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 WiseWong6/wise-skills --skill wise-image-flowgit clone --depth 1 https://github.com/WiseWong6/wise-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/wisewong6/wise-skills/wise-image-flow)<a href="https://agentmods.dev/skills/wisewong6/wise-skills/wise-image-flow"><img src="https://agentmods.dev/badge/skills/wisewong6/wise-skills/wise-image-flow/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/wisewong6/wise-skills/wise-image-flow"><img src="https://agentmods.dev/badge/skills/wisewong6/wise-skills/wise-image-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00111 | $0.05526 |
| Opus 5 | $0.00056 | $0.02763 |
| Sonnet 5 | $0.00022 | $0.01105 |
| Haiku 4.5 | $0.00011 | $0.00553 |
Grade A, and why
wise-image-flow 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 today.
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 — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wise Image Flow · 配图全流程
一个 skill 覆盖「内容 → 提示词 → 生图」全链路：
- 上半场（配图助手）：把文章/模块/PPT 大纲转成统一风格、少字高可读的提示词（10 种风格 + 25 种布局 + 5 阶段流程）
- 下半场（生图工具）：Codex 只用
image_gen.imagegen，不可用或失败即停；其他宿主按下方通道规则选择内置工具、MCP 或 API。
触发方式
先判断是否需要配图规划，再选择普通或 PPT 模式；不能只凭图片数量、文件格式或布局标记触发。
- 进入本 Skill：用户明确指定
wise-image-flow；或要求将文章/PPT 大纲拆成系列配图，需要确定图清单、统一系列风格、逐张文案和提示词，并可继续生图、拼版交付。 - 直接使用生图工具：普通生图、修图、已有完整提示词的单张或批量执行，不进入本 Skill。在 Codex 中直接使用
image_gen.imagegen，不插入图清单、风格 Gallery 或 Copy Spec 确认流程。 - 用户指定优先：用户说“直接用 Codex 生图”“不用这个 Skill”时跳过本 Skill；不因“配图”“出图”“PPT”或单张图片的风格要求强制进入。仅拼接已有图片时使用
image-to-pages。 - 续作：已在本 Skill 中完成规划后要求“出图”，沿用已确认方案进入生图步骤；已提供完整提示词并显式指定本 Skill 时，同样跳过前置规划。
普通配图模式
例如：“把这篇文章拆成一组图，规划每张讲什么、写什么，并统一风格。”
PPT 配图模式（快速通道，3 阶段）
只有已满足本 Skill 进入条件，且用户要求按 PPT 大纲规划系列配图时才进入。第X页、可视化类型：、ASCII 框图和布局标记只辅助解析，不独立触发。
详见 references/stages/00-ppt-mode.md。
风格 Gallery（⚠️ 阶段 2 必须用户确认，禁止自动决定）
支持 10 种风格，必须向用户展示并等待明确选择：
⚠️ 禁止自动选择：以下"参考关键词"仅供推荐参考，严禁未获用户确认前擅自决定风格。
| 风格 ID | 名称 | 适用场景 | 参考关键词 |
|---|---|---|---|
cream-paper |
奶油纸手绘 | 配图、信息图、概览、框架图、路线图（默认推荐） | 通用/配图/概览/框架 |
infographic |
扁平化科普图 | 概念解释、原理说明、步骤展示 | 科普/原理/是什么/如何 |
handdrawn |
方格纸手绘 | 笔记手绘、学习感 | 笔记/手绘/草图/学习 |
healing |
治愈系插画 | 情绪叙事、场景氛围、治愈感 | 情绪/故事/人物/治愈 |
sokamono |
描边插画 | 清新文艺、简洁治愈 | 清新/简洁/文艺 |
minimalist-sketch |
极简手绘笔记 | 细线条手绘、纯白背景、信息图解 | 极简/技术/专业 |
xhs-cartoon |
小红书卡通 | 干货分享、萌系表达、轻松活泼 | 萌系/干货/分享/活泼 |
editorial |
社论全景 | 深度分析、商业场景；封面 21:9，内页 16:9 | 商业/深度/全景/严肃 |
cream-journal |
奶油手账 | 手账风知识卡片、小红书图文、学习笔记（3:4） | 手账/笔记/知识卡片 |
editorial-paper |
社论纸艺 | 责任关系、工作流重构、AI 工作产品；默认 3:4，也可按场景扩展横版 | 纸艺/拼贴/责任/工作流 |
强制流程：1. 展示上表 → 2. 询问"请选择（数字或名称）" → 3. 收到明确选择才进入下一阶段 → 4. 风格锁定后阶段 3+ 不得更改（要换回退到阶段 2.5）
布局系统（自包含速查表）
注：本表为 25 种布局标记的自包含速查表（标记 + 名称 + 场景 + 选择原则）。5 种通用结构模板（
balanced/comparison/list/flow/sparse）位于references/templates/16x9-*.md，阶段 4 按 Layout ID 动态读取（见references/stages/04-prompts.md）。
What ships with it
29 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.
- agents/openai.yaml 382 B
- LICENSE 1.0 KB
- README.md 3.1 KB
- references/examples/ai-tools-selection.md 451 B
- references/stages/00-ppt-mode.md 2.7 KB
- references/stages/01-brief.md 3.9 KB
- references/stages/02-plan.md 7.0 KB
- references/stages/03-copy.md 2.7 KB
- references/stages/04-prompts.md 9.2 KB
- references/stages/05-iterate.md 892 B
- references/styles.json 22 KB
- references/templates/16x9-3cards-insights.md 586 B
- references/templates/16x9-5panel-comic.md 440 B
- references/templates/16x9-contrast-2cards.md 507 B
- references/templates/16x9-cover-roadmap.md 800 B
- references/templates/16x9-infographic.md 503 B
- references/templates/checklist.md 690 B
- references/templates/style-block-cream-journal.md 3.9 KB
- references/templates/style-block-cream-paper.md 653 B
- references/templates/style-block-editorial-paper.md 1.8 KB
- references/templates/style-block-editorial.md 2.8 KB
- references/templates/style-block-handdrawn.md 776 B
- references/templates/style-block-healing.md 672 B
- references/templates/style-block-infographic.md 657 B
- references/templates/style-block-minimalist-sketch.md 1.7 KB
- references/templates/style-block-sokamono.md 589 B
- references/templates/style-block-xhs-cartoon.md 2.0 KB
- scripts/generate_html.py 32 KB runs code
- scripts/generate_image.py 33 KB runs code
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.
- today Changed · +3 lines · -18 tokens per session b74ba4562969
- 10d ago First seen · 341 lines · 129 tokens per session scan A 5f1f40821875
wise-image-flow is a skill published in the GitHub repository WiseWong6/wise-skills (6 stars, last pushed yesterday), licensed MIT. It adds 111 tokens to every session and 5,526 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
html-ppt-zhangzara-retro-zine
A neighborhood zine on the disappearing corner shops — portraits, voices, and what a block loses when they close. Built as a decision-grade story deck for community, local readers.
html-ppt-zhangzara-studio
A photography studio's portfolio-and-rate deck — the signature work, the process, and the packages that win the brief. Built as a decision-grade design craft deck for prospective clients.
motion-frames
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…
webgl-halftone-drift
A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…