Performance
Performance profiling and optimization
craft-coder-help
by timequity
Help and documentation for Craft-Coder plugin. Use when: user asks about available skills, commands, or how to use this plugin. Triggers: "help", "what can you do", "craft help", "как пользоваться".
evaluation
by Nymbo
Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.
cc_chrome_devtools_mcp_skill
by auldsyababua
Comprehensive Chrome DevTools automation for performance testing, Core Web Vitals measurement (INP, LCP, CLS), network monitoring, accessibility validation, responsive testing, and browser automation. Uses Chrome DevTools Protocol via MCP to provide professional-grade web application testing, debugging, and analysis capabilities including performance tracing, HAR export, device emulation, and multi-page workflows.
performance-profiling
by timequity
Identify performance bottlenecks systematically. Measure before optimizing.
llm-training
by eyadsibai
Use when "training LLM", "finetuning", "RLHF", "distributed training", "DeepSpeed", "Accelerate", "PyTorch Lightning", "Ray Train", "TRL", "Unsloth", "LoRA training", "flash attention", "gradient checkpointing"
dask
by eyadsibai
Use when "Dask", "parallel computing", "distributed computing", "larger than memory", or asking about "parallel pandas", "parallel numpy", "out-of-core", "multi-file processing", "cluster computing", "lazy evaluation dataframe"
personal-assistant
by auldsyababua
This skill should be used whenever users request personal assistance tasks such as schedule management, task tracking, reminder setting, habit monitoring, productivity advice, time management, or any query requiring personalized responses based on user preferences and context. On first use, collects comprehensive user information including schedule, working habits, preferences, goals, and routines. Maintains an intelligent database that automatically organizes and prioritizes information, keeping relevant data and discarding outdated context.
context-degradation
by eyadsibai
Use when diagnosing agent failures, debugging lost-in-middle issues, understanding context poisoning, or asking about "context degradation", "lost in middle", "context poisoning", "attention patterns", "context clash", "agent performance drops"
Resources
by torlando-tech
https://github.com/markqvist/Reticulum/docs/source/understanding.rst (resource overview)
configure
by designnotdrum
"Configure pattern-radar sources, weights, and domains."
flash-attention
by tylertitsworth
"Flash Attention, FlashInfer, SDPA backends, PagedAttention, and attention kernel selection/configuration. Use when choosing or configuring attention backends for training or inference (FlashAttention-2/3, FlashInfer, SDPA, xFormers, PagedAttention, Ring Attention, FlexAttention/FlexDecoding, varlen_attn)."
managing-memory
by designnotdrum
"Guide for storing enriched memories that capture decisions, preferences, and context. Use when making significant decisions or learning user preferences."
rem-sleep
by stewnight
Memory consolidation and defragmentation for long-term memory maintenance. Use when asked to consolidate memories, defrag memory, run REM sleep, clean up memory files, or process session logs into durable memory. Also use periodically during heartbeats for memory maintenance.
Interfaces
by torlando-tech
https://github.com/markqvist/Reticulum/docs/source/understanding.rst - Lines 677-694 (IFAC), 834-867 (announce propagation)
onboardjs-react
by OnboardJS
Integrate OnboardJS into React projects for building user onboarding flows. Use when: (1) Setting up OnboardJS in a React/Next.js project (2) Creating multi-step onboarding, wizards, or guided flows (3) Implementing conditional navigation, data persistence, or step validation (4) Working with OnboardingProvider, useOnboarding hook, or step components Triggers: "onboarding", "onboardjs", "wizard flow", "user onboarding", "guided tour", "multi-step form"
analyst
by vxcozy
Senior engineering analyst for code review, plan review, and automation review. Four-lens review covering architecture, code quality, reliability, and performance, each scored 1-10. Delivers APPROVE, REVISE, or REJECT verdicts. Use when you need a code review, plan review, quality check, or want to verify work before shipping. Part of the architect-system loop. Reads from system/blueprints/ and source code. Outputs to system/reviews/.
product-management
by ProjAnvil
Expertise in product management lifecycle, from ideation to launch. Covers requirements gathering, user story creation, prioritization, and product strategy. Use this skill for product planning, writing PRDs, defining MVPs, or competitive analysis.
web-quality-audit
by thoreinstein
Comprehensive web quality audit covering performance, accessibility, SEO, and best practices. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website".
compiler-performance
by marius-townhouse
Use when build times are slow. Use when optimizing TypeScript projects. Use when configuring project references. Use when dealing with large codebases. Use when improving IDE responsiveness.
deepagents-skills
by christian-bromann
Creating and using custom skills with progressive disclosure, SKILL.md format, and the Agent Skills protocol in Deep Agents.
flutter-best-practices
by Mauriciog87
Comprehensive Flutter development guidelines covering architecture, state management, performance optimization, testing, and cross-platform best practices. Use when building, refactoring, or reviewing Flutter applications for mobile, web, and desktop platforms. Covers widget patterns, Riverpod/BLoC state management, navigation with go_router, Firebase integration, platform channels, custom painting, animations, CI/CD, and production deployment.
php-performance
by peixotorms
Use when optimizing PHP performance, configuring OPcache or JIT, setting up caching (Redis, Memcached), tuning database queries (PDO), choosing faster function alternatives, managing memory, or profiling. Covers OPcache configuration, opcache.validate_timestamps, preload, preloading, php.ini tuning, memory_limit, realpath_cache, JIT tracing, micro-optimizations, function choices, loops, casting, memory management, connection pooling, lazy loading, N+1 query problem, SPL data structures, SplFixedArray, PDO best practices, caching patterns, Xdebug profiler, and Blackfire production profiling.
standards-init
by weegigs
Initialize project standards baseline from a profile. Use when setting up a new project with predefined coding standards and conventions.
track-equity-cumulative-return
by fatfingererr
Track cumulative return of stocks/indices with multi-ticker comparison, index Top N ranking, and visualization. All comparisons use S&P 500 as the fixed benchmark.