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 full-aigc-skills/jimeng-skills --skill jimeng-prompt-text2imagegit clone --depth 1 https://github.com/full-aigc-skills/jimeng-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/full-aigc-skills/jimeng-skills/jimeng-prompt-text2image)<a href="https://agentmods.dev/skills/full-aigc-skills/jimeng-skills/jimeng-prompt-text2image"><img src="https://agentmods.dev/badge/skills/full-aigc-skills/jimeng-skills/jimeng-prompt-text2image/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/full-aigc-skills/jimeng-skills/jimeng-prompt-text2image"><img src="https://agentmods.dev/badge/skills/full-aigc-skills/jimeng-skills/jimeng-prompt-text2image.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 | $0.00208 | $0.02280 |
| Opus 5 | $0.00104 | $0.01140 |
| Sonnet 5 | $0.00042 | $0.00456 |
| Haiku 4.5 | $0.00021 | $0.00228 |
Grade B, and why
jimeng-prompt-text2image scanned grade B with 1 finding 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 12d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
7. **Color library is for YOUR reference only** — Load `color-library/chinese-traditional.md` to FIND the right color name to write into the prompt. Do NOT copy hex codes into the output prompt text How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jimeng-prompt-text2image — 即梦文生图提示词
Craft production-ready text-to-image prompts for 即梦 (Jimeng/Dreamina) models.
When to use this skill
Use this skill when the user:
- Asks you to write an image generation prompt ("帮我写个提示词")
- Describes an image they want and needs it turned into a proper prompt
- Wants to refine, optimize, or translate an existing prompt
- Mentions keywords like: 提示词, 文生图, text2image, AI绘画, AI生图, prompt, 文字成图
- Asks about how to describe a specific visual scene, style, or effect
Do NOT use this skill for:
- Executing CLI commands to generate images → use jimeng-cli-text2image
- Writing video prompts → use jimeng-prompt-text2video
- Image-to-image editing prompts → use jimeng-prompt-image2image
Core Methodology
The prompt formula is a reasoning framework — not a rigid template. Apply it flexibly:
[主体/人物] + [场景/背景] + [动作/姿态] + [风格/艺术类型] + [光线/色彩] + [构图/视角] + [画质/细节]
Each component is optional. Select and weight components based on the scenario:
- Portrait: emphasize subject, expression, clothing, lighting, composition
- Landscape: emphasize environment, time/weather, color palette, atmosphere
- Product: emphasize object details, material, background, lighting setup
- Abstract/Artistic: emphasize style, color scheme, texture, mood
How to use this skill
Step 1: Identify scenario category
→ Load rules/category-table.md to match user's request to the right category and example file
Step 2: Load reference materials
Load the relevant vocabulary files from word-library/ based on what you need — never load the whole library:
| 你需要的 | 加载文件 |
|---|---|
| 人物/面部/体型/发型/表情/妆容/服装/配饰 | word-library/subject.md |
| 场景/环境/天气/时间/季节/地域 | word-library/scene.md |
| 摄影/绘画/设计/数字/民族风格 | word-library/style.md |
| 材质/肌理（金属/木材/石材/织物/玻璃） | word-library/material.md |
| 动作/姿态/动态/手势 | word-library/motion.md |
| 道具/器物/乐器/武器/科技/食物 | word-library/props.md |
| 光线/光影/光效/照明 | word-library/lighting.md |
| 构图/视角/景深/镜头 | word-library/composition.md |
| 画质/质感/通感词 | word-library/quality.md |
| 氛围/情绪/意境 | word-library/atmosphere.md |
| 抽象/概念/视觉隐喻 | word-library/abstract.md |
| 自然元素（花卉/树木/动物） | word-library/nature.md |
What ships with it
60 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.
- examples/abstract.md 4.3 KB
- examples/aerial.md 3.2 KB
- examples/animal.md 4.0 KB
- examples/anime.md 4.4 KB
- examples/architecture.md 4.1 KB
- examples/botanical.md 3.3 KB
- examples/children.md 3.2 KB
- examples/cinematic.md 4.2 KB
- examples/commercial.md 4.7 KB
- examples/education.md 3.5 KB
- examples/fantasy.md 3.7 KB
- examples/fashion.md 3.4 KB
- examples/festival.md 4.1 KB
- examples/food-product.md 4.2 KB
- examples/game.md 3.6 KB
- examples/guofeng.md 4.5 KB
- examples/landscape.md 4.3 KB
- examples/macro.md 3.2 KB
- examples/medical.md 3.5 KB
- examples/minimalism.md 3.1 KB
- examples/music-dance.md 3.6 KB
- examples/night.md 3.3 KB
- examples/pet.md 3.2 KB
- examples/portrait.md 4.5 KB
- examples/scifi.md 3.6 KB
- examples/sport.md 3.4 KB
- examples/steampunk.md 3.6 KB
- examples/street.md 3.3 KB
- examples/surreal.md 3.6 KB
- examples/tech.md 3.4 KB
- examples/travel.md 3.6 KB
- examples/underwater.md 3.4 KB
- examples/vehicle.md 3.4 KB
- examples/vintage.md 3.5 KB
- examples/wedding.md 3.4 KB
- LICENSE.txt 11 KB
- references/3.0/vocabulary-core.md 4.3 KB
- references/3.0/vocabulary-materials.md 3.5 KB
- references/3.0/vocabulary-styles.md 7.6 KB
- references/618-ecommerce-poster-examples.md 14 KB
- references/color-library.md 36 KB
- references/color-library/chinese-traditional.md 12 KB
- references/color-library/modern-schemes.md 6.7 KB
- references/color-library/pantone.md 3.5 KB
- references/color-library/ral.md 15 KB
- references/enhanced-validation.md 429 B
- references/gugong-384-colors.md 26 KB
- references/jimeng-2.1-prompt-guide.md 1.6 KB
- references/jimeng-3.0-prompt-guide.md 3.0 KB
- references/jimeng-3.0-vocabulary.md 15 KB
- references/jimeng-3.0-word-library.md 22 KB
- references/jimeng-3.1-prompt-guide.md 1.6 KB
- references/jimeng-4.0-prompt-guide.md 2.5 KB
- references/jimeng-4.1-prompt-guide.md 3.7 KB
- references/jimeng-4.5-prompt-guide.md 3.5 KB
- references/rules/category-table.md 4.0 KB
- references/rules/core-methodology.md 2.1 KB
- references/rules/validation-checklist.md 595 B
- references/rules/writing-rules.md 3.4 KB
- references/seedream-5.0-prompt-guide.md 2.3 KB
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.
- 12d ago First seen · 122 lines · 208 tokens per session scan B c70de607c941
jimeng-prompt-text2image is a skill published in the GitHub repository full-aigc-skills/jimeng-skills (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 208 tokens to every session and 2,280 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…