From ai-telemetry
Create an AI operations readout from logs, OpenTelemetry traces, Honeycomb queries, Claude analytics, ChatGPT/Codex telemetry, screenshots, CSV exports, or narrative observations. Use when the user wants a daily or weekly summary of AI adoption, cost, depth of use, quality, risk, prompt patterns, team usage, productive token spend, or what leaders should do next.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-telemetry:ai-ops-readoutThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Turn AI telemetry into a short management readout that helps the organization learn.
Turn AI telemetry into a short management readout that helps the organization learn.
Use whatever the user provides:
If data is missing, say what is missing and produce a readout scaffold with the best available evidence. Do not invent numbers.
Organize findings into five metric families:
Then translate telemetry into decisions:
Return a concise brief:
Write for managers and operators, not observability specialists. Be concrete. Avoid shame. The point is to improve the system, not rank people publicly.
Aggregate by team or workflow when possible. Include user-level detail only when the user has asked for individual coaching, investigation, or policy review and the data access model supports it.
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
npx claudepluginhub caravanai/caravan-tools --plugin ai-telemetry