性能
性能分析与优化
vercel-react-best-practices
Jackiexiao
Vercel Engineering的React和Next.js性能优化指南。在编写、审阅或重构React/Next.js代码时应使用此技能，以确保最佳性能模式。触发涉及React组件、Next.js页面、数据获取、捆绑优化或性能改进的任务。
creating-skill
squirrel289
Evaluate a specific use case or skill idea against memory patterns and existing skills, then provide actionable recommendations for enhancing existing skills, creating new PAX skills, project-local skills, aspects, or AGENTS.md updates. Delegates actual skill creation to skill-creator.
interactive-task
AgustinAlbonico
Aclarar y ejecutar tareas de desarrollo no-bug (agregar, cambiar, refactorizar, configurar, optimizar) con preguntas adaptativas via question (opciones + respuesta libre). Usar cuando el pedido llega incompleto o ambiguo y se necesita definir alcance rapido.
omni-recall
ralph-wren
"Omni-Recall: Neural Knowledge & Long-Term Context Engine. Manages cross-session agent memory via Supabase (pgvector) and APIYI. Invoke to store/retrieve persistent context."
rust-binary-size
ccusage
Guides Rust binary size reduction for ccusage. Use when changing the rust/Cargo.toml release profile, dependency features, native packaging size, or investigating executable bloat with cargo bloat.
code-reviewer
karchtho
code review feedback quality analysis best practices consistency checking
video-avatars-and-virtual-backgrounds
tippyentertainment
Build and debug real-time video effects for conferencing and streaming: selfie segmentation virtual backgrounds, reverse segmentation, face mesh tracking, and avatar replacement using WebRTC, MediaPipe, and WebGL/WebGPU.
numpy-linalg
cuba6112
Linear algebra operations in NumPy, including matrix multiplication, SVD, system solving, and least squares fitting. Triggers: linalg, matrix multiplication, SVD, eigenvalues, matrix decomposition, lstsq, multi_dot.
Frontend Developer
anorbert-cmyk
World-class Frontend Engineer specializing in accessible, performant, secure-by-default React/Web applications.
masm-locals-over-globals
tomevault-io
Use when a MASM procedure needs temporary scratch storage — keep it in procedure-local memory so it cannot collide in a shared global region.
golang-master
Tomlord1122
Golang language expert specializing in concurrency, performance optimization, standard library, and testing. Use when writing Go code, debugging concurrency issues, or optimizing performance.
pipes-performance
subsquid-labs
Analyzes and optimizes blockchain indexer sync performance to reduce sync time while maintaining data completeness.
cleanup-context
kbrdn1
Optimize memory bank files by removing duplicates, consolidating content, and archiving obsolete documentation
database-schema-analysis
Olino3
Forge is a marketplace for a Claude Code Plugins
performance-review
Protagonistss
性能瓶颈定位、资源评估与优化建议能力。
Code Sculptor
smouj
Automated code refactoring and optimization engine for maintainability and performance
growth-hacker
YPYT1
Growth Hacker subagent
open-memory-local-manager
contextware
Advanced skill for managing memories in OpenMemory Local. Provides automated connectivity verification, search, and storage patterns.
langchain-agents
cuba6112
Building LLM agents with LangChain and LangGraph, covering tool-calling model initialization, state management, and observability with LangSmith. Triggers: langchain, langgraph, langsmith, agent-executor, chat-model-tools.
tidyfactor-next
TidyFactor
"TidyFactor Next.js track — production-grade multi-tenant SaaS on Next.js 16, React 19, TypeScript strict, and Supabase (Postgres, Auth, Storage, Edge Functions, Realtime). Locked tenant isolation (shared schema, tenant_id + Postgres RLS); pluggable query layer (Supabase JS / Drizzle / Prisma) chosen once per project. Covers architecture, tenant resolution/lifecycle, RLS authoring and leak diagnosis, auth/RBAC, schema/data management, storage security, API contracts, App Router/React 19 patterns, testing, observability, CI/CD, performance, incident recovery, maintenance. Trigger on commands 'init', 'tenant', 'rls', 'auth', 'data', 'storage', 'api', 'app', 'test', 'observe', 'deploy', 'perf', 'incident', 'audit', or requests like 'build a multi-tenant SaaS', 'add RLS to this table', 'why is one tenant seeing another tenant's data', 'set up tenant resolution', 'audit our tenant isolation'. Use for new projects and for hardening/auditing existing Next.js + Supabase SaaS codebases."
seithar-cogdef
ItsJamieHosie
Cognitive Defense Analyst. Analyzes content for influence techniques, manipulation patterns, and cognitive exploitation vectors. Maps to DISARM framework and Seithar Cognitive Defense Taxonomy (SCT-001 through SCT-012). Tells you when something is trying to reprogram you.
context-management
0xjohmsmith
"Programmatically measure and trim memory file sizes without LLM calls. Use for memory hygiene, context budget management, and enforcing token limits on memory/*.md files."
ad-launch-package
tonyflo79
Platform-compliant packaging and delivery preparation for ad campaign launch. Use after pre-launch scoring (A10) is complete and you need to package everything for the media buyer to go live. Launch-ready means COMPLETE — the media buyer can launch without asking a single question. Includes correct platform specs, file naming conventions, folder structure, campaign structure recommendations, and budget allocation suggestions. Trigger when users mention launch package, ad delivery, campaign packaging, preparing ads for launch, media buyer handoff, or getting ads ready to go live. Requires A10 scoring report and all upstream production assets.
gleam-performance-review
bromanko
This skill should be used when the user asks to "review performance", "optimize gleam", "BEAM performance", "performance audit", "find bottlenecks", "improve efficiency", or wants analysis of Gleam code performance focusing on BEAM runtime patterns, process architecture, and data structure choices.