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 fluentlc/shiny-skills --skill image-to-prompt-skillgit clone --depth 1 https://github.com/fluentlc/shiny-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/fluentlc/shiny-skills/image-to-prompt-skill)<a href="https://agentmods.dev/skills/fluentlc/shiny-skills/image-to-prompt-skill"><img src="https://agentmods.dev/badge/skills/fluentlc/shiny-skills/image-to-prompt-skill/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/fluentlc/shiny-skills/image-to-prompt-skill"><img src="https://agentmods.dev/badge/skills/fluentlc/shiny-skills/image-to-prompt-skill.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 | $0.00071 | $0.01810 |
| Opus 5 | $0.00036 | $0.00905 |
| Sonnet 5 | $0.00014 | $0.00362 |
| Haiku 4.5 | $0.00007 | $0.00181 |
Grade A, and why
image-to-prompt-skill 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 11d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image to Prompt Skill
Overview
Reverse-engineers uploaded images into two artifacts:
- Prompt Template — A reusable structured prompt with
[PLACEHOLDER]variables for generating similar images with different subjects. - Prompt Case — The concrete prompt with placeholders filled using actual content observed in the input image.
This skill is the reverse counterpart of image-creation-prompt-skill:
image-creation-prompt-skill= forward: text description -> structured promptimage-to-prompt-skill= reverse: image -> structured prompt + reusable template
Trigger Conditions
Activate when:
- User uploads an image (base64, file path, or URL) and asks for prompt generation
- Explicit requests: "根据这张图生成 prompt", "reverse engineer this image", "分析这张图片的风格", "拆解这张图的结构"
- Keywords: "image to prompt", "图片转 prompt", "prompt 模板", "逆向图片", "根据图片生成 prompt"
10-Step Visual Analysis Framework
Before generating output, systematically analyze the image across these 10 dimensions:
| Step | Dimension | What to Extract |
|---|---|---|
| 1 | Overall Style | Art movement, visual genre, aesthetic label (e.g., "graffiti collage poster", "minimalist flat illustration") |
| 2 | Color Scheme | Primary/secondary/accent colors, contrast level, saturation, palette type (monochrome, complementary, analogous, triadic) |
| 3 | Main Subject | Central figure/object: identity, pose, expression, clothing, accessories, physical traits, proportions relative to frame |
| 4 | Background Design | Environment, depth of field, background elements, layering, spatial relationship to subject |
| 5 | Text & Typography | All visible text content, font styles, sizes, orientations, languages, placement strategy, hierarchy |
| 6 | Composition & Perspective | Framing, rule of thirds, symmetry/asymmetry, diagonal lines, camera angle, focal point, visual hierarchy |
| 7 | Material & Texture | Surface qualities: paper, metal, fabric, digital smoothness, brush strokes, torn edges, grain, gloss/matte |
| 8 | Lighting & Mood | Light direction, intensity, shadows, highlights, emotional tone, atmosphere, time of day feel |
| 9 | Decorative & Auxiliary Elements | Icons, borders, geometric shapes, patterns, filters, overlays, vignettes, watermarks, corner decorations |
| 10 | Quality & Technical Parameters | Estimated aspect ratio, resolution cues, suspected AI model parameters (e.g., --ar 9:16 --v 5 --style raw) |
What ships with it
6 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.
- 11d ago First seen · 123 lines · 71 tokens per session scan A b1fe5e9b95b1
image-to-prompt-skill is a skill published in the GitHub repository fluentlc/shiny-skills (16 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 1,810 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
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.
seedance-antislop
This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.
seedance-examples-ja
This skill should be used when the user asks for Japanese Seedance 2.0 examples, Japanese prompt patterns, example rewrites, or safe versions of working Japanese video-generation prompts.
seedance-filter
This skill should be used when a Seedance 2.0 prompt is blocked or rejected, when moderation is a suspected cause of a problem, or when the user asks for a content-boundary review or safer alternative. Assess the actual request before offering a clarification.
seedance-prompt-short
This skill should be used when the user asks for a compact Seedance 2.0 prompt, short Chinese prompt, prompt compression, 30-100 word output, or removal of unnecessary prompt language.
seedance-vocab-zh
This skill should be used when the user asks for Chinese Seedance 2.0 prompt wording, Mandarin cinematic vocabulary, Chinese prompt compression, or translation of camera, lighting, action, VFX, audio, and production terms into Chinese.