scaleScale systems, software architecture, and companies with bottleneck mapping, staged leverage plans, and risk-aware execution loops.
Install via ClawdBot CLI:
clawdbot install ivangdavila/scaleGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://clawic.com/skills/scaleAudited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
An online retailer experiencing slow checkout times during peak holiday traffic needs to scale their payment processing system. The skill helps identify database connection pooling as the bottleneck, recommends implementing connection pooling with load balancing as the smallest high-leverage change, and establishes guardrails for transaction success rates alongside throughput increases.
A B2B SaaS company with 50 employees needs to scale engineering output to support rapid customer acquisition. The skill guides bottleneck analysis to reveal unclear ownership of microservices as the constraint, suggests formalizing API contracts and service boundaries before hiring, and pairs deployment velocity with change failure rate guardrails.
A financial technology company must scale transaction processing capacity to handle 10x growth while maintaining strict compliance requirements. The skill helps map bottlenecks to legacy batch processing systems, recommends incremental migration to event-driven architecture with rollback criteria, and ensures throughput scaling is paired with latency and error rate guardrails.
A telehealth platform needs to scale system reliability to meet increasing patient demand while maintaining HIPAA compliance. The skill identifies authentication service rate limiting as the bottleneck, suggests implementing horizontal scaling with health checks as the smallest effective change, and establishes uptime SLOs paired with security audit trail completeness as guardrails.
Monthly recurring revenue model where scaling focuses on maintaining service reliability and performance as customer count grows. The skill helps balance feature deployment velocity with system stability, ensuring customer retention metrics guard against technical debt accumulation during rapid expansion.
Revenue generated per transaction processed, requiring scaling of throughput capacity while maintaining low error rates. The skill assists in identifying processing bottlenecks, implementing staged capacity increases, and pairing transaction volume growth with quality and latency guardrails.
Custom solutions and consulting services where scaling involves team capacity and delivery processes. The skill helps map coordination bottlenecks across teams, recommends standardizing repeatable work before expanding headcount, and pairs project delivery speed with quality and margin guardrails.
💬 Integration Tip
Start by creating the ~/scale/ directory structure and running the scale-diagnostic.md template to systematically identify your current bottleneck before planning any scaling interventions.
Scored Apr 19, 2026
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce AI costs.
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Reduce OpenClaw AI costs by 97%. Haiku model routing, free Ollama heartbeats, prompt caching, and budget controls. Go from $1,500/month to $50/month in 5 min...
Generate and edit images with Gemini API using pure Python stdlib. Zero dependencies - works on locked-down environments where pip/uv aren't available.
Manage and use local Ollama models. Use for model management (list/pull/remove), chat/completions, embeddings, and tool-use with local LLMs. Covers OpenClaw sub-agent integration and model selection guidance.
Auto-route tasks to the cheapest Claude model that works correctly. Three-tier progression: Haiku → Sonnet → Opus. Classify before responding. HAIKU (default): factual Q&A, greetings, reminders, status checks, lookups, simple file ops, heartbeats, casual chat, 1-2 sentence tasks. ESCALATE TO SONNET: code >10 lines, analysis, comparisons, planning, reports, multi-step reasoning, tables, long writing >3 paragraphs, summarization, research synthesis, most user conversations. ESCALATE TO OPUS: architecture decisions, complex debugging, multi-file refactoring, strategic planning, nuanced judgment, deep research, critical production decisions. Rule: If a human needs >30 seconds of focused thinking, escalate. If Sonnet struggles with complexity, go to Opus. Save 50-90% on API costs by starting cheap and escalating only when needed.