diff --git a/presentation/2026-04-25-gdg-kolachi-cli-claude-code-gemini/index.html b/presentation/2026-04-25-gdg-kolachi-cli-claude-code-gemini/index.html index 9e96b22..d8de64d 100644 --- a/presentation/2026-04-25-gdg-kolachi-cli-claude-code-gemini/index.html +++ b/presentation/2026-04-25-gdg-kolachi-cli-claude-code-gemini/index.html @@ -1863,10 +1863,60 @@ todoapp/ - +
+ Most fields control how and when the skill loads — enforced by the harness. Only description lives in prompt-land.
The description field is the single prompt-land field — it’s what makes Claude decide when to invoke your skill. Write it well.
Small description, full body loaded on demand — this is progressive disclosure. Claude’s main context stays lean until the skill is actually needed.
Skills are the specific things the reporter has been trained to do. Our reporter has two: fetch the data, and render it as a card.
Skills are plain markdown files. If you can write a recipe, you can write a skill.
The small config block at the top of a SKILL.md (the "frontmatter") controls how the skill behaves:
Now that you've met the reporter and know their skills, let's understand what they can actually hold in mind at once. Every agent — including the weather reporter — gets its own fresh brain.
The moment you open Claude Code, certain things land in Claude's brain before you've typed a word. The rest waits in the wings — only loaded when you actually need it. This is called progressive disclosure.
@@ -2287,7 +2338,7 @@ Fetch the current temperature for Dubai, UAE.
The more stuff crammed into Claude's brain, the harder it is to focus on what matters. This is called context rot — performance drops as the brain gets crowded.
You can't create the context — it's just there, the moment you open a chat. But you can see how full it is, trim it down, or wipe it clean. Three commands give you full control.
The weather reporter consults this at the start of every shift — even though their brain resets overnight. It's the standing instructions pinned in that brain before you've said a word.
You don't need to write CLAUDE.md by hand. Claude can look at your project and draft one for you.
Claude Code uses two mechanisms to find CLAUDE.md files:
One word kicks off the whole chain. /weather-orchestrator → agent → skill → SVG card. Commands are the entry point into any workflow.
Commands are markdown files too. If you can write a recipe, you can write a command.
Watch the weather reporter example run from one keystroke to SVG card output. Five concepts, one orchestrated flow.
This is the core architecture pattern of Claude Code workflows — demonstrated in this very repo by the weather example:
The weather workflow demonstrates both skill patterns in a single flow:
A workflow isn't a separate file type. It emerges when one command calls agents and skills in sequence.
Five concepts, one running example
From meeting the weather reporter to wiring the full Command → Agent → Skill chain. The same five pieces compose every workflow you'll ever build.