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 agentmods add skills/tencentcloudbase/awesome-miniprogram-skills/image-edit-skillnpx skills add TencentCloudBase/awesome-miniprogram-skills --skill image-edit-skillgit clone --depth 1 https://github.com/TencentCloudBase/awesome-miniprogram-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/tencentcloudbase/awesome-miniprogram-skills/image-edit-skill)<a href="https://agentmods.dev/skills/tencentcloudbase/awesome-miniprogram-skills/image-edit-skill"><img src="https://agentmods.dev/badge/skills/tencentcloudbase/awesome-miniprogram-skills/image-edit-skill.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.00422 |
| Opus 5 | $0.00019 | $0.00211 |
| Sonnet 5 | $0.00008 | $0.00084 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
image-edit-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 5d 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.
What it actually says
AI 图片编辑
触发场景
用户原话举例：
- 风格转换："把这张图改成水墨画风格"、"变成动漫风格"
- 背景替换："把背景换成白色"、"把室内背景换成海边"
- 内容修改："把猫换成狗"、"给画面加一些樱花飘落"
- 扩图生成："把画面往右延伸"
不适用范围
- 从零生成的图片（无原图）→ 不在本技能范围，由 image-gen-skill 处理
- 文本生成需求 → 不在本技能范围，由 text-gen-skill 处理
- 需要精确到像素级别的专业修图 → 不在本技能范围，AI 无法保证像素级精度
接口链路
editImage：基于原图和编辑需求，通过 AI 重绘实现图片编辑效果
使用顺序
- 用户需要提供一张原图（图片 URL）和编辑描述
- 基于编辑描述生成新的 prompt，调用图片生成模型重新生成
- 返回原图和编辑后图片的对比
- 编辑后的图片自动持久化到云存储
设计约束
- 此为 AI 重绘实现的编辑，非像素级精确编辑，不能保证与原图完全一致
- 必须通过云函数调用，小程序端不直接处理图片
- 原图需要提供可访问的网络 URL
What ships with it
15 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.
- apis/editImage.js 1.6 KB runs code
- cloudbaserc.json 701 B
- cloudfunctions/image-edit-handler/ai/edit.js 2.2 KB runs code
- cloudfunctions/image-edit-handler/index.js 620 B runs code
- cloudfunctions/image-edit-handler/package.json 217 B
- components/image-edit-card/index.js 3.0 KB runs code
- components/image-edit-card/index.json 49 B
- components/image-edit-card/index.wxml 1.1 KB
- components/image-edit-card/index.wxss 2.5 KB
- data/seed.js 334 B runs code
- index.js 357 B runs code
- mcp.json 3.2 KB
- mp-skills.json 154 B
- README.md 2.4 KB
- utils/util.js 594 B 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.
- 5d ago First seen · 41 lines · 39 tokens per session scan A a363faf1bef2
image-edit-skill is a skill published in the GitHub repository TencentCloudBase/awesome-miniprogram-skills (35 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 422 once invoked, about $0.0002 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
gzh_article
公众号图文创作 / 推文 / 官方号文章 (official account article) — 端到端：选题→搜集→成文→配图→去AI化→公众号内联样式排版→交付/草稿箱。honors user persona & style memory.
weapp-vite-best-practices
面向采用 weapp-vite 项目布局仓库或已安装 weapp-vite 依赖项目的工程化实践手册，覆盖 vite.config.ts 的 weapp 配置、内置 i18n、自动路由、routeRules/layout、buildScope、自动导入组件、分包、npm、六平台单目标构建、受管 TypeScript、HMR、sourcemap、prepare、MCP、Web runtime、lib mode、worker、AI skills，以及与 weapp-ide-cli 的命令治理边界。.
native-to-weapp-vite-wevu-migration
面向原生微信、支付宝、抖音等小程序渐进迁移到 weapp-vite + 原生 或继续升级到 weapp-vite + wevu + Vue SFC 的结构化工作流，覆盖六平台单目标构建、原生扩展名保留、Web 联调边界、路线选择、工具链接入、SFC 试点、响应式升级与可回滚验证。.
weapp-vite-vue-sfc-best-practices
面向使用 weapp-vite 的小程序项目的 Vue SFC 实践手册，覆盖 script setup、纯模板 SFC、JSON 宏、definePageMeta/layout、defineModel、usingComponents、内置 i18n Behavior、JSX/TSX script block、模板指令兼容、多平台 SFC、.weapp-vite 类型支持文件与受管 prepare 工作流。.
docs-and-website-sync
面向 weapp-vite monorepo 的文档、website 与公开 skills 同步工作流。适用于源码能力变化后同步配置、CLI、React/Wevu/Vue SFC、多平台、mpcore、README、packaged docs、脚手架 AGENTS.md、AI skills 元数据和触发回归入口。.
weapp-devtools-e2e-best-practices
面向 weapp-vite 仓库的 WeChat DevTools 与 mpcore headless runtime e2e 工作流。适用于 e2e/ide/、miniprogram-automator、WEAPPVITEE2ERUNTIMEPROVIDER、全局串行、共享 automator、miniProgram.reLaunch(...)、DevTools/headless parity、跨平台 launcher，以及 screenshot/compare/logs 验收。.