ListenHub
Turn ideas into podcasts, explainer videos, voice narration, and AI images via ListenHub
共 361809 条已上架资产
Turn ideas into podcasts, explainer videos, voice narration, and AI images via ListenHub
Create mathematical animations with synchronized voiceover narration and subtitles using Manim Community and manim-voice…
SenseAudio Text-to-Speech (TTS) API for converting text to natural speech
调用百度PaddleOCR-VL大模型API解析文档
Identify and reduce Azure bandwidth and egress costs — often the most invisible Azure cost driver
对 OpenClaw 管理的服务器执行轻量级安全基线审计,识别高风险的 SSH/防火墙问题,并提供一键修复及合规性
英语一对一私教技能,提供中英翻译练习和个性化教学反馈
中文翻译成英文的专业翻译技能,专为悬疑/推理/纪实类文本(如真实犯罪短视频、案件解说、刑侦分析)设计
梓享AI双擎搜索平台官方付费技能,通过POST请求调用搜索接口,支持中国区/全球双引擎,返回结构化JSON搜索结果,按调用次数计费
Search and execute dynamic tools via QVeris API
Build and execute an SEO strategy for organic search traffic
印象笔记 API skill,用于管理用户的印象笔记
通过关键词进行网络搜索,批量抓取网页并截图,最终汇总成专业PPT演示文稿
Transition from vibe coding to vibe clawing by trusting agents with full responsibilities, designing self-closing loops,…
抓取雪球/网页资料,整理为带格式的 Markdown,通过微信公众号草稿箱 API 直接入库(不群发、无需浏览器登录)
当用户明确想做“浏览器扩展多模型API”,或提到独立开发与微型SaaS中的相关身份和任务时使用
Use when AI agents need to read, inspect, operate, navigate, debug, or verify browser state through the omnibot CLI and …
Browser automation workflows through the agentbrowse CLI for launch, attach, observe, act, extract, navigation, and scre…
当操作员需要本地或远程GUI代理来驱动桌面、浏览器和计算机使用任务并支持多模态模型时,请使用UI-TARS Desktop
"【Agent 浏览器操作助手】让 Agent 通过 Playwright/Selenium 完成网页打开、填表、点击、提取与登录态复用,附可运行脚本