style-guide-builder

style-guide-builder is a skill for Claude Code from PicsArt/gen-ai-skills. It costs 14 tokens per session (4,141 once invoked), scanned A, original, MIT.

A method for turning reference images into a reusable written description of their visual style. The result is a set of Markdown files that can guide new images or videos in the same visual world.

In plain words
What is it for?
Analyzing screenshots or image collections, defining a visual identity, and preparing style guidance for future generated artwork.
Why use it?
It separates recurring design choices from details that appear in only one image, making visual consistency easier to maintain.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the picsart plugin — 23 skills, 2 MCP servers shipped together

Good fit Analyzing screenshots or image collections, defining a visual identity, and preparing style guidance for future generated artwork.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/picsart/gen-ai-skills/style-guide-builder
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.

Any agent
npx skills add PicsArt/gen-ai-skills --skill style-guide-builder
Clone the repo
git clone --depth 1 https://github.com/PicsArt/gen-ai-skills

Made for: Claude Code.

Or install picsart, the plugin that ships this one along with the rest of its 23 skills, 2 MCP servers.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for style-guide-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/picsart/gen-ai-skills/style-guide-builder/github.svg)](https://agentmods.dev/skills/picsart/gen-ai-skills/style-guide-builder)
Your own site
<a href="https://agentmods.dev/skills/picsart/gen-ai-skills/style-guide-builder"><img src="https://agentmods.dev/badge/skills/picsart/gen-ai-skills/style-guide-builder/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for style-guide-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/picsart/gen-ai-skills/style-guide-builder"><img src="https://agentmods.dev/badge/skills/picsart/gen-ai-skills/style-guide-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,141 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00014 $0.04141
Opus 5 $0.00007 $0.02070
Sonnet 5 $0.00003 $0.00828
Haiku 4.5 $0.00001 $0.00414

Measured 11d ago against content hash aff5aeba8ef3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

style-guide-builder scanned grade A with 0 findings 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 11d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/style-guide-builder/SKILL.md · 339 lines

How it starts

The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Style Guide Builder

You take reference images and produce a style guide: a set of markdown files that describe a look precisely enough for someone, or another skill, to generate new work that belongs in the same world.

You are not writing a caption per image. Captions are worthless for this. The value is in what is consistent across the set, separated from what happens to be true of one frame.

When to Use

Use when the user has reference images and wants a reusable visual style captured from them, so new images or video can be generated to match. Trigger phrases include "make a style guide from these", "I want a cartoon that looks like this", "match this style", "analyze these references", "extract the style from these screenshots", "build a theme from these images", "create a look book", "define our visual identity from these", "keep everything consistent with these references", "I took screenshots from a show I like", "generate more images in this style", "what style is this", "describe these images for prompting", "turn these frames into a style". Also use when a user drops a folder of images and asks what to do with them.

The output is a set of markdown files that other skills read, not a single description.

The usual case: a user has screenshots from a cartoon, a game, a brand campaign or a film, and wants new material that looks like it came from the same production. They will later generate things that are not in the references at all, and it still has to match. So the guide has to answer two different questions:

  1. How does this style render the things I can see? A tiger, a kitchen, a face.
  2. How would this style render something I cannot see? A pig, a bus stop, a crowd.

The second question is the one that makes a style guide useful rather than decorative, and most of the work goes into it. See references/extrapolation.md.

If the user asks for a brand system rather than a look derived from references, that is agency-brand-scoping and the brandkit tooling, not this.

Read the full file on GitHub · 339 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 339 lines · 14 tokens per session scan A aff5aeba8ef3

Subscribe to this mod's changes

style-guide-builder is a skill published in the GitHub repository PicsArt/gen-ai-skills (4 stars, last pushed 14d ago), licensed MIT. It adds 14 tokens to every session and 4,141 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.