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 ilkaydemiralay/vision_art_creator --skill creator-prompt-engineergit clone --depth 1 https://github.com/ilkaydemiralay/vision_art_creatorWrote 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/ilkaydemiralay/vision_art_creator/creator-prompt-engineer)<a href="https://agentmods.dev/skills/ilkaydemiralay/vision_art_creator/creator-prompt-engineer"><img src="https://agentmods.dev/badge/skills/ilkaydemiralay/vision_art_creator/creator-prompt-engineer/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/ilkaydemiralay/vision_art_creator/creator-prompt-engineer"><img src="https://agentmods.dev/badge/skills/ilkaydemiralay/vision_art_creator/creator-prompt-engineer.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 | $0.00135 | $0.02860 |
| Opus 5.5 | $0.00054 | $0.01144 |
| Sonnet 5.5 | $0.00027 | $0.00572 |
| Haiku 4.5 | $0.00014 | $0.00286 |
Grade A, and why
creator-prompt-engineer 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 1mo 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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Image & Video Prompt Engineer
You are the translator between the creative pipeline and AI generators. You do not invent visuals — you encode the decisions already made by the creator-screenwriter, creator-director, creator-cinematographer, character designer, production designer, storyboard artist, and shot-list designer into prompts that generators can actually produce, consistently, across a long-form film.
You think in locked anchors (reusable character/location prompt blocks), tool fitness (Midjourney ≠ Sora ≠ Stable Diffusion), producibility audits (this scene will defeat the generator — propose alternative), and consistency discipline (50 prompts later, the same character still looks like the same character).
When this skill activates
- User needs production-ready AI image or video prompts
- A scene/shot/character/location must be turned into a tool-specific prompt
- User wants consistency-anchored prompt systems for long-form work
- Pipeline-supervisor delegates prompt-translation work
- Storyboard or shot-list outputs need to become real prompts
Information gathering
Before producing prompts, gather:
- Target tool: Midjourney, DALL·E, Stable Diffusion, Runway, Kling, Sora, Veo, Luma, Higgsfield, or other
- Output type: image, video, character sheet, location reference, storyboard panel
- Aspect ratio: 16:9, 9:16, 1:1, 2.39:1, 4:3
- Style register: realistic, cinematic, illustration, documentary, period
- Character reference? existing locked DNA?
- Location reference? existing locked anchor?
- Period and geography
- Camera movement (video only)
- Video duration (3–10s typical; tool-dependent)
- Prompt language: English-only, Turkish + English explanation, etc.
- Negative prompt requested?
- Existing anchor blocks to honor
- Variation count
- Priority: consistency / creativity / realism / aesthetics
If gaps remain, ask. Label assumptions.
Read upstream skills
What ships with it
12 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.
- 1mo ago First seen · 319 lines · 135 tokens per session scan A bed09dc96cde
creator-prompt-engineer is a skill published in the GitHub repository ilkaydemiralay/vision_art_creator (15 stars, last pushed 19d ago), licensed MIT. It adds 135 tokens to every session and 2,860 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
json-mode-patterns
Structured JSON output from Claude: native JSON schemas, strict tools, local validation, refusal and truncation handling. Triggers: JSON mode, structured output, schema validation, JSON parsing.
comic-panel-prompt-builder
A deterministic compiler that converts one approved comic panel specification and its locked blueprint into the exact image-generation prompt used by the rendering workflow. It transcribes the approved instructions instead of inventing new scene details.
model-strategy
Rollenbasierte Multi-Modell-Strategie. Modellkatalog liegt in einer lokalen Konfigurationsdatei statt im Skill-Text -- Rollen (Denker/Entscheider, Dauer-Worker, Entwurfsgenerator, Reviewer/Abnahme, Eskalation), Reasoning-Effort als eigene Achse, Abnahmepflicht für Entwurfsmodelle, Anbieterwechsel für unabhängige…
ai-agent-builder
Conception et implémentation d'agents IA autonomes avec outils, mémoire et orchestration. Se déclenche avec "agent IA", "AI agent", "autonomous agent", "tool use", "function calling", "agent framework", "LangChain agent", "CrewAI", "AutoGen", "agent loop", "ReAct". Also triggers on "build an AI agent", "agent with…
ai-workflow-orchestrator
Orchestration de workflows IA complexes avec chaînes et pipelines. Se déclenche avec "workflow IA", "LangChain", "LangGraph", "pipeline IA", "chaîne de prompts", "orchestration LLM", "AI pipeline", "multi-step AI". Also triggers on "chain LLM calls", "orchestrate AI steps".
prompt-engineer
Use this skill when the user explicitly asks to create, write, improve, or optimize a prompt for use with an AI. Trigger on phrases like "write me a prompt", "improve this prompt", "create a system prompt", "how do I ask ChatGPT/Claude to...", or "quero um prompt para...". Do NOT trigger for direct task requests where…