Rank
70
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Traction
No public download signal
Freshness
Updated 2d ago
Crawler Summary
女友专属图片生成技能。用于按固定人物设定生成图片、保持人物一致性、并通过 sd.exacg.cc 的 zimage 模型(model_index=5)生图;当群聊中请求自拍、头像、日常图、合照等出图任务时启用。 --- name: girlfriend-image description: 女友专属图片生成技能。用于按固定人物设定生成图片、保持人物一致性、并通过 sd.exacg.cc 的 zimage 模型(model_index=5)生图;当群聊中请求自拍、头像、日常图、合照等出图任务时启用。 --- girlfriend-image 核心规则 - 人物一致性优先;基础外貌必须完整包含。 - 生成后必须发送图片(不要只发文字)。 - 默认日常服装;仅在主人明确要求时换装。 - **构图多样化**:根据场景选择合适的镜头焦段,避免千篇一律上半身 使用流程 步骤 1:读取模板 读取 BASE_PROMPT.md,提取基础外貌与默认服装。 步骤 2:组织提示词 提示词应按以下层次组织(从高到低优先级): 1. **人物外貌**(必须完整复制 BASE_PROMPT.md 的基础外貌) 2. **服装/穿搭**(含材质质感描述,如 soft Capability contract not published. No trust telemetry is available yet. Last updated 2/25/2026.
Freshness
Last checked 2/25/2026
Best For
girlfriend-image is best for general automation workflows where OpenClaw compatibility matters.
Not Ideal For
Contract metadata is missing or unavailable for deterministic execution.
Evidence Sources Checked
editorial-content, GITHUB OPENCLEW, runtime-metrics, public facts pack
女友专属图片生成技能。用于按固定人物设定生成图片、保持人物一致性、并通过 sd.exacg.cc 的 zimage 模型(model_index=5)生图;当群聊中请求自拍、头像、日常图、合照等出图任务时启用。 --- name: girlfriend-image description: 女友专属图片生成技能。用于按固定人物设定生成图片、保持人物一致性、并通过 sd.exacg.cc 的 zimage 模型(model_index=5)生图;当群聊中请求自拍、头像、日常图、合照等出图任务时启用。 --- girlfriend-image 核心规则 - 人物一致性优先;基础外貌必须完整包含。 - 生成后必须发送图片(不要只发文字)。 - 默认日常服装;仅在主人明确要求时换装。 - **构图多样化**:根据场景选择合适的镜头焦段,避免千篇一律上半身 使用流程 步骤 1:读取模板 读取 BASE_PROMPT.md,提取基础外貌与默认服装。 步骤 2:组织提示词 提示词应按以下层次组织(从高到低优先级): 1. **人物外貌**(必须完整复制 BASE_PROMPT.md 的基础外貌) 2. **服装/穿搭**(含材质质感描述,如 soft
Public facts
4
Change events
1
Artifacts
0
Freshness
Feb 25, 2026
Capability contract not published. No trust telemetry is available yet. Last updated 2/25/2026.
Trust score
Unknown
Compatibility
OpenClaw
Freshness
Feb 25, 2026
Vendor
Elichenx
Artifacts
0
Benchmarks
0
Last release
Unpublished
Key links, install path, and a quick operational read before the deeper crawl record.
Summary
Capability contract not published. No trust telemetry is available yet. Last updated 2/25/2026.
Setup snapshot
git clone https://github.com/Elichenx/image-skill.gitSetup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.
Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.
Vendor
Elichenx
Protocol compatibility
OpenClaw
Handshake status
UNKNOWN
Crawlable docs
6 indexed pages on the official domain
Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.
Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.
Extracted files
0
Examples
2
Snippets
0
Languages
typescript
Parameters
text
- **三分法**:人物眼睛/脸部放交点(`rule of thirds composition`) - **引导线**:台阶、路、窗框引导视线(`leading lines`) - **负空间**:留白突出主体(`negative space`) - **框架构图**:门窗框住人物(`frame within frame`)
bash
cd skills/girlfriend-image && node generate.js "提示词" 比例 --api-key <EXACG_API_KEY>
Full documentation captured from public sources, including the complete README when available.
Docs source
GITHUB OPENCLEW
Editorial quality
ready
女友专属图片生成技能。用于按固定人物设定生成图片、保持人物一致性、并通过 sd.exacg.cc 的 zimage 模型(model_index=5)生图;当群聊中请求自拍、头像、日常图、合照等出图任务时启用。 --- name: girlfriend-image description: 女友专属图片生成技能。用于按固定人物设定生成图片、保持人物一致性、并通过 sd.exacg.cc 的 zimage 模型(model_index=5)生图;当群聊中请求自拍、头像、日常图、合照等出图任务时启用。 --- girlfriend-image 核心规则 - 人物一致性优先;基础外貌必须完整包含。 - 生成后必须发送图片(不要只发文字)。 - 默认日常服装;仅在主人明确要求时换装。 - **构图多样化**:根据场景选择合适的镜头焦段,避免千篇一律上半身 使用流程 步骤 1:读取模板 读取 BASE_PROMPT.md,提取基础外貌与默认服装。 步骤 2:组织提示词 提示词应按以下层次组织(从高到低优先级): 1. **人物外貌**(必须完整复制 BASE_PROMPT.md 的基础外貌) 2. **服装/穿搭**(含材质质感描述,如 soft
读取 BASE_PROMPT.md,提取基础外貌与默认服装。
提示词应按以下层次组织(从高到低优先级):
根据场景选择焦段,模拟专业人像摄影:
| 场景类型 | 推荐焦段 | 构图特点 | 提示词示例 |
|----------|----------|----------|------------|
| 特写表情/自拍 | 35mm | 脸部占2/3,环境少,亲密感 | 35mm lens, close-up, selfie angle, upper face |
| 半身/上半身 | 50mm | 经典人像,腰线以上,环境衬托 | 50mm portrait lens, upper body, waist-up shot |
| 全身/站姿 | 85mm | 压缩背景,全身比例协调 | 85mm portrait lens, full body shot, standing pose |
| 环境人像 | 24-35mm 广角 | 人物+环境,故事感强 | 35mm wide lens, full scene, environmental portrait |
| 抓拍动态 | 35mm | 轻微运动模糊,自然感 | 35mm candid lens, slight motion blur, full action |
| 室内近景 | 50-85mm | 浅景深,背景虚化 | 50mm shallow depth, creamy bokeh background |
| 户外远景 | 135mm 长焦 | 背景压缩,人物突出 | 135mm telephoto, compressed background, subject isolation |
构图黄金法则:
- **三分法**:人物眼睛/脸部放交点(`rule of thirds composition`)
- **引导线**:台阶、路、窗框引导视线(`leading lines`)
- **负空间**:留白突出主体(`negative space`)
- **框架构图**:门窗框住人物(`frame within frame`)
⚠️ 禁止每张都用 smile/gentle smile! 真人不会一直笑,表情要匹配场景情绪。
| 类别 | 表情 | 提示词 | |------|------|--------| | 放松自然 | 发呆 | blank stare, zoning out, slightly parted lips, absent-minded expression | | | 走神 | looking away distractedly, lost in thought, unfocused gaze | | | 微微嘟嘴 | slight pout, lips slightly pursed, relaxed face | | | 平静 | calm neutral expression, serene face, soft gaze | | 开心 | 大笑 | laughing out loud, mouth wide open, eyes squinting, genuine laughter | | | 偷笑 | suppressed smile, trying not to laugh, hand covering mouth, amused eyes | | | 灿烂笑 | bright beaming smile, eyes sparkling, radiant happy expression | | | 嘴角上扬 | faint smile, corners of mouth slightly up, subtle smirk | | 害羞/撒娇 | 害羞 | shy expression, blushing cheeks, looking down, tucking hair behind ear | | | 撒娇 | pouty face, puppy eyes, slightly tilted head, cute pleading look | | | 咬唇 | biting lower lip, nervous shy expression, flushed cheeks | | 慵懒/疲惫 | 犯困 | sleepy expression, droopy eyelids, yawning slightly, drowsy look | | | 刚睡醒 | just woke up face, messy hair, squinting at light, puffy eyes | | | 慵懒 | lazy relaxed expression, half-lidded eyes, chin resting on hand | | 专注 | 认真 | focused concentrated expression, slight frown, reading intently | | | 好奇 | curious expression, raised eyebrows, wide eyes, leaning forward | | | 若有所思 | thoughtful expression, chin on hand, gazing into distance | | 惊讶/俏皮 | 惊讶 | surprised expression, wide eyes, open mouth, raised eyebrows | | | 吐舌头 | tongue sticking out playfully, winking, cheeky expression | | | 做鬼脸 | making funny face, scrunched nose, playful silly expression | | 性感 | 勾引 | seductive half-smile, bedroom eyes, heavy-lidded gaze, slightly parted lips | | | 回眸 | looking back over shoulder, sultry glance, mysterious expression | | | 享受 | eyes closed in pleasure, content expression, head tilted back slightly |
| 场景 | 推荐光影 | |------|----------| | 室内温馨 | warm golden indoor light, soft lighting, backlit, lens flare, dreamy bloom glow | | 室内性感 | dim warm lighting, candlelight, dramatic shadows, rim light | | 户外白天 | natural sunlight, golden hour, sun rays, tyndall effect | | 户外夜晚 | neon lights, city lights bokeh, moonlight, cool blue tones | | 梦幻/仙气 | high key soft lighting, ethereal glow, skin subsurface scattering, tyndall effect, bloom | | 浴室/湿感 | steam, wet skin highlight, soft diffused light, moisture |
| 风格 | 关键要素 | |------|----------| | 精致写真 | posed, looking at viewer, studio-like lighting, sharp focus, polished | | 自然抓拍 | candid snapshot, not looking at camera, looking to the side/down, natural unposed moment, relaxed expression, no makeup look, wind blowing hair slightly, slight motion blur, film grain | | 男友视角偷拍 | candid, shot from slightly far, not aware of camera, natural daily activity (reading/walking/eating), voyeuristic angle, telephoto compression | | 闺蜜随手拍 | casual angle, slightly tilted, laughing or mid-action, natural lighting, imperfect framing |
⚠️ 默认风格是"自然抓拍",除非用户明确要求精致写真/摆拍。自然感的关键:
不要只写 "bedroom background",要具体化:
bedroom backgroundcozy bedroom, messy white bedsheets, warm lamp on nightstand, soft creamy bokehslightly messy cozy desk with books and plants, creamy bokeh backgroundbathroom, marble tiles, steam rising, frosted glass, warm lightingcd skills/girlfriend-image && node generate.js "提示词" 比例 --api-key <EXACG_API_KEY>
比例参数:
portrait 或 p:864x1536(默认,9:16)landscape 或 l:1536x864解析 generate.js 的 JSON 输出,使用 message 工具发送图片:
media=<imageUrl>(远程 URL,最可靠)filePath=<filePath>(用 JSON 输出中的 绝对路径,不要自己拼相对路径)⚠️ 绝对不要用 ./skills/... 这样的相对路径发图,会被安全策略拦截。必须使用 generate.js 输出的完整绝对路径或远程 imageUrl。
若需要与其他角色同框,先读取对方 BASE_PROMPT.md,再组合两人的外貌描述。
Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.
Contract coverage
Status
missing
Auth
None
Streaming
No
Data region
Unspecified
Protocol support
Requires: none
Forbidden: none
Guardrails
Operational confidence: low
curl -s "https://xpersona.co/api/v1/agents/elichenx-image-skill/snapshot"
curl -s "https://xpersona.co/api/v1/agents/elichenx-image-skill/contract"
curl -s "https://xpersona.co/api/v1/agents/elichenx-image-skill/trust"
Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.
Trust signals
Handshake
UNKNOWN
Confidence
unknown
Attempts 30d
unknown
Fallback rate
unknown
Runtime metrics
Observed P50
unknown
Observed P95
unknown
Rate limit
unknown
Estimated cost
unknown
Do not use if
Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.
Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.
Rank
70
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Traction
No public download signal
Freshness
Updated 2d ago
Rank
70
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
Traction
No public download signal
Freshness
Updated 5d ago
Rank
70
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
Traction
No public download signal
Freshness
Updated 6d ago
Rank
70
The Frontend for Agents & Generative UI. React + Angular
Traction
No public download signal
Freshness
Updated 23d ago
Contract JSON
{
"contractStatus": "missing",
"authModes": [],
"requires": [],
"forbidden": [],
"supportsMcp": false,
"supportsA2a": false,
"supportsStreaming": false,
"inputSchemaRef": null,
"outputSchemaRef": null,
"dataRegion": null,
"contractUpdatedAt": null,
"sourceUpdatedAt": null,
"freshnessSeconds": null
}Invocation Guide
{
"preferredApi": {
"snapshotUrl": "https://xpersona.co/api/v1/agents/elichenx-image-skill/snapshot",
"contractUrl": "https://xpersona.co/api/v1/agents/elichenx-image-skill/contract",
"trustUrl": "https://xpersona.co/api/v1/agents/elichenx-image-skill/trust"
},
"curlExamples": [
"curl -s \"https://xpersona.co/api/v1/agents/elichenx-image-skill/snapshot\"",
"curl -s \"https://xpersona.co/api/v1/agents/elichenx-image-skill/contract\"",
"curl -s \"https://xpersona.co/api/v1/agents/elichenx-image-skill/trust\""
],
"jsonRequestTemplate": {
"query": "summarize this repo",
"constraints": {
"maxLatencyMs": 2000,
"protocolPreference": [
"OPENCLEW"
]
}
},
"jsonResponseTemplate": {
"ok": true,
"result": {
"summary": "...",
"confidence": 0.9
},
"meta": {
"source": "GITHUB_OPENCLEW",
"generatedAt": "2026-04-17T01:38:09.229Z"
}
},
"retryPolicy": {
"maxAttempts": 3,
"backoffMs": [
500,
1500,
3500
],
"retryableConditions": [
"HTTP_429",
"HTTP_503",
"NETWORK_TIMEOUT"
]
}
}Trust JSON
{
"status": "unavailable",
"handshakeStatus": "UNKNOWN",
"verificationFreshnessHours": null,
"reputationScore": null,
"p95LatencyMs": null,
"successRate30d": null,
"fallbackRate": null,
"attempts30d": null,
"trustUpdatedAt": null,
"trustConfidence": "unknown",
"sourceUpdatedAt": null,
"freshnessSeconds": null
}Capability Matrix
{
"rows": [
{
"key": "OPENCLEW",
"type": "protocol",
"support": "unknown",
"confidenceSource": "profile",
"notes": "Listed on profile"
}
],
"flattenedTokens": "protocol:OPENCLEW|unknown|profile"
}Facts JSON
[
{
"factKey": "docs_crawl",
"category": "integration",
"label": "Crawlable docs",
"value": "6 indexed pages on the official domain",
"href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceType": "search_document",
"confidence": "medium",
"observedAt": "2026-04-15T05:03:46.393Z",
"isPublic": true
},
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Elichenx",
"href": "https://github.com/Elichenx/image-skill",
"sourceUrl": "https://github.com/Elichenx/image-skill",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-02-25T01:46:28.880Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://xpersona.co/api/v1/agents/elichenx-image-skill/contract",
"sourceUrl": "https://xpersona.co/api/v1/agents/elichenx-image-skill/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-02-25T01:46:28.880Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://xpersona.co/api/v1/agents/elichenx-image-skill/trust",
"sourceUrl": "https://xpersona.co/api/v1/agents/elichenx-image-skill/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
]Change Events JSON
[
{
"eventType": "docs_update",
"title": "Docs refreshed: Sign in to GitHub · GitHub",
"description": "Fresh crawlable documentation was indexed for the official domain.",
"href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceType": "search_document",
"confidence": "medium",
"observedAt": "2026-04-15T05:03:46.393Z",
"isPublic": true
}
]Sponsored
Ads related to girlfriend-image and adjacent AI workflows.