Best fit
- Writing or refining a prompt for any pack-ai-image provider.
- After image-provider-routing has selected the target provider.
- When a prompt is underperforming and needs provider-specific tuning.
event4u-app/agent-config
prompt-engineering-image
Translate an image brief into provider-specific prompt grammar per model. Use when writing or refining an image-generation prompt for Ideogram, Flux, Gemini, GPT Image 2, or Recraft.
94Collecting
See how to use itView GitHub source
npx skills add https://github.com/event4u-app/agent-config --skill "src/skills/prompt-engineering-image"Automated source guide
Source checked Jul 28, 2026·Refresh due Oct 26, 2026
Reorganized from the pinned upstream SKILL.md
Turn prompt-engineering-image's source instructions into a guide you can follow
According to the pinned SKILL.md from event4u-app/agent-config: Translate an image brief into a provider-specific prompt string. Each model has distinct prompt grammar — this skill applies the right structure per adapter.
npx skills add https://github.com/event4u-app/agent-config --skill "src/skills/prompt-engineering-image"Bring this context
- A concrete task that matches the documented purpose of prompt-engineering-image.
- The files, examples, or context the task depends on.
- Your constraints, target environment, and definition of done.
Expected outputs
- Target provider — name + adapter file reference.
- Prompt string — the exact string to pass to the adapter, ready to copy.
- Key params — any model-specific fields (aspect ratio, style, negative prompts).
Key source sections
Read prompt-engineering-image through these 5 source sections
Sections are extracted automatically from the pinned SKILL.md and link back to the source.
Procedure
1. Receive the brief — extract: subject, style, output format (raster/vector/banner), target provider (from image-provider-routing or explicitly stated). 2. Structure the prompt blocks — subject · style · composition · technical params. 3. Apply provider grammar from the section…
Receive the brief — extract: subject, style, output format (raster/vector/banner),Structure the prompt blocks — subject · style · composition · technical params.Apply provider grammar from the section above for the target model.
When to use
Writing or refining a prompt for any pack-ai-image provider.
Writing or refining a prompt for any pack-ai-image provider.After image-provider-routing has selected the target provider.When a prompt is underperforming and needs provider-specific tuning.
Per-provider prompt grammar
Lead with the text literal in quotes: "BAKERY NAME" in bold serif on a cream background.
Lead with the text literal in quotes: "BAKERY NAME" in bold serif on a cream background.Follow with visual context: background, color palette, style (flat, vintage, art-deco).Avoid long scene descriptions — Ideogram renders text best with a focused layout brief.
Ideogram (text-in-image: logos, banners, typographic art)
Lead with the text literal in quotes: "BAKERY NAME" in bold serif on a cream background.
Lead with the text literal in quotes: "BAKERY NAME" in bold serif on a cream background.Follow with visual context: background, color palette, style (flat, vintage, art-deco).Avoid long scene descriptions — Ideogram renders text best with a focused layout brief.
Flux (photoreal: product shots, portraits, scenes)
Descriptive noun phrase first: subject → lighting → environment → camera.
Descriptive noun phrase first: subject → lighting → environment → camera.Example: "Close-up product shot of a ceramic coffee mug, soft studio lighting,Style descriptors: cinematic, hyperrealistic, 8K, golden hour, DSLR.
SkillSignal prompt templates
Provide the task, context, and acceptance criteria
These prompts were written by SkillSignal from the source structure; they are not upstream text.
Task-start prompt
Confirm source fit, inputs, and outputs before acting.
Use prompt-engineering-image to help me with: [specific task]. Context: [files, data, or background]. Constraints: [environment, scope, and prohibited actions]. Before acting, check the pinned SKILL.md and explain which sections apply, what inputs are still missing, and what you will deliver.
Source-guided execution
Make the Agent explicitly follow the key extracted sections.
Apply the pinned prompt-engineering-image source to [task]. Pay particular attention to these source sections: “Procedure”, “When to use”, “Per-provider prompt grammar”, “Ideogram (text-in-image: logos, banners, typographic art)”, “Flux (photoreal: product shots, portraits, scenes)”. Preserve the important decision at each step. Mark facts not covered by the source as “needs confirmation” instead of inventing them. Then verify the result against my acceptance criteria: [criteria].
Result-review prompt
Check omissions, permissions, and source drift before delivery.
Review the current prompt-engineering-image result: (1) does it satisfy the original task; (2) were any applicable steps or limits in the pinned SKILL.md missed; (3) did it perform any unauthorized file, command, network, or data action; and (4) which conclusions remain unverified? List issues first, then fix only what the source or user authorization supports.
Output checklist
Verify each item before delivery
The task matches the purpose documented in the SKILL.md.
The source section “Procedure” has been checked.
The source section “When to use” has been checked.
The source section “Per-provider prompt grammar” has been checked.
The source section “Ideogram (text-in-image: logos, banners, typographic art)” has been checked.
Inputs, constraints, and acceptance criteria are explicit.
Unverified facts, compatibility, and outcome claims are clearly marked.
Any file, command, network, or data action has been reviewed.
Choose a different workflow
When another Skill is the better fit
brand-landingpage
Brand-first landing page designer — runs a brand-identity interview (colors, typography, shape language), then generates and iterates on a polished landing page via Stitch with deployment-ready HTML. Use when the user asks to create, design, or build a landing page, homepage, or marketing page and has no established visual direction. Skip when they have a design mockup, need a dashboard or app UI, are working at component level, building a multi-page app, or restyling with known design tokens —
A separate implementation from wshobson/agents; compare its source, maintenance signals, and permission requirements.
Open source detailvideodb
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, v
A separate implementation from affaan-m/ECC; compare its source, maintenance signals, and permission requirements.
Open source detailios-localization
Implement, review, or improve localization and internationalization in iOS/macOS apps — String Catalogs (.xcstrings), generated localizable symbols, stable key naming, LocalizedStringKey, LocalizedStringResource, pluralization, FormatStyle for numbers/dates/measurements, right-to-left layout, Dynamic Type, and locale-aware formatting. Use when adding multi-language support, setting up String Catalogs, enabling generated symbols for compile-time-safe localization keys, handling plural forms, form
A separate implementation from dpearson2699/swift-ios-skills; compare its source, maintenance signals, and permission requirements.
Open source detailFAQ
What does prompt-engineering-image do?
Translate an image brief into a provider-specific prompt string. Each model has distinct prompt grammar — this skill applies the right structure per adapter.
How do I start using prompt-engineering-image?
The catalog detected this source-specific install command: npx skills add https://github.com/event4u-app/agent-config --skill "src/skills/prompt-engineering-image". Inspect the command and pinned source before running it.
Which Agent platforms does it declare?
No dedicated Agent platform is declared in the pinned source record.
Repository stars
7
Repository forks
1
Quality
94/100
Source repository last pushed
Quality breakdown
Based on traceable docs and repository signals; stars are not treated as quality.
Documentation24/30
Specificity25/25
Maintenance20/20
Trust signals25/25
Compare before choosing
Related Agent Skills and source variants
These links are selected from shared tasks, functions, stacks, platforms, and same-name variants. Compare the source owner, documentation, permissions, and maintenance signals.
brand-landingpage by wshobson
Brand-first landing page designer — runs a brand-identity interview (colors, typography, shape language), then generates and iterates on a polished landing page via Stitch with deployment-ready HTML. Use when the user asks to create, design, or build a landing page, homepage, or marketing page and has no established visual direction. Skip when they have a design mockup, need a dashboard or app UI, are working at component level, building a multi-page app, or restyling with known design tokens —
videodb by affaan-m
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, v
ios-localization by dpearson2699
Implement, review, or improve localization and internationalization in iOS/macOS apps — String Catalogs (.xcstrings), generated localizable symbols, stable key naming, LocalizedStringKey, LocalizedStringResource, pluralization, FormatStyle for numbers/dates/measurements, right-to-left layout, Dynamic Type, and locale-aware formatting. Use when adding multi-language support, setting up String Catalogs, enabling generated symbols for compile-time-safe localization keys, handling plural forms, form
figma-implement-design by openai
Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions "implement design", "generate code", "implement component", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`.
figma by openai
Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.
View original Skill.mdThis page is parsed directly from the repository SKILL.md without editorial rewriting. Collected: Jul 28, 2026 · about 4 min
prompt-engineering-image
Translate an image brief into a provider-specific prompt string. Each model has distinct prompt grammar — this skill applies the right structure per adapter.
When to use
- Writing or refining a prompt for any
pack-ai-imageprovider. - After
image-provider-routinghas selected the target provider. - When a prompt is underperforming and needs provider-specific tuning.
Per-provider prompt grammar
Ideogram (text-in-image: logos, banners, typographic art)
- Lead with the text literal in quotes:
"BAKERY NAME" in bold serif on a cream background. - Follow with visual context: background, color palette, style (flat, vintage, art-deco).
- Avoid long scene descriptions — Ideogram renders text best with a focused layout brief.
- Key params:
model: V_2,aspect_ratio: ASPECT_1_1(square logo) orASPECT_16_9(banner),magic_prompt_option: AUTO(let Ideogram enrich).
Flux (photoreal: product shots, portraits, scenes)
- Descriptive noun phrase first: subject → lighting → environment → camera.
- Example:
"Close-up product shot of a ceramic coffee mug, soft studio lighting, clean white background, 50 mm lens bokeh, ultra sharp". - Style descriptors: cinematic, hyperrealistic, 8K, golden hour, DSLR.
- Negative prompts accepted:
--no cartoon, illustration, text. - Routes through fal/Replicate — model slug:
fal-ai/flux-proorblack-forest-labs/flux-pro.
Recraft (vector / SVG logos and icons)
- Style param is mandatory:
style: vector_illustration(SVG output),style: icon(for simplified marks),style: realistic_image(raster fallback). - Keep prompt minimal — recraft interprets shape semantics:
"minimalist leaf icon, single color". - Avoid photographic language (lighting, bokeh, grain) — it has no effect on vector output.
- Key params:
model: recraftv3,response_format: url.
Gemini-image / GPT Image 2 (general art, edits, multimodal)
- Natural language works well — no special syntax required.
- Be explicit about style:
"watercolor illustration","flat design","oil painting". - For GPT Image 2 image editing: include the edit instruction after describing the target:
"Remove the background and replace with a solid pastel blue". - Gemini: submit via
generateContent(Nano Banana family) orimagen-4.0:predict(Imagen 4).
Procedure
- Receive the brief — extract: subject, style, output format (raster/vector/banner),
target provider (from
image-provider-routingor explicitly stated). - Structure the prompt blocks — subject · style · composition · technical params.
- Apply provider grammar from the section above for the target model.
- Tune for the job shape — text-literal first for Ideogram; noun-phrase first for Flux;
minimal +
style:param for Recraft; natural language for Gemini/GPT. - Inspect the adapter header — open
node_modules/@event4u/agent-config/src/scripts/ai-image/adapters/<provider>.shand confirm the param enums (aspect/style/model) the prompt relies on still match. - Emit the prompt in the Output format below.
Output format
- Target provider — name + adapter file reference.
- Prompt string — the exact string to pass to the adapter, ready to copy.
- Key params — any model-specific fields (aspect ratio, style, negative prompts).
- Variant (optional) — one alternative phrasing when the brief is ambiguous.
Gotcha
- Per-provider param enums drift —
aspect_ratio,style, andmodelenum values are ASSUMED from the adapter header comments. Verify against live API docs before promotion; never hardcode these in production without a smoke trace. - Adapters are scaffold-tier — prompts authored here are not live-validated.
Actual rendering requires adapter promotion to
stableperprovider-lifecycle-discipline. - Recraft: photographic descriptors (
bokeh,lighting,grain) silently have no effect on vector output — strip them to avoid prompt budget waste.
Good example: Ideogram brief for a bakery logo — lead with the text literal:
'"Le Four" in warm serif, vintage French patisserie style, cream and terracotta'.
Bad example: Sending a photorealism-heavy Flux prompt to Recraft — the style descriptors will be ignored and the vector output will be wrong.
Do NOT
- Do NOT send photographic descriptors (
bokeh,lighting,grain) to Recraft — they have no effect on vector output and waste the prompt budget. - Do NOT hardcode ASSUMED param enums into a live run without a smoke trace — verify against the adapter header / provider docs first.
- Do NOT embed a real person's likeness, a trademarked brand mark, or a named living
artist's style in a prompt without the rights check (
image-likeness-and-rights). - Do NOT write a prompt before the provider is chosen — route via
image-provider-routingfirst.
See also
image-provider-routing— select the provider before writing the prompt.provider-lifecycle-discipline— lifecycle tier gates live runs.node_modules/@event4u/agent-config/src/scripts/ai-image/adapters/— adapter header comments for param enums.image-likeness-and-rights— rights check before generating real-person likenesses or brand marks.
- Source repo
- event4u-app/agent-config
- Skill path
- src/skills/prompt-engineering-image/SKILL.md
- Commit SHA
- 0adf49a8ae84
- Repository license
- MIT
- Data collected