#workflow

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.

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.

Use when a user wants to turn a fact-checked explainer script into a faceless, journal-style knowledge video. Five checkpoints, each waiting for the user to confirm: voice and script, material list, storyboard, 3-second sample, full cut. Does not change the script, invent data, or publish. The bundled script renders only a minimal example; voice-over, screen recording, and complex editing must be prepared separately. Use case: Let an agent turn your explainer script into a faceless, journal-style knowledge video, with you confirming every step.

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.

Advanced tutorial: first decide whether you need a team at all, then build it following an SOP: the orchestrator splits up tasks, specialists each do one thing in parallel, and the reviewer only reads and never edits, acting as the gatekeeper. When dispatching work, spell out everything. Set tools and effort per role, and cap budget, depth, and time. Includes complete Python code and prompts to hand to an Agent for execution.

A set of specialized bots, each handling one area: automatically summarizing email, news, and traffic every day, watching competitor activity, drafting content before anything is published, and coordinated by a manager bot.

Advanced tutorial: Walk through four weeks with a sample Markdown-to-PDF site: in Week 1, screen for small, precise demand; in Week 2, check search results to decide page format; in Week 3, write a core page and supporting pages and link them to each other; from Week 4 on, read Search Console against a symptom lookup table. Includes two prompt templates and an experiment log template.

A beginner's guide: set a role and constraints first, describe the goal as the finished result, ask step by step, add a line against made-up facts, then have the AI score its own answer and revise it. All five rules come with copy-ready wording and one combined template.

Advanced developer tutorial: how to get an Agent to handle complex tasks: set the goal first, split it into subtasks, use structured output (JSON) so downstream steps can pick it up easily, then use event-driven handling for unexpected situations.

An advanced developer tutorial on when to use multiple agents, what they offer over a single agent, and communication and collaboration patterns (group chat, hand-off) and how to see what they are doing.

Advanced developer tutorial: what Microsoft's Agent Framework offers: five multi-agent orchestration patterns, observability, security, durability and human-in-the-loop approval, plus core concepts such as agents, tools and conversation threads.

Agents get less obedient the more you use them, usually because AGENTS.md has piled up too much. Write only what the agent can't see for itself and that really affects results, prune it regularly, and include a cleanup prompt.

A prompt I have refined over a long period on ChatGPT and Gemini. It makes the model give the answer first, attach conditions to its judgments, search first for time-sensitive information, and end with a next step. Includes a simplified full text and usage instructions.

Use when a user wants to study an existing product's features and flows and build their own version (architecture, build, testing, branding, launch). Based on the open-source replica-skill (MIT), a set of 11 Skills; only borrows features and flows, and does not copy the other party's code, logos, copy, or content. Analysis uses only public information and the user's own accounts. Use case: Have an agent analyze a product's features and flows, then build your own differentiated version step by step.

Want to recreate a video? First decide whether you want to learn how it was made or rebuild an editable copy of it. REA-Video is open source and free, breaking down each shot into visuals, subtitles, editing and sound. HyperFrames reverse-any-video is a Pro feature that rebuilds an editable project and compares it frame by frame with the original. Includes tool selection, hands-on steps and FAQ.

Turn a 5-second talking-head line into a halftone paper-collage assembly animation: design the visual metaphor first, and leave the paid video generation to the end behind three checkpoints. Includes prerequisites, step-by-step instructions and FAQ.

Props are generated with code in Blender, characters get meshes from a generator, then the Agent cleans them up, splits them into parts, rigs bones, sets weights, writes animations and exports to Unity or Roblox. Includes route choices, costs and a common troubleshooting table.

Put flat 2D characters into a lit 3D scene and tell a true story. A pipeline covering form breakdown, scriptwriting, storyboarding, building the scene in Blender, voiceover and captions, then review and iteration, with ready-to-adapt prompts and compliance reminders.

When the base-tier Claude quota runs out, it's usually because bulk output work was also handed to it. Keep judgment tasks for Claude, send bulk generation to Codex or a cheaper tool, and write the division of labor into CLAUDE.md.