#ai-agent

Beginner tutorial: have your AI agent search the web for an unfamiliar industry using the five forces model, then use a fresh chat to check the sources, ask peers and customers what the web cannot answer, try a small task yourself, and pick a first step based on how much you can afford to lose, with 6 copy-ready prompts.

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.

Intermediate tutorial: Give your AI agent the ai-host-video Skill and connect it to the video platform jqsp.com. Set up the host, background extras and voice once. After that, each video only needs the video type, the target audience and the website URL. Your AI agent reads the site as the Skill describes, writes the copy and a three-shot script, checks every storyboard frame, renders, then adds B-roll and bilingual voiceover. In our test, a two-minute bilingual video cost about 169 credits, or about $0.42. Includes 4 copy-paste 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 REA, an open-source reverse-engineering tool. Point it at an app and a feature, and it takes the feature apart without the source code, explaining the workflow with evidence. Once you understand the principle, it writes its own version from scratch in your project and adds one improvement. Includes 3 copy-paste prompts.

Intermediate tutorial: Hand REM, an open-source competitor research tool, to your AI agent. Run a free first check, read the ads, social, search page and website redesign reports, turn one finding into next week's experiment, then re-run and compare a week later. Includes 3 copy-paste prompts.

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.

Intermediate tutorial: Have your AI agent set up the official AWS Emulator and its Skill, confirm it is running locally and not against your real AWS account, point your project SDK at it to run tests, and check which features you can trust by their fidelity scores. Includes 3 copy-paste prompts and 5 FAQs.

Beginner tutorial: connect several inboxes in NetEase Mail Master, set rules so Mail Agent only saves drafts and never makes things up, then have it audit subscriptions and renewal risks, export tables, turn newsletters into a weekly brief, and track partner emails as a progress table. Includes four copy-and-paste prompts.

You open the recording during a meeting, and later you can ask AI what you discussed this week, with whom, and which items still need follow-up

Intermediate tutorial: Put a team of AI agents on shifts, one job each: morning briefings, group chat triage, X growth, content repurposing, competitor watch, lead hunting, subscription audits, a second brain, multi-agent coordination, and small tool building. Start with the morning briefer, add two roles a week after that, and keep every message, payment and post waiting for your OK. Includes 10 role briefs you can copy and paste.

Beginner tutorial: connect the ChatCut AI editing tool to your AI agent, have it study a reference video's pacing, subtitles and motion graphics, save them as a style card, then cut your own talking-head footage to that card. Review the cut and write fixes back into the card. Includes 3 prompts you can copy as-is.

A daily trend briefing delivered automatically with sources, every item in the source table traceable, topics scored, first-draft facts easy to verify, and reusable conclusions from reviews.