Loading...
Loading...
Found 173 Skills
Guides AI ops leadership—LLM SRE, model/prompt releases, eval/incidents, cost/capacity, vendors, and cross-functional cadence. Use for AI platform ops, LLM SLAs, incidents, rollout governance, unit economics, red-team/eval gates, and team rituals—not memory (ai-memory-developer), context code (ai-context-engineer), security programs (cybersecurity), token roadmaps (ai-token-improvement-plan-engineer), solution architecture (applied-ai-architect-commercial-enterprise), skills portfolio (ai-skill-manager), or vertical AI product eng management (engineering-manager-vertical-ai-products). Prompt/eval team management and golden-set release policy: engineering-manager-agent-prompts-evals. Safeguard inference platform: ml-infrastructure-engineer-safeguards. Safeguard model research: ml-research-engineer-safeguards.
Builds AI-native products using OpenAI's development philosophy and modern AI UX patterns. Use when integrating AI features, designing for model improvements, implementing evals as product specs, or creating AI-first experiences. Based on Kevin Weil (OpenAI CPO) on building for future models, hybrid approaches, and cost optimization.
Optimize Groq costs through tier selection, sampling, and usage monitoring. Use when analyzing Groq billing, reducing API costs, or implementing usage monitoring and budget alerts. Trigger with phrases like "groq cost", "groq billing", "reduce groq costs", "groq pricing", "groq expensive", "groq budget".
Create and orchestrate multi-agent clusters to complete complex tasks. Use this skill when users need to break down complex tasks into multiple specialized agents for parallel or serial execution. Applicable scenarios: (1) Complex projects requiring multi-role collaboration (planning, research, coding, writing, design, analysis, review) (2) Need to execute multiple independent sub-tasks in parallel to improve efficiency (3) Need professional division of labor to optimize cost and quality. Keywords: multi-agent, agent cluster, task orchestration, parallel execution, agent team.
AWS/GCP cloud infrastructure: Well-Architected, security, cost, observability. Use when working with Terraform outputs, IAM policies, VPC design, load balancers, or cloud architecture decisions.
Playbook for selecting Solana RPC providers and building resilient client access (fallbacks, timeouts, rate limits, caching, cost control). Use when designing infra or debugging RPC issues.
Expert guidance for designing, assessing, and optimizing Azure workloads using Azure Well Architected. Covers design review checklists, recommendations, design principles, tradeoffs, service guides, workload patterns, and assessment questions. Use when designing AI, SAP, Oracle, SaaS, HPC, or mission‑critical workloads on Azure, and other Azure Well Architected related development tasks.
Design GCP architectures for startups and enterprises. Use when asked to design Google Cloud infrastructure, deploy to GKE or Cloud Run, configure BigQuery pipelines, optimize GCP costs, or migrate to GCP. Covers Cloud Run, GKE, Cloud Functions, Cloud SQL, BigQuery, and cost optimization.
Reviews Forge apps for security vulnerabilities, architecture issues, cost inefficiencies, performance problems, and trigger/scheduling waste before deployment. Use when the user says "review my Forge app", "check my app", "pre-deploy check", "is my app ready to deploy", "audit my Forge app", "check for security issues", "check performance", "review manifest", "check my Forge app for problems", "app review", "optimize my Forge app costs", "reduce invocations", "why is my app expensive", "check my triggers", or any request to evaluate a Forge app's quality, safety, cost efficiency, or readiness. Also triggers when users ask about Forge best practices, permission scopes, resolver optimization, storage efficiency, cold start reduction, frontend offloading, trigger filtering, scheduled trigger frequency, N+1 API calls, bulk API usage, verbose logging, or Forge platform pricing.
Every Render endpoint, plus diff, drift, cost, audit, and orphan analytics no other Render tool ships. Trigger phrases: `diff render env vars`, `promote env vars between render services`, `check render blueprint drift`, `render monthly cost`, `clean up stale render preview environments`, `where is this render env var used`, `render incident timeline`, `render audit log search`, `use render`, `run render-pp-cli`.
Route low-risk coding tasks to cheaper LLMs while keeping Codex for high-risk decisions, using MCP tools for cost-aware delegation
Create and manage Oodle metric drop rules — reduce ingestion cost by dropping or sampling high-volume, low-value metrics.