#skill

Beginner tutorial: install an open-source video editing skill for your AI agent, then hand it your recorded talking-head video. It removes filler words and half-finished sentences, checks every cut, adds subtitles and effects, and hides URLs that show up on screen. You check the result against a checklist before you publish, with 3 copy-ready prompts.

Use when the user gives a URL, product page or tutorial page to promote and wants an explainer or promo video with a host on camera. The agent reads the page, writes copy and a three-shot script, builds a lip-synced host and silent background extras on jqsp.com, checks each storyboard grid panel by panel, adds B-roll, captions and a QR code, then makes a second-language dub with local F5-TTS. Every paid step is quoted first, no numbers are invented, and no one else's likeness is used. Use case: In one line: give your AI agent a URL, and it makes an explainer video with a host, background extras and a bilingual voiceover.

Intermediate tutorial: have your AI agent install the free, open-source Mono Editorial Landing Skill and draft a black-and-white, magazine-style landing page from your README. You write the headline and pick whether the top of the page shows a sign-up form or buttons. The agent checks the layout at four screen widths and hands back an HTML file you can upload as is, then walks you through putting it online. Includes 3 copy-paste prompts.

Intermediate tutorial: On a Windows PC with AutoCAD, have your AI agent install an open-source Skill and redraw a photo, scan, sketch, or screenshot of an old drawing as an editable DWG. Each dimension is labeled as written on the drawing, calculated from scale, or inferred. Then overlay the result on the original and check the key dimensions yourself. Includes 3 copy-paste prompts.

An open-source Agent Skill that lets AI agents like Claude Code and Codex write instrumental music note by note, render it with real instrument samples, and export MP3, MIDI, stems and an editable project. Includes seven example tracks, setup requirements, commercial limits and a ready-to-use prompt.

Use when the user wants to cut silence and pauses out of talking-head videos, screen recordings, or podcasts, shorten a recording, fast-forward quiet passages, or import the auto-cut result into Premiere, DaVinci Resolve, Final Cut, or similar editors. Based on the open-source command-line tool auto-editor. Preview first, then render, and never overwrite the original. It judges only by volume and picture, so it cannot catch slips of the tongue. Use case: Let your AI agent cut the silence and pauses out of a talking-head video in one pass, then export an editor project to keep polishing in your own software

Intermediate tutorial: Split your talking-head recording into one clip per sentence, then have your AI agent install the open-source skill and run its demo first. Answer three setup questions about theme, logo and materials. Approve the scene table before reviewing key frames, then render, mix and frame-check the final video. Includes 3 copy-ready prompts.

Use when you want to wrap a set of talking-head clips in a finance or science explainer video with big numbers, card walls, charts, a world map and web screenshot highlights, or redo the explainer visuals for an existing talking-head video. The agent asks about background, logo and materials first, writes a scene table for your approval, researches and writes a facts file, builds the storyboard with Remotion layouts, reviews key frames, then renders, mixes and frame-checks the video. It does not write scripts or generate on-camera footage, keeps the AI-generated label, and never uses a real creator's logo, portrait or voice. Use case: Let your AI agent turn your talking-head clips into explainer videos with animated charts and sourced numbers.

Use when the user wants a prospect list, a target company list, or wants to know who to contact at a certain type of company. The agent queries the people and company data sources in Firecrawl Alexandria, finds companies first, then people, and fetches work emails only for the shortlisted people. The output is a ranked table or CSV with a source on every row, and it can run weekly to show only new prospects. It never guesses emails, looks up personal contact info or sends outreach, and it quotes the cost before spending credits. Use case: Have your agent build a verified, sourced B2B prospect list from your customer profile.

Use when you want to know how a company gets customers, what ads it is running, how several competitors' channels compare, or you want a promotion plan modeled on a rival's playbook. Your AI agent runs the open-source tool REM to collect public evidence on ad libraries, tracking tags, SEO, social media, founders, pricing and past selling points, then writes a report where every claim cites an evidence number and anything it could not find is listed separately. Public sources only. It does not invent spend and does not copy the rival's creatives. Use case: Have your AI agent map out a rival's customer acquisition playbook, with every judgment backed by evidence.

Song Xiatian Dazzle (宋夏天Dazzle) released the map Skill Three Scope Map 3.0, which lets your AI agent generate runnable 3D globe and administrative-region map projects. Click from the globe into China, its provinces, cities, and districts or counties. Switch between 3D, 2D, and 2D layered over 3D views, recolor everything in one step, and use the new native React support. Note that it uses a custom license with platform restrictions, not an open-source license.

Use when the user wants to learn AI Agents from scratch, asks where to start, wants beginner tutorial recommendations, or pastes a cwyz.com tutorial link and says 'walk me through this one'. First asks three multiple-choice questions about the user's goal, tools and computer, then picks suitable tutorials from CWYZ's free beginner path and tutorial list and walks through them step by step. The Agent runs the prompts in the tutorials and asks before installing software or spending money. When a section needs unlocking, it points the user to unlock it on the site with credits and does not work around it. It can save learning progress and suggest the next tutorial. Use case: One line: have your AI agent pick free CWYZ beginner tutorials for your goal and walk you through them step by step

Use when the user wants meeting, conversation or lecture recordings in a personal knowledge base: sync automatically from Feishu, or process transcripts exported from tools like Zoom, Google Meet or Otter. Also for capturing ideas, saving articles, and looking up past conversations about a person or project. Originals are never edited, and new people are confirmed before they get a profile. CC BY-NC 4.0, non-commercial use only. Use case: In one line: your AI agent saves each meeting recording as an original, writes the notes, identifies people and to-dos, and can answer questions about them later

Intermediate tutorial: install the open-source AutoHarness plugin and Claude Code starts reviewing your work in the background. It turns the methods it finds in a session into Skills, combines similar ones, updates a Skill when you correct it, and archives the ones you stop using. Check your Python version first, install with two commands, save a lesson by hand with /learn, and review what it has learned. Includes 3 copy-ready prompts.

Beginner tutorial: Use the open-source Hypit to give Claude Code or Codex a video-making skill. Hand it a reference video, have it break down the opening hook, pacing, and subtitle structure first, then swap in your product, presenter, and language to regenerate. Get a price quote before spending money, and reuse assets to batch out several versions. Includes 4 copy-ready prompts.

Beginner tutorial: turn one full-body image of your character into transparent animations with sprite-gen, an open-source Skill for Codex or Claude Code. Choose between GPT frame-by-frame or Grok video, write the actions, loops and export format, remove bad frames in the curator, and export animations for videos, animated stickers or websites. Includes 3 copy-paste prompts.

Use when the user wants public information about businesses of one type in one place (name, address, phone, website, rating, reviews, and optionally public emails on the website) for B2B lead generation or local market research. Runs an open-source scraper in Docker on the local machine. Explains Google's terms and local legal risks first, runs a one-query sample before a full run, and returns only public business information, with cleaned emails labeled unverified. Use case: Have the Agent turn the public information about one type of business in one place into a customer list.

Use when the user wants to turn one image (an AI image, a render, a photo of a figurine or product, a hand-drawn sketch) into a 3D model, a 3D-printable sculpt, or a time-lapse video of a sculpting process, or wants to check how far a model is from the original image. Faces the photo can see are fitted to the photo, hidden back and side faces are filled from generated views that agree with each other, every step is recorded and replayed in Blender, and GLB/OBJ/STL are exported. It needs paid fal endpoints (about $2 per model), so state the cost before starting. Use case: Have the agent turn one image into a 3D sculpt that matches the original, and replay the whole sculpting process.

Use when the user wants to make 3D animation, 3D characters, cutaway demos, science maps and timelines, or to edit short videos or add sound effects. 12 Skills plus two commands, /3dg and /2dg, work with free tools such as Blender, Three.js, Remotion, and FFmpeg. Clarify needs first, make a preview before the final version, and get consent before installing any software. Use case: Let an agent make 3D animation, characters, science maps and short videos for you

Beginner tutorial: get Claude Code or Codex ready, ask it in one sentence to install Creator Generalist and the free software it needs, then describe what you want in plain words. Answer a few multiple-choice questions, check a preview, and say where to change things if you are not satisfied. Includes 4 prompts you can copy directly.