Menu
Generate images via SiliconFlow API (OpenAI compatible). Uses Qwen/Qwen-Image model.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | openai-image-gen-siliconflow |
| description | Generate images via SiliconFlow API (OpenAI compatible). Uses Qwen/Qwen-Image model. |
| metadata | {"openclaw":{"emoji":"🖼️","requires":{"env":["OPENAI_API_KEY"]},"primaryEnv":"OPENAI_API_KEY"}} |
使用 SiliconFlow API 生成图片，支持 Qwen/Qwen-Image 模型。
export OPENAI_API_KEY="your-siliconflow-api-key"
# base URL 已默认配置
必须用 python3.12+，不能用系统默认的 python3（macOS 默认是 3.9）
原因：gen.py 使用了 str | None 类型注解语法（Python 3.10+ 才支持），在 3.9 上会报错：
TypeError: unsupported operand type(s) for |: 'types.GenericAlias' and 'NoneType'
Qwen/Qwen-Image 模型用 image_size 而不是 sizequality 参数gpt-image-1（OpenAI），需显式指定 --model "Qwen/Qwen-Image"/images/generations（不是 /image_generation）OPENAI_API_KEY="sk-..." python3.12 {baseDir}/gen.py \
--model "Qwen/Qwen-Image" \
--prompt "描述" \
--count 1 \
--out-dir /tmp/output
import requests
api_key = "sk-..." # SiliconFlow key
r = requests.post(
"https://api.siliconflow.cn/v1/images/generations",
headers={"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"},
json={"model": "Qwen/Qwen-Image", "prompt": "test", "image_size": "1024x1024", "n": 1}
)
print(r.json()) # 成功返回 {"images": [{"url": "..."}]}
--model: 模型名称（必须填 Qwen/Qwen-Image）--prompt: 图片描述--count: 生成数量--size/--image_size: 尺寸（Qwen 模型用 image_size）a beautiful Chinese woman, 28 years old, elegant makeup, stunning appearance,
taking a mirror selfie, wearing stylish outfit, realistic photo style, soft lighting
注意：Qwen-Image 模型生成的风格是"规矩流动"型，和 MiniMax 风格不同。人物一致性不如专业模型，但真实感较好。
OPENAI_API_KEY=sk-cyfunmsszjrqumckweykgkjojjfbclilbbochdvprfezqgcw
SILICONFLOW_BASE_URL=https://api.siliconflow.cn/v1
| 问题 | 原因 | 解决方案 |
|---|---|---|
401 Invalid token | endpoint 路径写错 | 用 /images/generations 不是 /image_generation |
TypeError: unsupported operand | Mac python3 是 3.9 | 必须用 python3.12 |
| 生成图片糊/不像 | prompt 没加 realistic photo style | 显式指定风格关键词 |
🧠 ontology-clawra v5.1 - Local Ontology Reasoning & Learning Engine **USE THIS SKILL WHENEVER** you need structured reasoning, knowledge graph management, logical inference, or learning from interactions. This is your go-to tool for: - Building and querying ontology knowledge graphs (concepts, entities, relationships) - Performing confidence-based reasoning with evidence tracking - Recording insights and patterns from completed tasks - Local memory search and knowledge retrieval **Key Use Cases:** - Before making complex decisions: "Let me use ontology-clawra to reason about this" - After completing tasks: "Record this learning to ontology-clawra" - Building domain expertise: "Create concepts for [domain] in ontology-clawra" - Analyzing patterns: "Query ontology-clawra for similar past cases" **Core Capabilities:** ✅ Local ontology storage in `~/.openclaw/skills/ontology-clawra/memory/` ✅ Confidence calculation (CONFIRMED/ASSUMED/SPECULATIVE) ✅ Learning from user confirmations ✅ Local memory search (no ne
Complete guide to using and extending Hermes Agent — CLI usage, setup, configuration, spawning additional agents, gateway platforms, skills, voice, tools, profiles, and a concise contributor reference. Load this skill when helping users configure Hermes, troubleshoot issues, spawn agent instances, or make code contributions.
Git push to HTTPS remote using token authentication — avoids SSH setup, works in CI/automated environments.
从 GitHub 历史中彻底清除敏感文件的完整流程 — 使用 git filter-repo + force push，适用于清理意外提交的个人文件、工作文件等
清理 GitHub 历史和 ClawHub 中意外泄露的个人/工作文件
Configure WhatsApp and Telegram messaging platforms on Hermes Agent