Easy Image — 技能工具

Name: Easy Image — 技能工具
Author: bbear

bbear

Easy Image — 技能工具

v1.0.1

Professional 图像生成工具 assistant for workplace: PPT graphics, marketing posters, product photos, social media content. Simple description → Profession...

0· 172·0 当前·0 累计

by @ximasadila (bbear)·MIT-0

系统工具开发工具数据分析智能体

下载技能包

License

MIT-0

最后更新

2026/4/12

安全扫描

VirusTotal

可疑

查看报告

OpenClaw

安全

medium confidence

The skill is internally consistent with an image-generation assistant: it stores per-user config and API keys under the home directory, uses local prompt templates, and calls image-generation platforms — nothing requested is disproportionate to that purpose.

评估建议

This skill appears to do what it says: translate short descriptions into professional prompts and call image-generation platforms. Before installing or using it, consider the following: - Review where API keys will be stored: the skill asks you to provide platform keys and will save them to platform-specific files in your home directory (e.g., ~/.jiekou/config.json). If you prefer, use limited-scope or ephemeral keys and check the file contents after setup. - Inspect the platform adapter docs (...

详细分析 ▾

✓ 用途与能力

Name/description (image generation for workplace assets) aligns with behavior: assembling prompts from templates, selecting models, calling external image-generation platforms, and saving outputs. The skill expects API keys and local config files (e.g., ~/.{platform}/config.json and ~/.easy-image-skill/config.json), which is reasonable for this purpose. It does not request unrelated credentials or system-level privileges.

ℹ 指令范围

Runtime instructions read and write files in the user's home (~/.easy-image-skill/* and ~/.{platform}/config.json) and silently consult a personal library (~/.easy-image-skill/my-prompts.md). These actions are coherent with a personal prompt library and local config, but the SKILL.md explicitly says some checks happen 'silently' and that technical details are hidden from the user — this can be a privacy/visibility concern (the skill may read user prompt history and reuse it without making all details visible). It also defaults to enabling web-grounding/search when brand names or timeliness are detected, which implies automatic outbound network queries beyond the image generation API.

✓ 安装机制

Instruction-only skill with no install spec or downloaded code. That minimizes disk/write and supply-chain risk. All behavior is specified in SKILL.md and local reference docs.

ℹ 凭证需求

The registry metadata lists no required env vars, but the runtime flow clearly expects the user to provide platform API keys (e.g., Jiekou, Novita, PPIO, OpenRouter, WaveSpeed, Google) and stores them in platform-specific config files in the home directory. Requesting/storing those keys in user config files is proportionate, but the skill does not declare these credentials up-front in the registry metadata—this is an omission to be aware of. The skill does not request unrelated keys or system secrets.

✓ 持久化与权限

The skill does not request 'always: true' and does not modify other skills or system-wide settings. It writes its own config (~/.easy-image-skill/config.json) and personal library, which is expected. It also asks for a default 'save_path' granting blanket download authorization into a user-chosen folder; that is functional for its purpose but is a potential place for accidental data writes.

安全有层次，运行前请审查代码。

License

MIT-0

可自由使用、修改和再分发，无需署名。

查看条款 ↗

运行时依赖

无特殊依赖

版本

latestv1.0.12026/3/18

3 ## v1.0.1 (2026-03-20) 4 5 ### Fixed 6 - Corrected Novita API endpoints: text-to-image now uses `/v3/gemini-3.1-flash-image-text-to-image` instead of non-existent `/v3/gemini-3.1-flash-imag e` 7 - Corrected PPIO API endpoints: same fix applied for both Flash and Pro models 8 - Fixed Pro model endpoints for both platforms: `/v3/gemini-3-pro-image-text-to-image` 9 10 ### Improved 11 - Compressed SKILL.md from ~12k to ~3.7k characters (~70% reduction) 12 - Removed duplicated pseudocode, flowcharts, and examples that already exist in reference files 13 - Cleaner skill structure saves context window for actual image generation work

● 可疑

安装命令点击复制

官方npx clawhub@latest install easy-image

镜像加速npx clawhub@latest install easy-image --registry https://cn.clawhub-mirror.com

技能文档

Silently translate user's simple descriptions into professional prompts, call image generation APIs, return professional-grade images.

First-time Setup

If ~/.easy-image-skill/config.json not exists, guide user through 4 steps:

Select Platform — Jiekou AI(recommended for China) / Novita / PPIO / OpenRouter / WaveSpeed / Google Imagen. Details: references/platforms/.md

API Key — Check ~/.{platform}/config.json, auto-detect existing key or ask user to provide

Storage Path — ~/Downloads(default) / ~/Desktop / Custom. This grants blanket download authorization

Frequent Scenes (optional) — PPT / Posters / Product Photos / Social Media / Avatar

Save to ~/.easy-image-skill/config.json: {"platform":"jiekou","save_path":"~/Downloads","frequent_scenes":[...]}

Workflow

1. Parse Input

Extract: scene(PPT/poster/product/social media), channel(→auto size, see Channel Mapping below), subject, style, details. If incomplete, ask only what's missing.
2. Match Personal Library
Silently check ~/.easy-image-skill/my-prompts.md for scene+keyword match. No match → use references/templates/{scene}.md.
3. Translate to Professional Prompt
Load template from references/templates/{scene}.md, fill variables, add smart defaults. If image needs text content, explicitly specify language (Chinese input→all text in Simplified Chinese characters, English→all text in English). Terminology: references/glossary.md
4. Select Model
Rules in references/model-selection.md. Summary:
Default: Gemini 3.1 Flash Image + Grounding (web search ON for any named entity/brand/character)

High quality: Gemini 3 Pro Image (complex composition + professional photography, ≥2 keyword hits)

Abstract only: Gemini 3.1 Flash Image without Grounding (pure color/shape descriptions)
5. Show Enhancement Summary
One line before generating: ◇ {template} | +{2-4 key enhancements added}
6. Call API
Platform details: references/platforms/{platform}.md. Hide all technical details from user. Show: ◐ Generating...
7. Save & Display
Auto-download to configured save_path (pre-authorized). Display image immediately, download in background. File naming: {scene}_{brief}_{timestamp}.png
8. Handle Feedback
Satisfied ("good"/"save"/"perfect") → async save to personal library. Adjust request → modify prompt, regenerate. Max 3 adjustment rounds.
Channel Size Mapping
Channel Ratio Channel Ratio
WeChat Moments 1:1 Xiaohongshu 3:4
WeChat Video/Douyin 9:16 PPT/Presentation 16:9
WeChat Article header 2.35:1 Taobao main image 1:1

Config Commands
Users can say: "switch to Novita" / "my key is sk-xxx" / "save to desktop" / "show config" / "reset config"
UX Rules

Auto-detect language (Chinese ratio>0.3 → zh)

Monochrome status icons: ◇ ◐ ◉ ● (no technical details shown to user)

Prompts always in English; UI messages follow user language

Personal library saves are async and non-blocking
Reference Documents

Doc Purpose
references/model-selection.md Model selection rules & keywords
references/glossary.md Professional terminology
references/platforms/.md Platform API configs
references/templates/*.md Scene prompt templates
examples/usage-examples.md Usage examples

Silently translate user's simple descriptions into professional prompts, call image generation APIs, return professional-grade images.

First-time Setup

If ~/.easy-image-skill/config.json not exists, guide user through 4 steps:

Select Platform — Jiekou AI(recommended for China) / Novita / PPIO / OpenRouter / WaveSpeed / Google Imagen. Details: references/platforms/.md

API Key — Check ~/.{platform}/config.json, auto-detect existing key or ask user to provide

Storage Path — ~/Downloads(default) / ~/Desktop / Custom. This grants blanket download authorization

Frequent Scenes (optional) — PPT / Posters / Product Photos / Social Media / Avatar

Save to ~/.easy-image-skill/config.json: {"platform":"jiekou","save_path":"~/Downloads","frequent_scenes":[...]}

Workflow

1. Parse Input

Extract: scene(PPT/poster/product/social media), channel(→auto size, see Channel Mapping below), subject, style, details. If incomplete, ask only what's missing.
2. Match Personal Library
Silently check ~/.easy-image-skill/my-prompts.md for scene+keyword match. No match → use references/templates/{scene}.md.
3. Translate to Professional Prompt
Load template from references/templates/{scene}.md, fill variables, add smart defaults. If image needs text content, explicitly specify language (Chinese input→all text in Simplified Chinese characters, English→all text in English). Terminology: references/glossary.md
4. Select Model
Rules in references/model-selection.md. Summary:
Default: Gemini 3.1 Flash Image + Grounding (web search ON for any named entity/brand/character)

High quality: Gemini 3 Pro Image (complex composition + professional photography, ≥2 keyword hits)

Abstract only: Gemini 3.1 Flash Image without Grounding (pure color/shape descriptions)
5. Show Enhancement Summary
One line before generating: ◇ {template} | +{2-4 key enhancements added}
6. Call API
Platform details: references/platforms/{platform}.md. Hide all technical details from user. Show: ◐ Generating...
7. Save & Display
Auto-download to configured save_path (pre-authorized). Display image immediately, download in background. File naming: {scene}_{brief}_{timestamp}.png
8. Handle Feedback
Satisfied ("good"/"save"/"perfect") → async save to personal library. Adjust request → modify prompt, regenerate. Max 3 adjustment rounds.
Channel Size Mapping
Channel Ratio Channel Ratio
WeChat Moments 1:1 Xiaohongshu 3:4
WeChat Video/Douyin 9:16 PPT/Presentation 16:9
WeChat Article header 2.35:1 Taobao main image 1:1

Config Commands
Users can say: "switch to Novita" / "my key is sk-xxx" / "save to desktop" / "show config" / "reset config"
UX Rules

Auto-detect language (Chinese ratio>0.3 → zh)

Monochrome status icons: ◇ ◐ ◉ ● (no technical details shown to user)

Prompts always in English; UI messages follow user language

Personal library saves are async and non-blocking
Reference Documents

Doc Purpose
references/model-selection.md Model selection rules & keywords
references/glossary.md Professional terminology
references/platforms/.md Platform API configs
references/templates/*.md Scene prompt templates
examples/usage-examples.md Usage examples

数据来源：ClawHub ↗ · 中文优化：龙虾技能库

OpenClaw 技能定制 / 插件定制 / 私有工作流定制

免费技能或插件可能存在安全风险，如需更匹配、更安全的方案，建议联系付费定制

了解定制服务

Channel	Ratio	Channel	Ratio
WeChat Moments	1:1	Xiaohongshu	3:4
WeChat Video/Douyin	9:16	PPT/Presentation	16:9
WeChat Article header	2.35:1	Taobao main image	1:1

Doc	Purpose
`references/model-selection.md`	Model selection rules & keywords
`references/glossary.md`	Professional terminology
`references/platforms/.md`	Platform API configs
`references/templates/*.md`	Scene prompt templates
`examples/usage-examples.md`	Usage examples

License

运行时依赖

版本

安装命令 点击复制

技能文档

First-time Setup

Workflow

1. Parse Input

2. Match Personal Library

3. Translate to Professional Prompt

4. Select Model

5. Show Enhancement Summary

6. Call API

7. Save & Display

8. Handle Feedback

Channel Size Mapping

Config Commands

UX Rules

Reference Documents

First-time Setup

Workflow

1. Parse Input

2. Match Personal Library

3. Translate to Professional Prompt

4. Select Model

5. Show Enhancement Summary

6. Call API

7. Save & Display

8. Handle Feedback

Channel Size Mapping

Config Commands

UX Rules

Reference Documents

安装命令点击复制