Agent skill

Scenario Ideogram

by scenario-labs in scenario-labs/skills

A skill your agent uses when generating or editing images with Ideogram models on Scenario via MCP: posters, logos, menus, packaging, or signage with exact in-image text, editing an image in place…

MITAuto-check passedMedia & Creative

Install Scenario Ideogram

skills CLI
$ npx skills add scenario-labs/skills --skill scenario-ideogram -a claude-code

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

GitHub CLI
$ gh skill install scenario-labs/skills scenario-ideogram --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/scenario-labs/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/scenario-ideogram .claude/skills/scenario-ideogram && 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
scenario-ideogram
GitHub stars
931
Token cost
~2.7k tokens
SKILL.md length
1,385 words
Files
1
Skills in repo
143
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when generating or editing images with Ideogram models on Scenario via MCP: posters, logos, menus, packaging, or signage with exact in-image text, editing an image in place…

  • Works in 7 steps: search with target="models",… → model_schema_get with that id: field… → model_run with that model_id,… → …
  • Editing images with Ideogram models on Scenario via MCP: posters
  • SKILL.md covers Overview, Quick reference, 4.5: tiers, sizes, and what… and Edits that keep the canvas, plus 4 more sections
  • Calls npx

What it does

Scenario Ideogram is an agent skill from scenario-labs/skills. Use when generating or editing images with Ideogram models on Scenario via MCP: posters, logos, menus, packaging, or signage with exact in-image text, editing an image in place while keeping its exact size, transparent PNG generation, background removal that keeps hair and glass edges, editable text layers for localization, or one consistent character from a reference. Keywords: Ideogram 4.5, Precise Edit, V4, V3, typography, aspect ratio, layerize, character reference, inpainting.

Its SKILL.md is about 2.7k 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 Media & Creative, covering Image editing, Internationalization and Logo and visual identity. It works with Model Context Protocol. The repository describes itself as: Get production-ready images, video, audio, and 3D from any AI agent: skills that pick the right model, price before spending, and keep characters and brands consistent through… The licence is MIT.

When your agent uses it

  • Editing images with Ideogram models on Scenario via MCP: posters
  • Signage with exact in-image text
  • Editing an image in place while keeping its exact size
  • Transparent PNG generation

Example prompts

  • “/scenario-ideogram”

Requirements

  • Node.js

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. search with target="models", query="ideogram", public=true. Members return as separate hits; match by name, e.g. model_ideogram-v4-5 for…
  2. model_schema_get with that id: field names, allowed values, and defaults before anything else.
  3. model_run with that model_id, dry_run=true, and parameters={"prompt": "Retro travel poster, warm dusk palette. The headline reads \"KYOTO…
  4. Repeat model_run with wait=false, then jobs_wait with the returned job id, re-called with pending_job_ids on timeout, never a second…
  5. asset_display the outputs and pick one.
  6. To make the copy editable, discover the Layerize member the same way (model_ideogram-v3-layerize-text at authoring time), read its schema…
  7. jobs_wait, then asset_display and asset_download.

What it can do on your machine

Read from SKILL.md and the folder at commit 91caa01. 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:

    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    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

Scenario Ideogram loads about 2.7k tokens when it runs. Until then it costs about 126 tokens; SKILL.md has 1,385 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~126
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k

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 scenario-labs/skills at commit 91caa01, republished under its MIT licence (© scenario-labs). 1,385 words, ~2,664 tokens.

Download SKILL.mdSave it as .claude/skills/scenario-ideogram/SKILL.md (or your agent's skills folder).
name
scenario-ideogram
description
Use when generating or editing images with Ideogram models on Scenario via MCP: posters, logos, menus, packaging, or signage with exact in-image text, editing an image in place while keeping its exact size, transparent PNG generation, background removal that keeps hair and glass edges, editable text layers for localization, or one consistent character from a reference. Keywords: Ideogram 4.5, Precise Edit, V4, V3, typography, aspect ratio, layerize, character reference, inpainting.
license
MIT

Scenario Ideogram Image

Overview

Ideogram's image family on Scenario is a set of single-purpose members, not one model with modes: 4.5 for generation where in-image text must read and for reference-guided edits, 4.5 Precise Edit for changing one thing and leaving the rest alone, V3 Generate Transparent for native alpha output, V3 Layerize Text for turning a flat graphic into editable text layers, Character for one identity held across scenes, and Remove Background for cutouts. V4 still answers searches but was tagged deprecated in favor of 4.5 at authoring time. The members agree on almost nothing mechanically: the same concept changes name, casing, and allowed values between them, so discover each with search and treat its model_schema_get as the contract.

Connection and the core loop: see the scenario skill in this repo; model-agnostic image work (sizing families, reference cardinality, masks): the scenario-image skill; running a bake-off against another family: scenario-model-comparison. If a sibling skill named here is missing from your available skills, ask the user to install it (npx skills add scenario-labs/skills --skill <name>); unattended, proceed from tool schemas and flag the gap.

Quick reference

Pick the member by the job (names from the live schemas, caps at authoring time):

MemberJobInputs that matter
4.5Text-heavy generation, ref editsprompt, referenceImages (up to 5, the first is the source), mask, aspectRatio (auto, source, 25 ratios from 3:1 to 1:3), resolution (1K, 2K), quality, magicPrompt, numOutputs (up to 8)
4.5 Precise EditChange one thing, keep the restimage (output keeps its size), mask, referenceImages (up to 4 guides), quality (default medium), numOutputs (up to 8)
V3 Generate TransparentNative alpha outputprompt, negativePrompt, aspectRatio (15 ratios), renderingSpeed (adds FLASH), expandPrompt, numOutputs (up to 8), seed
V3 Layerize TextFlat graphic to layersimage, optional prompt, fontName* or fontFile* per tier (H1, H2, Body, Small), seed
CharacterSame character, new scenesprompt, characterReferenceImage, styleType (Auto, Fiction, Realistic), aspectRatio or resolution, image plus mask, renderingSpeed (Default, Turbo, Quality), seed
Remove BackgroundCutout to transparent PNGimage (10MB cap)

Nothing transfers between members. Masks flip between them: on 4.5 and Precise Edit white marks the region to edit, on Character black repaints and white stays. Only V3 Transparent takes a negativePrompt. renderingSpeed is uppercase on V3 Transparent and Title case on Character, whose middle tier is Default.

4.5: tiers, sizes, and what they cost

quality is the price dial on both 4.5 members (very_low, low, medium, high; very_low needs an input image, which Precise Edit's image satisfies and 4.5 takes as a referenceImages entry). At authoring time dry_run quoted 7.75, 13.75, and 41.75 CU for low, medium, and high, Precise Edit's very_low 3.75, and the same figure at 1K and 2K and for a 0.4 MP, 4.3 MP, or 8.3 MP source; billed jobs came in 1.75 CU under each estimate. 4.5 defaults to high, its top and most expensive tier; Precise Edit defaults to medium, and its high picks the best of several candidates at three times the price. Tier names do not line up across families: Ideogram's high is its ceiling, while GPT Image 2.5's high is its third tier of five and priced near Ideogram's medium. Compare families at a matched price, never a matched tier name, and dry_run the exact payload.

2K output observed at authoring time: 2048 by 2048 (1:1), 2560 by 1440 (16:9), 2880 by 1440 (2:1), 2944 by 1152 (23:9), 3072 by 1024 (3:1), so the long edge tops out near 3072 and there is no 4K. 1K is about 1 MP (16:9 returned 1280 by 720) and exists only for 1:1, 4:5, 3:4, 2:3, 5:8, 9:16, 1:2 and their landscape counterparts; 3:1 at 1K passes dry_run, then fails at run time with a hint naming the fix. A ratio outside the list (4:1) is a 400 listing the allowed values. A mask requires aspectRatio: "auto".

Edits that keep the canvas

For an edit, aspectRatio: "source" on 4.5 and every Precise Edit run return the source's exact pixel size, even one outside the ratio list: a 1326 by 313 (4.24:1) turnaround sheet came back 1326 by 313 from both, while auto rebuilt it as a full 3072 by 1024 scene. Use this when the edited file must drop back into a layout, a sprite sheet, or a page template unchanged. A localized change such as a headline swap needs no mask on Precise Edit: maskless at the medium default left the rest of the scene untouched. The GPT Image family pads such a source with white bands instead (see scenario-gpt-image).

In a single-sample bake-off at authoring time against GPT Image 2.5 on the same sources, the 4.5 members disturbed two to four times fewer pixels outside the edited region on a sign-text swap and an add-and-remove-objects edit, and read closer to a requested painterly medium (a watercolor restyle, a gouache landscape; hands-on use found the same for pencil sketches). GPT Image 2.5 led on photoreal product shots, on following a character brief, and on material and color changes: asked for burnished gold armor, both 4.5 members returned an olive brass, and Precise Edit also recolored the sword the prompt said to keep. Route by the job, and say "keep everything else exactly the same" plus the list of what must survive in every edit prompt.

Show full SKILL.md (505 more words)Show less

Exact text wants expansion off

The generators rewrite the prompt before generating by default, which helps a short exploratory prompt and hurts the family's specialty: the rewrite can paraphrase the exact copy that must render. When the image carries wording, disable it (magicPrompt: "off" on 4.5, expandPrompt: false on V3 Transparent), quote each piece of copy, and give it a place and a style ('the headline reads "GRAND OPENING" in bold condensed capitals across the top'). magicPrompt applies to text-to-image only: 4.5 turns every edit into structured instructions regardless.

Two routes to transparency

Native: V3 Generate Transparent writes the alpha channel directly, so icons, stickers, and UI elements arrive compositing-ready. Cutout: generate on 4.5, then run Remove Background on the result; it reconstructs edge pixels with partial transparency rather than segmenting, so hair, fur, and glass survive. Go native when the asset is designed as an isolated element; go cutout when typography or overall quality leads. 4.5 has no background field, so prompting "transparent background" there yields an opaque image.

Worked example: a localizable poster

  1. search with target="models", query="ideogram", public=true. Members return as separate hits; match by name, e.g. model_ideogram-v4-5 for typography (a live hit at authoring time: re-discover each session).
  2. model_schema_get with that id: field names, allowed values, and defaults before anything else.
  3. model_run with that model_id, dry_run=true, and parameters={"prompt": "Retro travel poster, warm dusk palette. The headline reads \"KYOTO IN BLOOM\" in bold serif across the top; caption \"April 2027\" bottom right.", "aspectRatio": "9:16", "resolution": "2K", "quality": "high", "magicPrompt": "off", "numOutputs": 2} for the cost estimate.
  4. Repeat model_run with wait=false, then jobs_wait with the returned job id, re-called with pending_job_ids on timeout, never a second model_run.
  5. asset_display the outputs and pick one.
  6. To make the copy editable, discover the Layerize member the same way (model_ideogram-v3-layerize-text at authoring time), read its schema, and model_run with parameters={"image": "<poster asset id>"}: a generated asset's id feeds a file input directly, no re-upload. The output is a text-erased base plus text blocks with role, position, and content.
  7. jobs_wait, then asset_display and asset_download.

Common mistakes

  • Carrying one member's block to the next: magicPrompt and resolution are 4.5's; V3 Transparent wants aspectRatio and expandPrompt; Precise Edit takes image, not referenceImages, for the source.
  • Leaving 4.5 on its high default for drafts: low or medium first, high for the final.
  • Leaving expansion on with exact copy in the prompt: the rewrite can change the words before the model sees them.
  • Editing with aspectRatio: "auto" when the canvas must not change: use source, or Precise Edit.
  • Prompting a transparent background on 4.5: generate on V3 Transparent or chain Remove Background instead.
  • Inpainting on Character with image but no mask: they go together, characterReferenceImage stays required, and sizing fields are ignored while inpainting.
  • Setting fontNameH1 and fontFileH1 together on Layerize: a tier's font comes from a font name or a font file, never both. upload_asset has no font kind, so with only a local font file use the font name route and flag the gap.

© scenario-labs, 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 skills/scenario-ideogram of scenario-labs/skills.

Open the folder on GitHubat commit 91caa01

Compare with similar skills

Scenario Ideogram 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.

Scenario Ideogram compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Scenario Ideogram this skillscenario-labs/skills931—~2.7kAutomated safety check: PassMIT
Web Visualsglifxyz/glif-mcp-server212—~1.5kAutomated safety check: PassMIT
Olore Recraft Latestolorehq/olore104—~773Automated safety check: PassMIT
Image Prompt ReverseLunarXuan/image-prompt-reverse479—~678Automated safety check: PassGPL-3.0
App Icons And Logosglifxyz/glif-mcp-server212—~1.3kAutomated safety check: PassMIT
Nous Brandingmagnus919/agent-skills116—~4kAutomated safety check: PassMIT

Similar skills

  • Web Visuals

    glifxyz/glif-mcp-server

    Make images, textures, illustrations and background video for a website or app you are building, with Glif, and wire them into the code.

    212 GitHub stars~1.5k tokensUpdated today
    Media & CreativeAuto-check passed
  • Local recraft documentation reference (latest). An agent skill from olorehq/olore.

    104 GitHub stars~773 tokensUpdated today
    Media & CreativeAuto-check passed
  • Image Prompt Reverse

    LunarXuan/image-prompt-reverse

    Analyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts.

    479 GitHub stars~678 tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • App Icons And Logos

    glifxyz/glif-mcp-server

    Design a logo, app icon, favicon set, icon set or brand kit with Glif for an app or site you are building, then export every size and wire it into the code.

    212 GitHub stars~1.3k tokensUpdated today
    Media & CreativeAuto-check passed
  • Nous Branding

    magnus919/agent-skills

    Generate images and content consistent with the Nous Research brand identity.

    116 GitHub stars~4k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Brand Dna

    thatrebeccarae/claude-marketing

    Extract brand identity from a website URL — voice, colors, typography, imagery, values, and target audience — into a structured brand-profile.json.

    162 GitHub stars~1.8k tokensUpdated 4 mo ago
    Media & CreativeAuto-check passed

More from scenario-labs/skills

All 143 skills in this repo
  • Scenario Blender Grease Pencil

    scenario-labs/skills

    A skill your agent uses when drawing or animating with Grease Pencil in Blender 5.x from Python: 2D or 2.5D illustration, frame-by-frame animation, a cutout or part-based 2D character, strokes with…

    931 GitHub stars~4.5k tokensUpdated yesterday
    Auto-check passed
  • Scenario Blender Hair

    scenario-labs/skills

    A skill your agent uses when grooming hair or fur in Blender with hair curves, such as a character hairstyle, animal fur, procedural fur in geometry nodes, or hair cards and mesh hair for games.

    931 GitHub stars~4.7k tokensUpdated yesterday
    Auto-check passed
  • A skill your agent uses when lighting, rendering or compositing in Blender: light a character, product or hero shot, interior at dusk or night, three-point or motivated lighting, sun and sky, HDRI…

    931 GitHub stars~5k tokensUpdated yesterday
    Auto-check passed
  • Scenario Godot Animation

    scenario-labs/skills

    A skill your agent uses when animating characters or scenes in Godot 4.7: AnimationPlayer clips and RESET, AnimationTree state machines and blend spaces built in code, Mixamo or glTF import, loop…

    931 GitHub stars~4.7k tokensUpdated yesterday
    Auto-check passed
  • Scenario Godot Audio

    scenario-labs/skills

    A skill your agent uses when adding or fixing sound in Godot 4.7: audio buses and effects, volume sliders, 'too many sounds', combat audio with hundreds of enemies, sounds clipping or distorting, 3D…

    931 GitHub stars~4.7k tokensUpdated yesterday
    Auto-check passed
  • Scenario Godot Multiplayer

    scenario-labs/skills

    A skill your agent uses when a Godot 4 game goes online or co-op: host and join with ENet, WebSocket for a web build, RPCs (@rpc, rpcid, anypeer), MultiplayerSpawner and MultiplayerSynchronizer…

    931 GitHub stars~5.1k tokensUpdated yesterday
    Auto-check passed

Questions about Scenario Ideogram

What does Scenario Ideogram do?

A skill your agent uses when generating or editing images with Ideogram models on Scenario via MCP: posters, logos, menus, packaging, or signage with exact in-image text, editing an image in place…. Scenario Ideogram is an agent skill from scenario-labs/skills. Use when generating or editing images with Ideogram models on Scenario via MCP: posters, logos, menus, packaging, or signage with exact in-image text, editing an image in place while keeping its exact size, transparent PNG generation, background removal that keeps hair and glass edges, editable text layers for localization, or one consistent character from a reference.

When should I use Scenario Ideogram?

Scenario Ideogram fits situations like: editing images with Ideogram models on Scenario via MCP: posters; signage with exact in-image text; editing an image in place while keeping its exact size; transparent PNG generation.

How do I install Scenario Ideogram in Claude Code?

Run `npx skills add scenario-labs/skills --skill scenario-ideogram -a claude-code`. Or copy the skill folder (skills/scenario-ideogram in scenario-labs/skills) into .claude/skills/scenario-ideogram in your project. Claude Code loads it when a task matches its description.

How do I install Scenario Ideogram in Codex?

Run `npx skills add scenario-labs/skills --skill scenario-ideogram -a codex`. Or copy the skill folder (skills/scenario-ideogram in scenario-labs/skills) into .agents/skills/scenario-ideogram in your project. Codex loads it when a task matches its description.

Can I use Scenario Ideogram 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 scenario-labs/skills --skill scenario-ideogram -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scenario-ideogram, .gemini/skills/scenario-ideogram, .github/skills/scenario-ideogram and .opencode/skills/scenario-ideogram in your project.

What does Scenario Ideogram need to run?

Going by SKILL.md and its folder, Scenario Ideogram needs the command-line tools its instructions call (npx). Our summary lists: Node.js.

Does Scenario Ideogram access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Scenario Ideogram 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 Scenario Ideogram use?

Scenario Ideogram is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Scenario Ideogram use?

About 2.7k tokens (SKILL.md is roughly 11k 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 Scenario Ideogram?

Skills that share tags, products or a category with Scenario Ideogram: Web Visuals (glifxyz/glif-mcp-server, 212 stars), Olore Recraft Latest (olorehq/olore, 104 stars), Image Prompt Reverse (LunarXuan/image-prompt-reverse, 479 stars) and App Icons And Logos (glifxyz/glif-mcp-server, 212 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Scenario Ideogram?

scenario-labs (a GitHub organization) maintains it in scenario-labs/skills, which has 931 GitHub stars. The repository holds 143 skills in this directory. The repository was last updated on October 8, 2026.

Source: scenario-labs/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.