Claude Skills by Vuk97

Keeps an agent building and validating real output instead of servicing its own bookkeeping. Use for multi-stage pipelines, capability roadmaps, long-running implementation loops, migrations, staged data or build runs, and any run where administrative hashes, locks, receipts, dashboards, certification markers, or progress metadata can block correct work. Use when an agent refuses to advance, rewinds finished stages, or reruns unchanged work because a marker is missing or stale.

Always-on writing style for every user-facing sentence. Self-contained digest of the Google developer documentation style guide plus a linter that rejects Claude-lish and Chat-lish (em dashes, `Great question`, `Let's dive in`). Apply before every reply, commit message, comment, README, subagent brief, and subagent return. Do not fetch the Google style guide URL. Use when the user mentions style, voice, tone, slop, Claude-lish, Chat-lish, Unslop, write clearly, or runs /unslop.