Guides
Practical write-ups on building with Claude Code and AI agents: vertical video, agent skills and multi-agent systems.
- Workflow · 9 min read · 2 November 2026
How to make AI horror Shorts with Claude Code: a step-by-step workflow
From a one-line idea to a checked 1080x1920 episode, with Claude Code doing the typing and you directing the story.
- Agent skills · 8 min read · 2 November 2026
Claude Code skills for video: how they work and how to write one for vertical reels
A skill turns a workflow you explain every time into one Claude Code follows on its own. Here is how, with a video example.
- Remotion · 10 min read · 2 November 2026
Remotion + Claude Code: render 1080x1920 reels and Shorts from a spec
Video as code: a spec file in, a checked vertical mp4 out, with Claude Code writing the React.
- AI agents · 11 min read · 2 November 2026
How to build a multi-agent research system in Python: planner, researchers, source checker
The design behind an agent team that writes sourced reports: what to split, how agents pass work along, and how every sentence gets checked.
- Channel workflow · 8 min read · 2 November 2026
Faceless YouTube Shorts with AI: run an animated story channel with Claude Code
A faceless channel lives or dies on a repeatable episode loop. Here is how to set one up with Claude Code, from the series bible to the pre-post checks.
- Agent skills · 7 min read · 2 November 2026
How to write a SKILL.md for Claude Code: structure, frontmatter and common mistakes
The difference between a skill Claude uses well and one it ignores is mostly in how SKILL.md is written. Here is a structure that works.
- AI agents · 8 min read · 2 November 2026
How to test an LLM agent: traces, budgets and an eval gate in CI (Python)
An agent you cannot measure is an agent you cannot change safely. Three pieces make it measurable: traces, budgets and an eval gate.
- Claude Code · 9 min read · 2 November 2026
Claude Code subagents: how to create and use them (with examples)
A Claude Code subagent is a second Claude with its own context, tools and instructions. Used well, it keeps your main session clean and gives you a reviewer that did not write the work.
- Short-form video · 8 min read · 2 November 2026
YouTube Shorts hooks: 5 patterns for the first 3 seconds
In the Shorts feed nobody chooses your video: it simply starts. The first frame, the first caption line and the first second of motion decide whether anyone stays.
- AI agents · 10 min read · 2 November 2026
Retry OpenAI and Claude API calls in Python: 429s, 529s, backoff, jitter
Agents make many model calls, and some of them will fail. The difference between a flaky agent and a dependable one is mostly in how those failures are handled.
- AI agents · 9 min read · 2 November 2026
How to stop an AI agent infinite loop in Python (step caps, repeat checks)
An agent stuck in an infinite loop, calling the same tool again and again, is a common way agent runs fail. A few small guards turn it into a clean stop with a reason.
- Claude Code · 10 min read · 3 November 2026
Claude Code hooks: PreToolUse, PostToolUse and Stop examples
CLAUDE.md asks; a hook makes sure. How hooks work, the JSON they read and return, and five examples to adapt today.
- Claude Code · 8 min read · 3 November 2026
CLAUDE.md best practices: what to include and skip, with a template
CLAUDE.md is the note Claude Code loads into every session. Short, concrete and current, it saves you repeating yourself; long and vague, it costs context every session and is followed less reliably.
- Claude Code · 8 min read · 3 November 2026
Claude Code custom slash commands: how to create them (with examples)
Custom slash commands in Claude Code turn a prompt you type every day into a one-word command, with arguments and live project context filled in before Claude reads it.
- AI agents · 11 min read · 3 November 2026
AI agent memory in Python: short-term, long-term, shared, with code
A model remembers nothing between calls. Agent memory is the code around it that decides what goes back into the prompt, and what never should.
- Short-form video · 7 min read · 3 November 2026
YouTube Shorts safe zone: 1080x1920 pixel guide for captions
On YouTube Shorts, Reels and TikTok the app’s buttons and description sit on top of your video. Keep captions and faces inside x 65 to 950, y 288 to 1248 of a 1080x1920 frame, and check a frame of each caption before you post.
- Story · 8 min read · 3 November 2026
60-second horror script for YouTube Shorts: template and example
A 60-second horror script for Shorts has no time for a slow build: the fear has to start on the first frame and tighten with every shot until the last.
- AI agents · 9 min read · 3 November 2026
Tool calling in Python for Claude and OpenAI: the full agent loop
Tool calling is how a model asks your code to do something (OpenAI calls it function calling; Anthropic calls it tool use). The model only proposes; your code checks the request, runs it and reports back.