agentmods.dev

demo.create_pictures

demo.create_pictures is a skill for Claude Code from gpsaggese/helpers. It costs 13 tokens per session (369 once invoked), scanned A, original, Apache-2.0.

An image-prompt writing procedure for presentation storyboards. It creates one detailed prompt per slide for a separate image-generation tool and saves the prompts in a Markdown file.

In plain words
What is it for?
Use it to prepare clean, simple illustrations for each storyboard slide, including style, camera, layout, and limits on visual complexity.
Why use it?
It turns slide content into consistent visual instructions without requiring the image tool to interpret the storyboard directly.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is > ./helpers_root/dev_scripts_helpers/documentation/generate_images.py \.

not rated 158repo +1 today A scan 13 tokens original Apache-2.0

Good fit Use it to prepare clean, simple illustrations for each storyboard slide, including style, camera, layout, and limits on visual complexity.

Compare 6 skills from other repositories ↓
View source ↗ gpsaggese/helpers
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/gpsaggese/helpers
agentmods
npx agentmods add skills/gpsaggese/helpers/demo.create_pictures

Made for: Claude Code.

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 demo.create_pictures

README.md
[![agentmods](https://agentmods.dev/badge/skills/gpsaggese/helpers/demo.create_pictures/github.svg)](https://agentmods.dev/skills/gpsaggese/helpers/demo.create_pictures)
Your own site
<a href="https://agentmods.dev/skills/gpsaggese/helpers/demo.create_pictures"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/demo.create_pictures/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 demo.create_pictures

Your own site · 80×15
<a href="https://agentmods.dev/skills/gpsaggese/helpers/demo.create_pictures"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/demo.create_pictures.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 369 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 $0.00013 $0.00369
Opus 5.5 $0.00005 $0.00148
Sonnet 5.5 $0.00003 $0.00074
Haiku 4.5 $0.00001 $0.00037

Measured yesterday against content hash ca0ffe7492db, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

demo.create_pictures 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 yesterday.

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.

.claude/skills/demo.create_pictures/SKILL.md · 47 lines

What it actually says

Goal

  • Given the text of a storyboard for a presentation, generate an image prompt for each slide and save the result to demo_images.md

Workflow

Generate Image Prompts

  • For each slide, write a prompt in this format, with <DESCRIPTION> filled in: 
    CHARACTERS
<DESCRIPTION>

STYLE ANCHOR:
Clean, modern vector-illustration style, flat colors, soft gradients, consistent
lighting, no harsh shadows, slightly rounded shapes, minimal detail, professional
corporate look, designed for a slide deck, white background, high contrast, 16:9
aspect ratio, no text, no watermark.

SETTINGS:
- No photorealistic elements or textures
- No slide titles, headers, or explanatory text blocks
- No decorative elements that don't serve the concept
- No complex scenes with many small details
- Minimize the number of distinct elements (5-7 maximum per image)

CAMERA: Medium shot, straight-on.

Create the Output File

  • Write the prompts to demo_images.md, for use with this command: 
    > ./helpers_root/dev_scripts_helpers/documentation/generate_images.py \
   -i demo_images.md \
   --dst_dir demo_images.md.figs

Verification

  • Confirm demo_images.md has one prompt per storyboard slide
  • Confirm each prompt follows the CHARACTERS / STYLE ANCHOR / SETTINGS / CAMERA format
  • Run generate_images.py against demo_images.md and confirm it succeeds
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. yesterday First seen · 47 lines · 13 tokens per session scan A ca0ffe7492db

Subscribe to this mod's changes

demo.create_pictures is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 369 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-06.

Creative and media
Related

demo.create_pictures compared with skills from other repositories

demo.create_pictures next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
demo.create_picturesgpsaggese/helpersSkill158todayApache-2.0A13Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex