agentic working $ claude /ck:cook "inside claudekit" research plan implement testing...
/inside-claudekit

Claude Code,
but supercharged

Deep dives into ClaudeKit — the engineer kit that supercharges Claude Code.

Posts
No posts found.
Published
Working with Fable 5: Fix the map before entering the territory

Map vs Territory: the gap between prompt and codebase is your unknowns. A 6-stage pipeline, 3 fixed gates around ck:cook, 3 custom skills, and model cost tradeoffs.

Published
ClaudeKit's visualization toolkit

Orchestrate thinking or execute UI: pick the right skill among preview, frontend-design, stitch, tech-graph and show-off. With a real case study visualizing an entire plan file.

Published
Guard rails: the brake layer between model and action

When an agent can read files, run shells, edit code and ship PRs, one line in the prompt is not enough. A breakdown of the 4 guard layers, 7 guard-rail groups and 8 known gaps in CK.

Published
When to use /ck:plan --deep --tdd

--deep helps the plan see the full scope; --tdd adds a regression gate for refactors. This post sorts out when each option pays off, and when you can skip them.

Published
Getting Started with Claude Code & ClaudeKit

From AI assistant to development partner. Explains how Claude works and guides you through the Engineer Kit with real-world use cases and best/bad practices.