A skill your agent uses when drafting or revising the prose and figures of an ICCV paper, covering writing for an international generalist reviewer pool, the inclusive 8-page economy…

MITAuto-check passedWriting & Content

Install Iccv Writing Style

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

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

GitHub CLI
$ gh skill install brycewang-stanford/Awesome-Journal-Skills iccv-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/ICCV-Skills/skills/iccv-writing-style .claude/skills/iccv-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
iccv-writing-style
GitHub stars
1.2k
Token cost
~1.7k tokens
SKILL.md length
792 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 the prose and figures of an ICCV paper, covering writing for an international generalist reviewer pool, the inclusive 8-page economy…

  • Revising the prose and figures of an ICCV paper
  • SKILL.md covers Write for the generalist, cite…, The inclusive-8-pages economy, Mechanism-first sentences and Claims sized for a one-page…, plus 5 more sections
  • Calls pdftotext
  • Covering writing for an international generalist reviewer pool

What it does

Iccv Writing Style is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when drafting or revising the prose and figures of an ICCV paper, covering writing for an international generalist reviewer pool, the inclusive 8-page economy, mechanism-first exposition, calibrated claims that survive a one-page rebuttal cycle, and captions and figures that carry the paper for readers who skim first.

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 the prose and figures of an ICCV paper
  • Covering writing for an international generalist reviewer pool
  • The inclusive 8-page economy
  • Mechanism-first exposition

Example prompts

  • “/iccv-writing-style”

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:

    • pdftotext

    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

Iccv Writing Style loads about 1.7k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 792 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
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). 792 words, ~1,716 tokens.

Download SKILL.mdSave it as .claude/skills/iccv-writing-style/SKILL.md (or your agent's skills folder).
name
iccv-writing-style
description
Use when drafting or revising the prose and figures of an ICCV paper, covering writing for an international generalist reviewer pool, the inclusive 8-page economy, mechanism-first exposition, calibrated claims that survive a one-page rebuttal cycle, and captions and figures that carry the paper for readers who skim first.

ICCV Writing Style

An ICCV submission is read by reviewers drawn from the most international pool in computer vision — in 2025, every author of 11,239 submissions was also a potential reviewer — and most of them work outside your subfield. The style target is therefore precise: a paper a generalist vision researcher can evaluate fairly in one sitting, in their second or third language, under deadline pressure of their own.

Write for the generalist, cite for the specialist

The three reviewers you draw will rarely all be specialists in your niche. Concretely:

  • Define subfield jargon at first use, in one clause, even terms your lab considers standard ("the chamfer-L1 metric, i.e. average nearest-neighbor distance in both directions").
  • Make the method's mechanism explainable to an adjacent-area reviewer: what information flows where, and what would break without it. Specialists verify details; generalists score the story — you need both.
  • Prefer short declarative sentences. Non-native readers (and tired native ones) lose subordinate-clause chains; ICCV's reviewer pool is global by construction, and prose that filters readers filters scores.

The inclusive-8-pages economy

The cap is eight pages including figures and tables, references-only overflow (2025 rule). Treat layout as a market where every element bids for space with the evidence it delivers:

ElementEarns its space whenEvict when
Page-1 overview figureA stranger states the idea after 30 seconds with itIt needs the body text to decode
Pipeline figureIt replaces ≥ its own height in method proseIt restates the obvious encoder→decoder
Main results tableRows = strongest current baselines, matchedPadded with weak ancient rows for bulk
Qualitative stripShows the mechanism's visible signatureGeneric pretty outputs any method makes
Ablation tableEach row flips one switch (iccv-experiments)Grid dumped without a takeaway sentence
Equation blockNotation reused ≥ twice downstreamFormalizing what one sentence says

Every caption must be self-sufficient — dataset, setting, and the takeaway in words — because the skim pass reads only captions, and at most venues in this family the skim pass happens before the real one.

Mechanism-first sentences

The genre's strongest habit: name the mechanism, then the consequence, then the number. Compare the two registers:

text
weak:   "We propose a novel and effective framework that significantly
         outperforms state-of-the-art methods on several benchmarks."
strong: "Replacing per-frame matching with a persistent memory of object
         queries removes the re-detection bottleneck: +3.1 HOTA on
         DanceTrack at identical backbone and training budget."

The weak sentence contains zero checkable content — and at ICCV, unfalsifiable praise adjectives ("novel", "significantly", "state-of-the-art" unscoped) are read as inexperience markers. The strong sentence makes three commitments a reviewer can verify, which is exactly what earns scores.

Claims sized for a one-page defense

Every claim in the abstract will potentially need defending in May inside a shared, single rebuttal page (iccv-author-response). Size claims accordingly at writing time:

  • Scope superlatives to dataset + protocol + budget class, in the sentence itself, not a footnote.
  • If generalization is claimed, the paper must contain the cross-domain table that backs it; otherwise claim the domains you tested.
  • Put the limitation you know about into the limitations paragraph before reviewers find it — a self-reported failure costs a sentence; a discovered one costs a score point and rebuttal real estate.
  • Never let the intro promise what the conclusion doesn't deliver: read the contributions bullets against the conclusion as a final pass; they should be the same statements at two altitudes.
Show full SKILL.md (277 more words)Show less

Structure that survives skim-order reading

Reviewers at volume venues read out of order: abstract → figures → tables → conclusion → (maybe) everything else. Two consequences. First, the paper's argument must be reconstructible from abstract + captions + table headers alone — test this literally by extracting them:

bash
# Skim-pass simulator: what a reviewer sees in the first five minutes
pdftotext -layout paper.pdf - | grep -A2 -E '^(Figure|Table) [0-9]+[.:]' > skim.txt
head -60 skim.txt   # does this sequence state problem → idea → evidence?

Second, transitions between sections carry less weight than section openings: begin each section with its conclusion ("Our decoder attends over a persistent memory; this section details the write and read operations"), not with throat- clearing history.

Introduction in five moves

The ICCV intro that works is a proof sketch, not a literature tour: (1) the visual capability at stake, one paragraph, concrete; (2) why current approaches miss it — mechanism of failure, not adjectives; (3) the idea, stated so a generalist could re-derive the design; (4) evidence preview with scoped numbers; (5) contributions as claims (each one falsifiable), not as an activity log ("we conduct extensive experiments" is an activity, not a contribution).

Language-level pass, last

Only after structure settles: strip hedge stacks ("could potentially help to"), convert passive method descriptions to active ("the features are fused" → "the decoder fuses"), unify tense (present for the method, past for experiments run), and hunt duplicated notation — vision papers accumulate three symbols for the same feature map by section 4. If any drafting was machine-assisted, verify every citation exists and every number matches your tables; author responsibility for the text is absolute, and fabricated references are review-killing at every CVF venue.

Reverify each cycle

  • Page cap and reference-overflow wording in the 2027 author kit.
  • Any new required sections (limitations, ethics, disclosure statements — none verified for 2025, 待核实 for 2027).
  • Template version pinned to the current cycle's official kit.

Output format

text
[Generalist test] adjacent-area reader states the idea after p.1: yes/no
[Space market] elements not earning their area: <list>
[Caption audit] self-sufficient: n/m
[Claim sizing] unscoped superlatives: <locations>
[Skim pass] abstract+captions+headers carry the argument: yes/no
[Edit queue] <highest score-impact 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 ICCV-Skills/skills/iccv-writing-style of brycewang-stanford/Awesome-Journal-Skills.

Open the folder on GitHubat commit 932eb23

Compare with similar skills

Iccv 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.

Iccv Writing Style compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Iccv 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

Questions about Iccv Writing Style

What does Iccv Writing Style do?

A skill your agent uses when drafting or revising the prose and figures of an ICCV paper, covering writing for an international generalist reviewer pool, the inclusive 8-page economy…. Iccv Writing Style is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when drafting or revising the prose and figures of an ICCV paper, covering writing for an international generalist reviewer pool, the inclusive 8-page economy, mechanism-first exposition, calibrated claims that survive a one-page rebuttal cycle, and captions and figures that carry the paper for readers who skim first.

When should I use Iccv Writing Style?

Iccv Writing Style fits situations like: revising the prose and figures of an ICCV paper; covering writing for an international generalist reviewer pool; the inclusive 8-page economy; mechanism-first exposition.

How do I install Iccv Writing Style in Claude Code?

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

How do I install Iccv Writing Style in Codex?

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

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

What does Iccv Writing Style need to run?

Going by SKILL.md and its folder, Iccv Writing Style needs the command-line tools its instructions call (pdftotext).

Does Iccv 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 Iccv 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 Iccv Writing Style use?

Iccv 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 Iccv Writing Style use?

About 1.7k tokens (SKILL.md is roughly 6.9k 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 Iccv Writing Style?

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