365 skills · sorted by relevance
Use when adding or updating Spark AI provider models or their compact and preflight metrics, especially baidu-oneapi, Grok, Claude, GPT, DeepSeek, OneAPI, context windows, output budgets, prices, thinking maps, or transports.
The English summary is being prepared. Showing the original description.
Google SRE (Site Reliability Engineering) practices distilled from the SRE book series and real Google Brain/Meta/ByteDance production experience. Covers SLI/SLO/Error Budget design, incident response, capacity planning, toil automation, monitoring golden signals, and chaos engineering principles. USE WHEN: designing reliability targets, setting up monitoring/alerting, planning capacity, reducing operational load, building incident response runbooks, implementing chaos engineering, defining error budgets, or establishing reliability culture that balances velocity with stability.
The English summary is being prepared. Showing the original description.
Blockchain USDC payments via APay — pay services, manage budgets, open streaming channels, and handle x402 protocol.
The English summary is being prepared. Showing the original description.
Build and harden high-performance APIs with strong security controls, endpoint budgets, rate limiting, and resilience patterns. Use when tasks involve API latency/throughput tuning, abuse resistance, authz hardening, or API release gates.
The English summary is being prepared. Showing the original description.
Use when adding or updating Spark AI provider models or their compact and preflight metrics, especially baidu-oneapi, Grok, Claude, GPT, DeepSeek, OneAPI, context windows, output budgets, prices, thinking maps, or transports.
The English summary is being prepared. Showing the original description.