124 boosters for "optimization" — open source, verified from GitHub, ready to install
A specialized agent for building and optimizing WeChat (WeCom) private domain ecosystems, helping enterprises manage customer relationships, community operations, and conversion funnels. Ideal for businesses leveraging WeChat as a primary sales and engagement channel.
A specialized agent that analyzes search query data to identify optimization opportunities, build negative keyword strategies, and align queries with user intent—enabling paid search managers to reduce wasted spend and capture high-intent traffic. Ideal for PPC professionals, marketing agencies, and e-commerce teams managing large-scale search campaigns.
Studio Operations is an AI agent that helps teams optimize day-to-day studio efficiency through process improvement, resource coordination, and productivity management. It benefits project managers, operations leads, and studio teams seeking to streamline workflows and maintain consistent standards.
A specialized marketing agent for Bilibili content creators seeking to optimize UP主 growth, master danmaku engagement, and build communities on China's leading video platform. Ideal for creators, brands, and marketing teams targeting Chinese Gen Z audiences.
A system prompt for Claude Code that enforces defensive security practices and provides CLI guidance, designed to help developers safely use Claude for software engineering tasks while preventing misuse.
1. Fetch homepage HTML (curl or WebFetch) 2. Detect business type (SaaS, Local, E-commerce, Publisher, Agency, Other) 3. Extract key pages from sitemap.xml or internal links (up to 50 pages)
"name": "claude-seo", "description": "Comprehensive SEO analysis skill for Claude Code. 20 core sub-skills covering technical SEO, content quality (E-E-A-T), schema markup, image optimization, sitemap architecture, AI search optimization (GEO), local SEO, maps intelligence, semantic topic clustering
"version": "0.25.5", "description": "The official Google Ads + Meta Ads + SEO + GEO plugin from NotFair. SEO analysis, Google Ads management, Meta (Facebook + Instagram) Ads management, keyword research, content optimization, schema markup tools, broken link checker, single-page deep audit, and Gene
"name": "prompt-improver", "description": "Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, bac
A hands-on course teaching developers how to build AI-powered agents using Foundry Local with modern SDK patterns, function calling, and hybrid cloud designs. Benefits beginners and intermediate developers wanting to prototype agentic applications quickly on edge devices.
LLM-first SEO analysis skill with 16 specialized sub-skills, 10 specialist agents, and 33 scripts for website, blog, and GitHub repository optimization. For prompt reliability in Codex/agent IDEs, map common user wording to a fixed workflow: When the user requests SEO analysis, follow this routing:
The Portfolio Optimization skill applies mathematical optimization techniques to project portfolio selection and balancing. It maximizes portfolio value while respecting budget, resource, and strategic constraints, enabling data-driven investment decisions. 1. Annual Planning: Optimize project selec
Comprehensive guide for Claude Code CLI tool, extensibility (agents/skills/output styles), and CLAUDE.md architecture. 1. Task verbs: create, build, debug, fix, deploy 2. Problem descriptions: slow, broken, failing
Heuristic scoring (no AI key configured).
Advanced Eloquent ORM patterns for performance and query reuse. Use when working with Eloquent relationships, scopes, or advanced query optimization in Laravel. (triggers: app/Models/**/*.php, scope, with, eager, chunk, model)
Drive a profile → modify → benchmark → log → commit loop on a GPU kernel until it runs faster than the reference. The user provides at minimum a kernel; everything else (reference, inputs, bench script, hints) is optional. Does NOT apply when: Before doing anything else, establish the workspace — th
Use this skill whenever the user wants to: This skill is organized to match the Rspack official documentation structure (https://rspack.rs/zh/guide/start/introduction, https://rspack.rs/zh/config/, https://rspack.rs/zh/plugins/, https://rspack.rs/zh/api/). When working with Rspack: 1. Identify the t
pycse is a Python library that assists with scientific computing tasks including nonlinear regression, uncertainty quantification, design of experiments, and neural network-based modeling. It's useful for researchers, engineers, and data scientists working on numerical optimization, experimental design, and uncertainty analysis.
"description": "Agent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage",
Opik MCP Server enables developers to integrate automated prompt optimization directly into Claude through the Model Context Protocol. It's valuable for teams building AI applications who want to systematically improve and test their prompts.
A comprehensive guide to Lit web components best practices covering component structure, rendering, styling, events, lifecycle, accessibility, and performance optimization. Ideal for developers building or reviewing Lit-based custom elements and web components.
"description": "Modern R development skills for Claude Code - tidyverse patterns, rlang metaprogramming, Bayesian inference, performance optimization, and more", "name": "Claude Code R Skills" "homepage": "https://github.com/ab604/claude-code-r-skills",
Build modern, on-brand marketing emails and send them via Resend. This skill encodes a complete pattern: asset hosting, reusable HTML components, GIF tooling, and the Resend send pipeline. Anything in is served at . Commit + push = instant CDN. No Cloudinary, no S3. Use this building-block inventor
A practical guide to Supervised Fine-Tuning using SFTTrainer and Unsloth optimizations, enabling developers to efficiently adapt pre-trained LLMs for instruction-following with 2x faster training. Ideal for ML engineers building custom instruction-tuned models and reasoning systems.
