Performance
Performance profiling and optimization
spice-ai
by spiceai
Add AI and LLM capabilities to Spice — chat completions, text-to-SQL (NSQL), tool use, memory, and model routing. Use when configuring language models, enabling tools (SQL, search, MCP, web search), setting up NSQL, adding conversational memory, configuring model fallback or load balancing, or using the OpenAI-compatible API.
spice-acceleration
by spiceai
Accelerate data locally for sub-second query performance. Use when enabling data acceleration, choosing an engine (Arrow, DuckDB, SQLite, Cayenne), configuring refresh modes, setting up retention policies, creating snapshots, adding indexes, or materializing datasets.
following-react-best-practices
by alunadev
React and Next.js performance optimization guidelines from Vercel Engineering. Use this skill when writing, reviewing, or refactoring React/Next.js code. Apply it proactively whenever working on React components, Next.js pages, API routes, data fetching (server or client), bundle size, rendering performance, re-renders, server actions, hydration, animations, or JavaScript optimizations. If the code involves React or Next.js, use this skill — even if performance isn't the stated goal, these patterns prevent issues before they arise.
skeptic-complexity
by data219
Use when evaluating proposals for overengineering, premature abstraction, build-vs-buy tradeoffs, or optimization without evidence, especially under deadline or authority pressure.
spice-models
by spiceai
Configure AI/LLM model providers in Spice (OpenAI, Anthropic, Azure, Google, xAI, Bedrock, Perplexity, Databricks, local models). Use when asked to "add a model", "configure LLM", "set up OpenAI", "add language model", "enable chat completions", "serve local model", "add AI gateway", or "configure system prompt".
suggest-performance-fix
by kjgarza
Identify performance issues and bottlenecks suggesting optimizations a senior developer would recommend. Use when user mentions performance/optimization/speed issues, asks "why is this slow?" or similar questions, code contains obvious performance anti-patterns (N+1 queries, unnecessary loops, etc.), user works on performance-critical code paths, performance profiling shows bottlenecks, or large data processing or database operations detected.
spice-accelerators
by spiceai
Configure data accelerators for local materialization and caching in Spice (Arrow, DuckDB, SQLite, Cayenne, PostgreSQL, Turso). Use when asked to "accelerate data", "enable caching", "materialize dataset", "configure refresh", "set up local storage", "improve query performance", "choose an accelerator", or "configure snapshots".
swiftui-development
by ProjAnvil
Specialized in building user interfaces using modern SwiftUI, covering NavigationStack, Observation framework, and SwiftData integration.
remember
by robabby
Store a memory in Obsidian for cross-session persistence
prioritization-frameworks
by alunadev
"Applies the right prioritization framework for the context — Opportunity Score, RICE, ICE, MoSCoW, or Kano — with formulas, scoring guidance, and when-to-use rationale. Use when ranking features or problems, comparing approaches, or preparing a prioritized backlog. Triggers on: prioritization, RICE, ICE, MoSCoW, Kano, backlog prioritization, feature ranking, opportunity score, prioritize features, what to build next."
performance-budget-setter
by patricio0312rev
Defines measurable performance budgets for bundle size, API latency, database queries, and render times. Provides enforcement strategies and monitoring plans. Use for "performance budgets", "performance monitoring", "web vitals", or "optimization targets".
cpp-benchmark-testing
by sentenz
Automates benchmark test creation for C++ projects using Google Benchmark with consistent software testing patterns. Use when creating performance benchmarks, profiling tests, or when the user mentions benchmarking, Google Benchmark, or performance testing.
dag-capability-ranker
by curiositech
Ranks skill matches by fit, performance history, and contextual relevance. Applies multi-factor scoring including success rate, resource usage, and task alignment. Activate on 'rank skills', 'best skill for', 'skill ranking', 'compare skills', 'optimal skill'. NOT for semantic matching (use dag-semantic-matcher) or skill catalog (use dag-skill-registry).
memory-vault
by yarlson
Maintain a project's persistent Memory Vault (.memory/) by initializing, reading, updating after code changes, reorganizing after large shifts, and compacting when it grows beyond limits.
strategic-compact
by peopleforrester
Context window optimization strategies for Claude Code. Covers token budgets, CLAUDE.md sizing, skill organization, tool selection, and techniques for maximizing productive output within context limits. Use when optimizing Claude Code configurations or managing large projects.
alphago-deep-rl
by curiositech
Apply AlphaGo-style patterns: learned priors plus search, mixed evaluators, self-play, and asynchronous fast/slow loops. Use for intractable search and compute allocation. NOT for basic supervised learning, tractable optimization, or domains without search bottlenecks.
swiftui-development
by ProjAnvil
专注于使用 modern SwiftUI 构建用户界面，涵盖 NavigationStack, Observation 框架和 SwiftData 集成。
notebook-debugger
by dangeles
Use when encountering Jupyter notebook errors including kernel crashes, environment conflicts, import errors, memory issues, or data pipeline failures in notebooks
essay-pipeline
by dangeles
Use when collaboratively writing a science blog essay through interactive thesis development, essay structuring, argument development, and paragraph writing with tiered fact-checking and voice matching.
systems-architect
by dangeles
Use when designing software architecture for bioinformatics pipelines, defining data structures, planning scalability, or making technical design decisions for complex systems.
essay-voice-matcher
by dangeles
Use when written text needs evaluation against a user's writing style profile and sample essays for voice consistency during essay pipeline execution.
mind-clone
by yzfly
Activate a Cognitive Digital Twin. Can simulate a custom subject (via core/ directory) OR load pre-installed celebrity/expert personas (from personas/ directory).
langchain-use
by NanmiCoder
LangChain 1.0 使用指南。提供 Agent、Tool、Memory、Middleware 等核心概念的快速参考。当用户需要创建 AI Agent、集成 LangChain、或解决 LangChain 相关问题时激活。
Reducing Complexity
by obra
Managing complexity is software's primary technical imperative - all other goals are secondary