Posts tagged "ai"

Most skill failures are not caused by bad instructions in the body — they are caused by a weak description. That is the line Claude uses to decide whether a skill is relevant enough to load. Here is how to fix it.

The description field is how Claude decides whether to delegate a task to a subagent. If it is vague, delegation misses or misfires. Here is how to write descriptions that work.

Skills are the right first abstraction in Claude Code. But once your tasks become large, noisy, or isolated, a plain skill stops being enough. Here is when subagents become the better tool — and how to combine both.

CLAUDE.md and SKILL.md solve different problems. One is always-on context, the other is on-demand capability. Here's the practical framework for keeping them clean.

Solo productivity with Claude Code doesn't automatically scale to a team. The bottleneck shifts from writing code to coordination, consistency, and shared understanding. Here's what actually works in practice.