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.
npx skills add PicsArt/gen-ai-skills --skill style-guide-buildergit clone --depth 1 https://github.com/PicsArt/gen-ai-skillsWrote 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.
[](https://agentmods.dev/skills/picsart/gen-ai-skills/style-guide-builder)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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:
- How does this style render the things I can see? A tiger, a kitchen, a face.
- 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.
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.
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.
- 11d ago First seen · 339 lines · 14 tokens per session scan A aff5aeba8ef3
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.
Other skills, from other repositories
infographic-creator
Create beautiful infographics based on given text content. Use when users request to create infographics.
ppt-orchestrator
A dispatcher for creating presentations, slide decks, long images, and weekly reports. It chooses a visual style and output format, then sends the work to a more specialised add-on.
zhongguose-html-skill
An HTML-only presentation system using traditional Chinese colours and Chinese-style visual design. It helps organise source material into a report structure and produces a self-contained HTML file with its assets.
svg-art
Generates artistic SVGs directly as code — minimal line icons, geometric marks, generative patterns, or hand-drawn compositions — and assembles a modern 2026 HTML gallery preview. Saves each session to its own semantically named folder on the Desktop. Learns from feedback: which styles you loved, which compositions…
deck-guizang-editorial
Editorial magazine meets e-ink: 10 layouts and 5 palettes (Ink, Indigo Porcelain, Forest Ink, Kraft Paper, Dune).
deck-swiss-international
16-column grid, one saturated accent, and 22 locked layouts (Klein Blue, Lemon, Mint, Safety Orange).