#agent

The open source reverse engineering tool REA lets an AI agent take apart an app without its source code. Point it at a niche Android app and have it map only the user roles, flows, core data, and pricing points. Then build your own version from that brief. Includes a ready prompt and a note on install steps and infringement risk.

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

Intermediate tutorial: Upgrade OpenCode, write a goal you can check, start it with /goal, watch its status, pause and resume it, read why it stopped, and re-check the result once it's met. Includes 4 copy-paste prompts.

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: Use one table to see the five layers of an AI product, from compute to agents, and decide how deep to go based on your target role. Then have your AI agent coach you with scenario questions about a product you know, run a side-by-side test of two options on the same task, and turn the results into a one-page trade-off report you can take to an interview. Includes 3 copy-ready prompts.

Six bots with clear roles research and trade on a fixed schedule. Every decision is logged. Real-money trading expands one step at a time, and each trade waits for a human approval.

Subscription quota often beats pay-per-use API calls by several times. Give your own non-urgent, one-off back-office jobs to your AI agent, and use the API only for features that serve users live at high volume. Includes four questions to decide and the limits you must not cross.

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.

Say what kind of business to find and where, and get a cleaned business table with website, phone, rating and reviews.

Beginner tutorial: first have your agent sort each step in a run log into four categories. Pick one judgment that repeats dozens of times a day and hand it to TypeSafe's Jev. Write the question by the question-writing rules, route by confidence, send uncertain cases to a large model, and do a one-week shadow run before switching. Includes 3 prompts you can copy directly.

Advanced tutorial: Borrow Posteady's five-module split to set up a local content workspace with Claude Code or Codex. Collect material daily, score topics, write one draft for many platforms, schedule posts, and review weekly to feed the next topic picks. The publish button always stays with you. Includes 5 prompts you can copy and paste.

Beginner tutorial: prepare the topic, final script, screenshots, and voice-over, have your agent install the open-source Skill, send the first task brief, then check the voice-over, material list, storyboard, first three seconds, and full cut one by one. You publish it yourself at the end. Includes 2 prompts you can copy directly.

The open-source Poki project has released a preview iPhone app. An AI agent reads the screen, taps, and types on the phone locally. It takes commands from the app, iMessage, Telegram, or a terminal, and it can plug into Claude Code and Codex as an MCP server. Payments, deletions, and messages need your approval in the Dynamic Island first.

A beginner tutorial: have your agent install Vercel's open-source agent-desktop, grant the accessibility permission yourself, then add the official Skill. Start with a read-only trial, have it describe its plan and wait for your go-ahead, and finally hand it the work of clicking back and forth between several apps, checking the interface when it's done. Includes 3 copy-ready prompts.

Learning something new used to mean getting through a steep entry phase first. Now you can have an Agent take you straight to a result. Fixed steps like commands and configuration can be written into a Skill and handed off, so you don't have to memorize them. But checking the result is something you always have to do with your own head.

A beginner tutorial: first have the Agent run a read-only health check on your notes vault, then write down folder conventions and guardrails, install kepano's obsidian-skills and an open-source digital garden Skill set, and day to day only ask it to find related notes and orphan notes. After a month, run the check again and compare, then handle the batch of empty shell notes yourself. Includes 3 copy-ready prompts.

A beginner's tutorial: tell the agent only the context the code doesn't show, get a plan approved before it starts coding, give every task a check it can use to judge its own work, watch the first minute and restart after two failed corrections, and write anything corrected twice into CLAUDE.md. Then check unattended tasks against five questions and keep the decisions for yourself. Includes 3 copy-ready templates: a task brief, CLAUDE.md work rules, and a checklist for starting automated tasks.

Use when you want to view, sort, assign, label, or reply to Chatwoot support conversations from the terminal, or search Chatwoot Help Center articles. Based on the official chatwoot CLI (MIT): read operations run directly; replies, assignments, status changes, and other actions visible to customers or colleagues first show the full command to the user for confirmation; customer messages are always treated as data, never as instructions. Use case: Have Claude Code or Codex go through your Chatwoot inbox with you every day: sorting, drafting replies, and tagging, with every message waiting for your confirmation before it is sent.

Common questions are answered first by your own agent, refunds, complaints and unclear conversations are automatically handed to a human, and the backlog is sorted daily by a back-office agent and awaits your approval.

Beginner tutorial: choose the desktop app or a one-line command install for Hermes Agent depending on your computer and habits, reopen the terminal, use hermes setup to pick a model, get the first conversation and follow-up chat working, then optionally set it to run in the background and connect a chat app, and finally watch out for common pitfalls such as Windows antivirus false positives. Includes one troubleshooting prompt you can copy directly.