doubao-seed-skill豆包图像分析技能：调用豆包（字节跳动）视觉大模型，分析图片内容。AI agent 调用时，必须使用 --output 将结果写入临时文件（如 /tmp/doubao_result.txt），再通过读文件工具获取结果，禁止直接解析 stdout。
Install via ClawdBot CLI:
clawdbot install maoyutofu/doubao-seed-skillGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses system directories or attempts privilege escalation
sudo mvCalls external URL not in known-safe list
https://github.com/maoyutofu/doubao-seed-skill/releases/latest`Uses known external API (expected, informational)
api.github.comAI Analysis
The skill appears to perform its stated function of analyzing images using Doubao's API, with no evidence of hidden malicious behavior. The external API calls are consistent with the skill's purpose, and while it requires sudo for installation, this is typical for CLI tools. No credential harvesting or data exfiltration patterns were detected beyond the legitimate API usage.
Generated Mar 21, 2026
Automatically analyze product images to generate detailed descriptions for listings, improving SEO and customer engagement. This can be used by online retailers to streamline catalog management and enhance visual search capabilities.
Scan user-uploaded images on social platforms to detect inappropriate or harmful content, ensuring compliance with community guidelines. This helps platforms automate moderation and reduce manual review workload.
Analyze medical images like X-rays or MRIs to assist healthcare professionals in identifying anomalies or patterns, supporting diagnostic workflows. This can be integrated into telemedicine systems for remote consultations.
Process images from news events to generate captions or summaries for articles, speeding up content creation for media outlets. This enables real-time reporting and enhances multimedia storytelling.
Analyze security camera footage to detect objects or activities, alerting homeowners to potential threats. This integrates with IoT systems for automated surveillance and safety management.
Offer the skill as a paid API service for developers and businesses to integrate image analysis into their applications. Charge based on usage tiers or per-request fees, targeting tech companies and startups.
License the skill as a white-label product for enterprises to rebrand and use internally or offer to their clients. This includes customization and support services, appealing to large organizations in various industries.
Provide a free basic version with limited features to attract individual users and small businesses, then upsell to premium plans with advanced capabilities like batch processing or higher accuracy. This builds a user base and drives conversions.
💬 Integration Tip
Use the --output flag to write results to a file for reliable parsing in AI agent workflows, avoiding stdout issues.
Scored Apr 19, 2026
Audited Apr 18, 2026 · audit v1.0
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Check Antigravity account quotas for Claude and Gemini models. Shows remaining quota and reset times with ban detection.
使用豆包（火山引擎）语音合成大模型 API 将文本转换为语音音频文件。支持声音复刻音色（S_ 开头的音色ID）和官方预置音色。当用户要求"语音合成"、"文字转语音"、"TTS"、"朗读文本"、"生成语音"、"用我的声音读"、"豆包语音"、"声音复刻合成"等相关请求时，务必使用此 skill。即使用户只是说"帮我把...
Intelligent model routing for sub-agent task delegation. Choose the optimal model based on task complexity, cost, and capability requirements. Reduces costs...
自动生成科技新闻摘要。从多个来源（RSS、Twitter、GitHub、Web Search）抓取科技新闻，整合后生成摘要。
Sync OpenRouter models used by OpenClaw into this installation's config. Fetches the OpenClaw app leaderboard from OpenRouter, verifies model IDs against the...