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

Cvpr Writing Style

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

A skill your agent uses when writing or revising a CVPR paper's prose and figures, covering the 8-page budget where figures and tables count against the limit, the page-1 teaser figure convention…

MITAuto-check passedBusiness, Finance & HR

Install Cvpr Writing Style

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

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

GitHub CLI
$ gh skill install brycewang-stanford/Awesome-Journal-Skills cvpr-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/CVPR-Skills/skills/cvpr-writing-style .claude/skills/cvpr-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
cvpr-writing-style
GitHub stars
1.2k
Token cost
~1.6k tokens
SKILL.md length
740 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 CVPR paper's prose and figures, covering the 8-page budget where figures and tables count against the limit, the page-1 teaser figure convention…

  • Works in 6 steps: Task + failure: the specific visual… → Cause: the mechanism behind the failure,… → Method: what you built, named, with its… → …
  • Revising a CVPR papers prose and figures
  • SKILL.md covers The two-pass reader, Budgeting eight inclusive pages, Sentence-level norms of the… and Claim calibration, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Cvpr Writing Style is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when writing or revising a CVPR paper's prose and figures, covering the 8-page budget where figures and tables count against the limit, the page-1 teaser figure convention, benchmark-table craft, claim calibration for a skeptical vision audience, and taking responsibility for tool-assisted text under CVPR's rules.

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 Business, Finance & HR, covering Brand voice and tone and Performance reviews. 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 CVPR papers prose and figures
  • Covering the 8-page budget where figures and tables count against the limit
  • The page-1 teaser figure convention
  • Benchmark-table craft

Example prompts

  • “/cvpr-writing-style”

Workflow steps

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

  1. Task + failure: the specific visual problem and where current methods break
  2. Cause: the mechanism behind the failure, in one clause — this sentence is what
  3. Method: what you built, named, with its one central idea.
  4. Headline evidence: the scoped number ("+2.1 AP on COCO, matched backbone").
  5. Breadth or cost: second dataset, transfer result, or the efficiency figure.
  6. Availability: what will be released (code/models/data — and remember datasets

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

Cvpr Writing Style loads about 1.6k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 740 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
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). 740 words, ~1,562 tokens.

Download SKILL.mdSave it as .claude/skills/cvpr-writing-style/SKILL.md (or your agent's skills folder).
name
cvpr-writing-style
description
Use when writing or revising a CVPR paper's prose and figures, covering the 8-page budget where figures and tables count against the limit, the page-1 teaser figure convention, benchmark-table craft, claim calibration for a skeptical vision audience, and taking responsibility for tool-assisted text under CVPR's rules.

CVPR Writing Style

CVPR is a visual venue with a brutal budget: eight pages including figures and tables (references overflow free — verified 2026 rule). The papers that survive triage by an overloaded reviewer pool are the ones a reader can evaluate in two passes: a 90-second flip through figures and tables, then a real read. Write both passes on purpose.

The two-pass reader

Pass one is visual. Reviewers at a 16k-submission venue flip: Figure 1, the tables, the qualitative grid, the ablation. If that flip communicates problem → idea → win, the close read starts friendly. Concretely:

  • Figure 1 (the teaser) sits on page 1 and must state the paper alone: task, what prior work gets wrong, what yours does instead — ideally on the same input. A teaser that needs the caption's third sentence has failed.
  • Every caption is self-contained: dataset, metric, and the takeaway sentence. Flip readers never see body text.
  • The main table is typeset as an argument: best numbers bold, second-best underlined, methods grouped by supervision/backbone class, your row where the eye lands last.

Budgeting eight inclusive pages

SectionTypical shareCompression lever
Title/abstract/teaser~1 pageTeaser earns its half page or shrinks
Intro~1 pageContributions as 3 bullets, no history lesson
Related work~0.75 pagePosition, don't survey (see cvpr-related-work)
Method + pipeline figure~2 pagesOne figure replacing a page of prose
Experiments~2.5–3 pagesGrids to supplement; keep the decisive ablation
Limitations/conclusion~0.25–0.5 pageHonest and short

Because figures count, figure design is text editing: a two-column pipeline figure costing 0.6 page must delete at least 0.6 page of method prose, or it is negative space. Cut from the flip-reader's perspective — never cut the ablation table to save a paragraph of adjectives.

Sentence-level norms of the genre

  • Present tense, active voice, mechanism first: "We replace the cost volume with …" beats "In recent years, cost volumes have been widely used…".
  • Name the delta in numbers early: "+2.1 AP on COCO with 40% fewer FLOPs" in the abstract, not "significant improvements".
  • One notation table, introduced once; vision papers drown in re-defined symbols.
  • Kill hype adjectives ("novel", "remarkable", "extensive") — at this venue they mark inexperience; the table is the adjective.

Claim calibration

Vision reviewers are professionally allergic to overclaiming, because the field's benchmark culture makes checking easy:

text
Weak claim, strong paper:
  "Ours improves X on datasets A and B under protocol P with backbone Q."
Strong claim, dead paper:
  "Ours solves X"  /  "generalizes to real-world scenes"   (shown on 2 curated clips)
  "state-of-the-art"                      (on one dataset, vs. year-old baselines)
  "real-time"                             (no hardware named — CRF row contradicts you)

Every superlative must name its scope: dataset, protocol, compute class. If a limitation is visible in your own qualitative grid, write it in the limitations paragraph first — reviewers reward the paper that scoops its own weaknesses.

Show full SKILL.md (326 more words)Show less

Tool-assisted text is your text

The verified 2026 author-side rule: use whatever tools you like, but fabricated citations and factual inaccuracies are rejection grounds — possibly without review — and "an LLM did it" is explicitly no defense. Operational habit: any machine-drafted paragraph gets a human pass for (a) citations that exist and say what's claimed, (b) numbers matching your own tables, (c) generic filler that flip-readers instantly recognize as padding.

An abstract skeleton that fits the venue

Six sentences carry a CVPR abstract; more usually means the contribution is unclear:

  1. Task + failure: the specific visual problem and where current methods break ("Trackers lose identity during occlusions longer than their temporal horizon").
  2. Cause: the mechanism behind the failure, in one clause — this sentence is what separates insight papers from tweak papers.
  3. Method: what you built, named, with its one central idea.
  4. Headline evidence: the scoped number ("+2.1 AP on COCO, matched backbone").
  5. Breadth or cost: second dataset, transfer result, or the efficiency figure.
  6. Availability: what will be released (code/models/data — and remember datasets claimed as contributions carry a camera-ready release obligation).

Write the abstract twice: once before the experiments as a plan, once after as a report; the diff between the two is your overclaiming audit.

Revision protocol for a drafted paper

  1. Print the figures and tables alone; run the 90-second flip test on a colleague outside the project.
  2. Reconcile abstract numbers against tables (rebuttal-week embarrassment prevention).
  3. Hunt "see supplement" pointers that hide decision-critical logic; pull those back.
  4. Delete the roadmap paragraph ("Section 2 reviews…") — page-limited venues stopped reading them years ago.
  5. Read the intro's last bullet against the conclusion: the promised contribution and the delivered one must be the same sentence.

Reverify each cycle

  • Page cap and the references-only overflow rule.
  • Template/author-kit version (build from the current cvpr-org/author-kit).
  • Any new writing-adjacent form fields (limitations sections, AI-use disclosures — none verified for 2026, 待核实 for later cycles).

Output format

text
[Flip test] passes / fails at: <figure or table>
[Budget] pages by section vs 8.0 incl. figures
[Claim audit] superlatives without scope: <list>
[Caption audit] non-self-contained: <figure numbers>
[Tool-text risk] unverified citations or numbers: <locations>
[Edit order] <highest-leverage cuts first>

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

Open the folder on GitHubat commit 932eb23

Compare with similar skills

Cvpr 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.

Cvpr Writing Style compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cvpr Writing Style this skillbrycewang-stanford/Awesome-Journal-Skills1.2k—~1.6kAutomated safety check: PassMIT
Cc Writing Stylefranklee16/academic-research-skills2231 repos~1kAutomated safety check: PassNone
AI Indexmizchi/skills360—~3.6kAutomated safety check: PassNone
62 Marketing Reviewminhnv0807/ai-business-skills609—~2.1kAutomated safety check: PassMIT
Social Performance Reviewstevenflanagan1/social-ai-team244—~3.7kAutomated safety check: PassNone
Draft In Voicegarrytan/gbrain31k—~3.7kAutomated safety check: PassMIT

Similar skills

  • Cc Writing Style

    franklee16/academic-research-skills

    A skill your agent uses when polishing prose for a Cancer Cell (Cell Press) manuscript — the Summary/Introduction/Results/Discussion craft, claim calibration, and Cell Press nomenclature/house style.

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

  • AI Index

    mizchi/skills

    Method and tooling for measuring how AI-generated a piece of prose reads, in Japanese or English.

    360 GitHub stars~3.6k tokensUpdated 9 days ago
    Business, Finance & HRAuto-check passed

  • 62 Marketing Review

    minhnv0807/ai-business-skills

    Dung khi leader phai DUYET output CHU cua team truoc khi trien khai — content brief co dung insight va dung pillar khong, CTA co ro khong; ads copy va creative co proof cho claim khong, dung tone…

    609 GitHub stars~2.1k tokensUpdated 29 days ago
    Business, Finance & HRAuto-check passed

  • Social Performance Review

    stevenflanagan1/social-ai-team

    Monthly social media performance review for SMBs. An agent skill from stevenflanagan1/social-ai-team.

    244 GitHub stars~3.7k tokensUpdated 4 days ago
    Business, Finance & HRAuto-check passed

  • Draft In Voice

    garrytan/gbrain

    Ghostwrite content in a specific person's voice from a VALIDATED voice profile — tweets, replies, short posts, launch copy, recruiting blurbs, emails.

    31k GitHub stars~3.7k tokensUpdated yesterday
    Writing & ContentAuto-check passed

  • 62 Marketing Review Global

    minhnv0807/ai-business-skills

    A skill your agent uses when a leader must review or approve TEXT-based team output before it ships — content briefs checked for angle, pillar, and CTA, ad copy and creative checked for…

    609 GitHub stars~2.5k tokensUpdated 29 days ago
    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 Cvpr Writing Style

What does Cvpr Writing Style do?

A skill your agent uses when writing or revising a CVPR paper's prose and figures, covering the 8-page budget where figures and tables count against the limit, the page-1 teaser figure convention…. Cvpr Writing Style is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when writing or revising a CVPR paper's prose and figures, covering the 8-page budget where figures and tables count against the limit, the page-1 teaser figure convention, benchmark-table craft, claim calibration for a skeptical vision audience, and taking responsibility for tool-assisted text under CVPR's rules.

When should I use Cvpr Writing Style?

Cvpr Writing Style fits situations like: revising a CVPR papers prose and figures; covering the 8-page budget where figures and tables count against the limit; the page-1 teaser figure convention; benchmark-table craft.

How do I install Cvpr Writing Style in Claude Code?

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

How do I install Cvpr Writing Style in Codex?

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

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

What does Cvpr Writing Style need to run?

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

Does Cvpr 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 Cvpr 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 Cvpr Writing Style use?

Cvpr 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 Cvpr Writing Style use?

About 1.6k tokens (SKILL.md is roughly 6.2k 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 Cvpr Writing Style?

Skills that share tags, products or a category with Cvpr Writing Style: Cc Writing Style (franklee16/academic-research-skills, 223 stars), AI Index (mizchi/skills, 360 stars), 62 Marketing Review (minhnv0807/ai-business-skills, 609 stars) and Social Performance Review (stevenflanagan1/social-ai-team, 244 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cvpr 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.