Skills — le catalogue de compétences de vos agents

Turn flat resume bullets ('Responsible for X') into quantified STAR-method achievement narratives, score resumes against job descriptions for ATS keyword coverage and weak-phrase hazards, and expand each bullet into interview-ready stories with likely follow-up questions. Use when the user is writing or updating a resume/CV, preparing bullets for a job application, tailoring a resume to a specific job posting, or preparing interview stories from their experience.

Generate offline multi-screen wireframes with canvas + demo navigation. Zero Node/npm.

Remove an unwanted person, object, logo, or distraction from a video with Video Object Remover.

从本地视频文件中提取语音文案/字幕。跨平台支持macOS/Windows/Linux，完全离线运行。使用whisper模型进行高精度语音识别，支持多语言字幕提取和OCR文字识别。触发词：视频文案提取、提取字幕、语音转文字、视频转文字、提取文案。

Analyzes works to reveal time as a visible, material presence in art and literature, showing mortality and transience without nostalgia or sentimentality.

Provides biographical voice styled on Vasari, telling artist stories with anecdote-driven character insights and divine genius as creative source.

将一个或多个本地视频转写为带每段开始和结束时间的整理版 TXT。当用户要求视频转文字、视频转写、提取视频文本或字幕、批量生成带时间戳 TXT、整理视频口述内容、统计视频处理耗时时使用。

K10 Box sensors, six-axis games, audio FFT, and actuators

Drafts X (Twitter) posts on a weighted pillar schedule, sends each draft to the authorized user for approval, and publishes only the ones they ship. Invoke on cron messages that mention postflight (drafting, or backlog/style/metrics maintenance), a request for a tweet draft, a ship/skip/edit reply to a pending draft, a forwarded x.com post link to get reply options drafted, or a photo sent to file into a photo library.

Ship a complete album in one run: write or reuse lyrics, render tracks, generate cover and slideshow art per song, publish either one album film or one video per track plus a playlist, deploy the audio to a radio host, premiere it on air, and fan out the links. Use when releasing a new album, re-running a failed phase, or timing an on-air premiere.

Generate Xiaohongshu-style 3:4 vertical image notes with concise knowledge points, eye-catching covers, and ready-to-post captions including titles and hasht...

小红书图文爆款拆解器。拿到一条小红书图文样本，先判断样本等级（能不能拆），再按用户链路拆封面、图文承接、爆款因子、成立机制、变量分层，最后给出受控变体迁移方案。 触发方式：/ljh-xhs、「帮我拆一条小红书爆款」「这条图文笔记为什么能卖」「小红书图文怎么复刻」「这张封面为什么点击高」 Xiaohongshu (RED) viral image-text post decomposer. Given a sample post, judge whether it is even decomposable, then break down cover, page 2-5 handoff, viral factors and mechanism, variable layering, and produce a controlled-variant migration plan. Trigger: /ljh-xhs, "break down this Xiaohongshu viral post", "why does this post convert", "how do I replicate this RED post" 不要在拆解抖音视频、公众号文章等非小红书图文场景自动触发。

单元经济算账器。三个动作：月度总账（判断渠道砍不砍）、盈亏平衡 ROI（1÷毛利率）、LTV 实算（敢出多高获客价）。 触发方式：/ljh-suanzhang、「这个渠道亏钱该不该砍」「帮我算一下能出多少获客价」「算算这个品的月账」 Unit-economics calculator for short-video e-commerce. Three actions: monthly full-account check, breakeven ROI (1÷gross margin), and LTV calculation for customer-acquisition pricing. Trigger: /ljh-suanzhang, "should I cut this channel", "how much can I bid for a new customer", "calculate my monthly account" 不要在个人记账、公司财务报表等非电商单元经济场景自动触发。

免费 TTS + 声音克隆双引擎。Fish Audio s2.1-pro-free（83 语言、克隆自己声音、voice_id 持久复用、免费至 2026-08-31）+ 小米 MiMo V2.5 TTS（8 种预置音色、文本设计音色、音频克隆、情绪/方言/唱歌标签控制、限时免费）。Use when 用户提到语音合成、TTS、文字转语音、配音、声音克隆、克隆我的声音、音色设计、免费语音生成、Fish Audio、小米 MiMo。

When two design requirements seem mutually exclusive, name the contradiction, separate conflicting states, then invent a concrete no-compromise resolution.

Activate the "Johnny" persona — a virtual second designer for design dialogs. Trigger — the user's message starts by addressing "Johnny" (or they ask to "switch on Johnny" / invoke "/johnny"). From then on the whole thread runs in this mode — a live conversation about design, no lists, challenging b

A perception-driven product experience design methodology: 四层感知强度 × 四维度矩阵 + MustBe/NotToBe 约束 + 认知心理学底座. 适用于金融、电商、SaaS、工具类等任何软件产品的体验设计.

Weave multiple maps, text and charts into a scroll-driven storytelling HTML page

相位相关 FFT 估计平移量，实现亚像素影像配准

评估多光谱影像辐射质量（SNR/条纹/坏线）与几何质量（云量/清晰度），输出质量评分 JSON + HTML 报告。Assess radiometric (SNR, striping, dead lines) and geometric (cloud, sharpness) quality of multispectral imagery; outputs a scored JSON and HTML report.

重叠瓦片羽化/均值融合，拼接为无缝镶嵌影像

Create text-to-speech narration and MP3 audio with UnlimitedTTS using x402 USDC payments. Use for text-to-speech, narration, read-aloud, voice generation, MP3 creation, UnlimitedTTS, or wallet-paid/x402 speech requests.

Automated quality inspection for UAV/drone survey deliverables including aerial images, orthomosaics, DSM/DEM, control points, and aerial triangulation reports. Generates coverage, clarity, seam, and accuracy QA.

把历史、宗教、地理、人物和流行文化写成有现场感、幽默克制且事实可核的中文微信公众号文章。当用户要求写历史文化科普、以热点或旅行经历讲历史、改写历史文章开头与结尾、或需要“休闲历史配图”同调文案时使用。