visual-research

A process for researching and comparing a brand’s visual identity, including its logos, colors, imagery, and design patterns.

In plain words
What is it for?
Use it to audit a competitor’s branding, compare design language, study positioning, and create a 13-section HTML visual research report.
Why use it?
It gathers visual evidence and organizes it into a structured report, making it easier to understand how competing brands present themselves.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/danpeg/visual-research/visual-research
Any agent
npx skills add danpeg/visual-research --skill visual-research
Clone the repo
git clone --depth 1 https://github.com/danpeg/visual-research

Made for: Claude Code, Codex.

Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,677 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00116 $0.08677
Opus 5 $0.00058 $0.04339
Sonnet 5 $0.00023 $0.01735
Haiku 4.5 $0.00012 $0.00868

Measured 2d ago against content hash 09223dba67c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

visual-research scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `curl` — Instagram API calls, direct image downloads. Pre-installed on macOS/Linux.
SKILL.md · 643 lines

How it starts

The opening of the file, as written. The whole thing — 643 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual Research

Full-pipeline skill for researching a brand's visual identity, capturing imagery from every available source, and packaging it into a branded HTML report with a 13-section competitive analysis.

Setup

Before starting, check available tools and build a capabilities report.

Required:

  • curl — Instagram API calls, direct image downloads. Pre-installed on macOS/Linux.

Recommended (API keys):

Key What it powers Phase Fallback
GEMINI_API_KEY Gemini Vision — color extraction, composition analysis from captured images Analyze Claude's built-in vision via Read tool. Good quality, Gemini preferred for batch processing

Check: echo $GEMINI_API_KEY

Optional (CLI tools):

Tool What it powers Phase Install Fallback
Playwright Full-page screenshots of websites, social grids, app stores Capture npx playwright install chromium web_fetch for text content. Loses visual capture
yt-dlp YouTube/TikTok video thumbnails Extract pip3 install yt-dlp web_search for campaign stills from press
Scrapling Anti-bot scraping for protected sites Capture/Extract pip3 install scrapling web_fetch — works for most sites

Check each: which playwright, which yt-dlp, python3 -c "import scrapling" 2>/dev/null && echo ok

Setup behavior:

  1. Check each prerequisite and report what's available

  2. For missing items, explain what the user loses and how to install

  3. If anything is missing, STOP and wait for the user to confirm before proceeding. Present a clear summary like:

    Ready:     Playwright, yt-dlp, curl
    Missing:   GEMINI_API_KEY (vision analysis will use Claude instead)
               Scrapling (will use web_fetch fallback)
    
    Install now, or proceed with what's available?
    

    Do NOT continue to Phase 1 until the user explicitly says to proceed.

    If everything is available, report the green status and proceed directly to Phase 1 — no confirmation needed.

  4. Record the capabilities in the output document's Setup section

Read the full file on GitHub · 643 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 643 lines · 116 tokens per session scan A 09223dba67c9

Subscribe to this mod's changes

visual-research is a skill published in the GitHub repository danpeg/visual-research (3 stars, last pushed 5mo ago), licensed MIT. It adds 116 tokens to every session and 8,677 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

logo-design

Design or evaluate a logo against the SAD bar — Simple, Appropriate, Distinct — always judged in context. Use when designing a new mark, refining one, or assessing whether an existing logo is any good. Triggers on 'logo,' 'wordmark,' 'brandmark,' 'mark,' 'monogram,' 'favicon/app icon,' 'is our logo good,' 'redesign…

zstvns/design-skills · 112 tokens

build-startup-brand

Turn a startup idea, product, URL, pitch, or existing visual identity into a distinctive startup brand system and a polished standalone HTML report. Use when Codex needs to create or refine startup positioning, a salient brand idea, brand promise, tagline, messaging, voice, creative territories, logo or symbol…

Kappaemme-git/build-startup-brand · 105 tokens

linkedin-carousel

Creates the slides of a LinkedIn carousel, both kinds. Use when the user wants a "LinkedIn carousel", a "LinkedIn document post", a "LinkedIn PDF carousel", a "LinkedIn carousel ad" or "several slides that swipe" for a LinkedIn project. Two paths, and the choice is asked rather than assumed. Either an organic document…

roslove44/brand-artisan · 149 tokens

facebook-carousel

Creates the cards of a Facebook carousel ad at Meta's dimensions, as a series of coherent visuals. Use when the user wants a "Facebook carousel", a "carousel ad" or "several cards that swipe" for a project. Produces N .tsx templates (one card = one PNG) in a dedicated subfolder, sharing a common theme, aligned with…

roslove44/brand-artisan · 89 tokens

facebook-page

Creates the visuals for a Facebook Page (profile photo = the brand, and cover photo) at Facebook's official dimensions. Use when the user wants a "Facebook profile photo", a "Facebook cover", a "Facebook page banner" or "the FB page logo" for a project. Produces one or two .tsx templates at the sizes Facebook imposes…

roslove44/brand-artisan · 112 tokens

new-template

Scaffolds a new visual (.tsx) in an existing BrandArtisan project, aligned with its brand.md guidelines. Use when the user wants to create a new image/cover/banner/OG in a project ("new visual", "add a cover for X", "create the OG for Y"). Always reads brands/ /brand.md and refuses if it is missing.

roslove44/brand-artisan · 78 tokens