Performance skills

This skill routes tasks to the cheapest capable model, reducing cost while preserving quality by selecting appropriate tiers and spawning sub-agents.

This skill benchmarks your agent memory retrieval using a peer-review-grade suite, collects anonymized statistics, and submits results to research aggregations.

This skill helps you resize, convert, and watermark images efficiently using libvips, reducing memory usage and speeding batch processing.

This skill helps automate ML competition evolution by learning from experiments and optimizing LB scores with memory-driven decisions.

This skill helps you build and modify Go web services with ngamux, enabling fast route creation, middleware, and flexible responses.

This skill provides persistent, semantic memory for AI agents by storing and recalling important context across sessions with fast, local processing.

This skill enables unified access to 343+ models for text, image, JSON, video and no-deploy workflows, maximizing token efficiency and speed.

This skill generates secure, parameterized SQL queries across multiple databases with validation, risk analysis, and audit-focused safeguards.

This skill enables fast local transcription using faster-whisper with GPU acceleration, providing word-level timestamps and flexible model options for accurate

This skill audits GitHub Actions runtimes against thresholds, identifying near-timeout and timed-out jobs to prevent CI failures.

This skill generates AI images using Google's Gemini 3.1 Flash via Evolink, enabling fast text-to-image and image editing with a single API key.

This skill helps you create video content with Remotion using React, enabling multi-format outputs, server-side rendering, and reusable component workflows.

This skill generates a single high-performance X tweet for builders, delivering sharp, postable output with strict formatting and creator mode.

This skill helps optimize media buying across platforms by assessing account health, bid efficiency, AB test design, and real-time anomaly monitoring.

This skill helps you design production-grade React apps with architecture, state management, performance, testing, and deployment strategies.

This skill analyzes OpenClaw token usage and cost, identifies high-cost scenarios, and provides concrete optimization guidance to reduce expenses.

This skill performs fast local speech-to-text transcription using Faster Whisper with NVIDIA GPU acceleration, delivering private, multi-language outputs.

This skill enforces mandatory pre-deployment quality assurance by validating builds, testing browsers, ensuring mobile responsiveness, and verifying links and

This skill routes each request to the cheapest capable model across 30+ providers to cut inference costs and speed.

This skill analyzes BigQuery usage and storage patterns to identify costly queries and optimize costs with actionable recommendations.

This skill enables OpenClaw to prioritize local Feishu document cache, reducing API calls and token costs while improving response speed.