calibrating claims to evaluation scale, writing the mandatory Limitations section as a scored asset, fitting the argument into 8 pages, and satisfying a dual reviewer audience of ML and robotics readers.

When should I use Corl Writing Style?

Corl Writing Style fits situations like: revising a CoRL papers prose — leading with the embodied task and the learned component; calibrating claims to evaluation scale; writing the mandatory Limitations section as a scored asset; fitting the argument into 8 pages.

How do I install Corl Writing Style in Claude Code?

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

How do I install Corl Writing Style in Codex?

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

Can I use Corl 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 corl-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/corl-writing-style, .gemini/skills/corl-writing-style, .github/skills/corl-writing-style and .opencode/skills/corl-writing-style in your project.

What does Corl Writing Style need to run?

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

Does Corl 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 Corl 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 Corl Writing Style use?

Corl 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 Corl Writing Style use?

About 1.6k tokens (SKILL.md is roughly 6.4k 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 Corl Writing Style?

Skills that share tags, products or a category with Corl 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 Corl 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.