性能
性能分析与优化
performance-profiling
timequity
Identify performance bottlenecks systematically. Measure before optimizing.
personal-assistant
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an intelligent database that automatically organizes and prioritizes information, keeping relevant data and discarding outdated context.
lead-research
Zuttam
Research LinkedIn prospects to find personalization opportunities and ice breakers. Use when user wants to research a lead, personalize outreach, find ice breakers, or understand a prospect better. Can be invoked with linkedin_url, lead_name, or campaign_id.
flutter-performance
spjoshis
Optimize Flutter app performance with widget rebuilds, memory management, rendering optimization, and profiling techniques. Achieve smooth 60fps rendering.
agile-metrics
spjoshis
Master agile metrics with velocity, burn-down charts, cycle time, and team health indicators for data-driven improvement.
team-coordination
spjoshis
Master team coordination with leadership, communication, conflict resolution, and collaboration techniques for high-performing teams.
performance-testing
spjoshis
Master performance testing with load testing, stress testing, JMeter, k6, and performance benchmarking.
Resources
torlando-tech
https://github.com/markqvist/Reticulum/docs/source/understanding.rst (resource overview)
flash-attention
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)."
Interfaces
torlando-tech
https://github.com/markqvist/Reticulum/docs/source/understanding.rst - Lines 677-694 (IFAC), 834-867 (announce propagation)
product-management
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.
context-engineering
vibery-studio
Master context engineering for AI agents - token optimization, degradation patterns, compression, memory systems, multi-agent coordination, evaluation. Use when designing agents, debugging context failures, or building LLM pipelines.
axolotl
tylertitsworth
"Axolotl — config-driven LLM fine-tuning framework. YAML-based SFT, instruction tuning, chat fine-tuning, DPO/IPO/KTO/ORPO preference optimization, GRPO reinforcement learning, reward modeling, LoRA/QLoRA, full fine-tuning with FSDP/DeepSpeed multi-GPU, N-D Parallelism (TP+CP+FSDP composition), multimodal VLM training, text diffusion training, QAT with NVFP4, sample packing, Flash Attention, dataset preprocessing, and checkpoint management. Use when fine-tuning or post-training LLMs with Axolotl."
memory
lidessen
Manages cross-session knowledge persistence. Triggers on "remember", "recall", "what did we", "save this decision", "todo", or session handoff.
swiftui-development
ProjAnvil
Specialized in building user interfaces using modern SwiftUI, covering NavigationStack, Observation framework, and SwiftData integration.
work-management
ajshedivy
"Query, monitor, and analyze jobs on IBM i using SQL table functions via ibmi-mcp-server. Use when user asks about: (1) finding jobs by status, user, subsystem, or type, (2) monitoring active job performance (CPU, I/O, memory), (3) detecting long-running SQL statements, (4) analyzing lock contention, (5) checking job queues, (6) replacing WRKACTJOB, WRKUSRJOB, WRKSBSJOB, WRKSBMJOB commands, or (7) any IBM i work management task."
database-indexing
1Mangesh1
Database indexing strategies and query optimization. Use when user asks to "optimize queries", "create indexes", "database performance", "query analysis", "explain plans", "index selection", "slow queries", "database tuning", "schema optimization", or mentions database performance and query optimization.
databases
vibery-studio
Work with MongoDB (document database, BSON documents, aggregation pipelines, Atlas cloud) and PostgreSQL (relational database, SQL queries, psql CLI, pgAdmin). Use when designing database schemas, writing queries and aggregations, optimizing indexes for performance, performing database migrations, configuring replication and sharding, implementing backup and restore strategies, managing database users and permissions, analyzing query performance, or administering production databases.
validation
lidessen
Unified validation orchestration for code quality, consistency, and project health. Auto-triggers on code changes, PR creation, or explicit validation requests. Coordinates refining, housekeeping, and custom validators into cohesive pipelines. Use for "validate", "check", "verify", "验证", "检查", or when quality assurance is needed.
web-performance
1Mangesh1
Web and frontend performance optimization. Use when user asks to "optimize performance", "improve loading time", "lazy loading", "code splitting", "bundle size", "Core Web Vitals", "image optimization", "CSS/JS minification", "caching strategies", "performance profiling", or mentions web performance and user experience metrics.
refinery
vxcozy
Convergence loop that iteratively improves work until quality thresholds are met. Scores, diagnoses specific weaknesses, rewrites, re-scores, and repeats until all dimensions reach 8/10 or diminishing returns are detected. Use when you want to refine or iterate on work, after the analyst gives a REVISE verdict, or when output quality is below your bar. Part of the architect-system loop. Outputs to system/refinery-log.md.
setup
lidessen
Bootstrap agent working system for a new project. Triggers on "setup agent system", "initialize claude", "bootstrap project".
orientation
lidessen
Orients agents in new projects by scanning entry documents and discovering capabilities. Use at session start, when entering unfamiliar territory, or when asking "what can you do" or "where do I start".
gpu-operator
tylertitsworth
"NVIDIA GPU Operator on Kubernetes — ClusterPolicy, DRA (Dynamic Resource Allocation), time-slicing, MIG, DCGM metrics, driver management, GPUDirect RDMA/GDS, CDI, and GPU scheduling. Use when installing, configuring, or troubleshooting GPU infrastructure on K8s."