Topic
Claude Code feature that packages reusable instructions as SKILL.md files, which the model can load on demand based on short descriptions kept in context.
A DEV Community post says Claude Code 2.1.296's skill listing budget is 30,000 characters, three times the 10,000 one team's commit test enforced. Japanese characters count double there, and the listing already stood near 28,100.
Reality
A skill installs with one command and runs with your own privileges, and while it is installed its description sits in every session's context so the model can decide to pick it up unasked. The opt-out is one line nobody set.
Reality
One developer found roughly 70 of his 112 installed skills reduced to bare names in the system prompt, and nothing in the tool had flagged it, because the listing budget drops descriptions without erroring.
Reality
A Claude Code skill that Anthropic staff reportedly use internally emits a single standalone HTML explainer built from big pictures and few words. The constraint is the product, and also the ceiling.
Reality
Every auto-generated Claude Code skill is injected into context on every conversation. One developer's weekly curator treats that like log rotation: stale at 30 days, archived at 90, nothing deleted.
Reality