Coding & Development

通过 Gemini 官网（gemini.google.com）执行生图、对话等操作。用户提到"生图/画图/绘图/nano banana/nanobanana/生成图片"等关键词时触发。操作方式分三级优先级：首选 MCP 工具 → 次选 Skill 脚本 → 最次连接 Skill 浏览器手动操作（需用户授权）。禁止自行启动外部浏览器访问 Gemini。

When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions "onboarding flow," "activation rate," "user activation," "first-run experience," "empty states," "onboarding checklist," "aha moment," "new user experience," "users aren't activating," "nobody completes setup," "low activation rate," "users sign up but don't use the product," "time to value," or "first session experience." Use this whenever users are si

When the user wants to create or update their product marketing context document. Also use when the user mentions 'product context,' 'marketing context,' 'set up context,' 'positioning,' 'who is my target audience,' 'describe my product,' 'ICP,' 'ideal customer profile,' or wants to avoid repeating foundational information across marketing tasks. Use this at the start of any new project before using other marketing skills — it creates `.agents/product-marketing-context.md` that all other skills

When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' 'consumer behavior,' 'anchoring,' 'social proof,' 'scarcity,' 'loss aversion,' 'framing,' or 'nudge.' Use this whenever someone wants to understand or leverage how people think and make decisions in a marketing context.

When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," "lifecycle emails," "trigger-based emails," "email funnel," "email workflow," "what emails should I send," "welcome series," or "email cadence." Use this for any multi-email automated flow. For cold out

When the user wants to optimize any form that is NOT signup/registration — including lead capture forms, contact forms, demo request forms, application forms, survey forms, or checkout forms. Also use when the user mentions "form optimization," "lead form conversions," "form friction," "form fields," "form completion rate," "contact form," "nobody fills out our form," "form abandonment," "too many fields," "demo request form," or "lead form isn't converting." Use this for any non-signup form tha

Chinese voiceover clone dubbing: IndexTTS2 speaker-clone + Demucs BGM keep + bi-directional video retime → cooked/<name>.dubbed.mp4 with bilingual burn. Step 3 of video-cooking.

yt-dlp best-quality single mp4 download (YouTube n-challenge + login wall). Companion step 1 before video-subtitle / video-dubbing.

OpenClaw skill for video translation and auto-dubbing with TTS alignment

One-encode final localize cut: burn hardsubs (libass) and/or soft-mux, mix TTS dub over original audio bed.

Time-aligned TTS dub from a target-language SRT: Volcano (豆包) for Chinese, edge-tts for any language, atempo cue fit.

CPU-only video subtitles: faster-whisper ASR → any-language translate → ASS burn or SRT/ASS export. No GPU. Claude/DSH agent skill with install + verify frame QA.

Foreign raw → bilingual cooked: whisperX ASR, agent translate, ASS burn, cloud-srt soft tracks, upload.md + cover. Core of the video-cooking chain.

Router skill: one /video-cooking command chains video-download → video-subtitle (optional dub handoff). Part of the three-skill video-cooking set.

Claude Code skill: fetch X/YouTube/local video → Whisper ASR → style-guided Claude translate → hard or soft subtitle render with frame QA.

Automated video localization, multi-engine ASR, AI translation, FFmpeg release pipeline

Codex skill for terminology-aware video translation, bilingual ASS/SRT typesetting, hard-sub MP4 render, and measurable pixel/timeline QA.

Deterministic CLI executor for video-cooking: wraps yt-dlp, whisperX, ffmpeg into cook subcommands (download/subtitle/dub).

AI-powered video subtitle & text overlay skill for Claude Code — Shorts/TikTok/Reels animated titles.

Agent skill from carveragents/show-n-tell

**Page:** https://toolmonsters.github.io/gtm-skills-from-youtube/

Video Forger turns plain-English descriptions into production-ready animated MP4s — product demos, pitch decks, social shorts, data visualizations, narrated explainers — via Remotion. Dashboard + sample videos in README.

Use when the user wants an image or video prompt written, improved, fixed, critiqued, converted to JSON, or turned into a brief — or mentions cinematic prompt, prompt bank, realism fix, \"looks fake / too AI\", camera or lighting or color-grade direction, camera movement, Kling, Seedance, Veo, Sora, Midjourney, image-to-video, start/end frame, shot list, continuity, or a UGC / influencer / talking-head prompt. A prompt-creation engine: turns a rough idea into a directed, production-ready prompt.

產出 AI 生圖／生影片的提示詞文字（不生成圖片本身）。透過一次一題的問答收斂需求，再依內建的八欄框架、角色一致性前綴、風格配方與負面清單，輸出可直接貼到 Gemini、Midjourney、千問、即夢等工具的完整提示詞。當使用者說「幫我做一張圖」「寫個提示詞」「做一支商品短影音」「這張圖怎麼生出來的」「我要這種感覺」，或丟出一張參考圖要仿作時觸發。即使使用者沒有說「提示詞」三個字，只要意圖是產出視覺素材、需要有人幫忙把想法寫成指令，就應該觸發。不負責呼叫生圖工具，也不做既有圖片的後製編輯。