Performance

Performance Optimizer

by anorbert-cmyk

Web Performance Optimizer (frontend + backend aware) converting performance findings into code-level fixes.

cp-skills-kotlin

by area44

A structured competitive programming knowledge base focused on algorithmic thinking, data structures, and high-performance Kotlin implementations.

m10-performance

by lywa1998

"CRITICAL: Use for performance optimization. Triggers: performance, optimization, benchmark, profiling, flamegraph, criterion, slow, fast, allocation, cache, SIMD, make it faster, 性能优化, 基准测试"

Performance Benchmarker

by anorbert-cmyk

Performance Engineer focusing on real-user impact, Core Web Vitals, and backend latency benchmarks.

persona

by esmondo

progressive-disclosure

by NCMcClure

Design and maintain file-based progressive disclosure memory systems for Claude Code projects. Use when a project needs durable knowledge persistence across sessions — architecture decisions, technical learnings, domain expertise, or people context that outlasts any individual task. Triggers include requests for "project memory", "session persistence", "knowledge base", "memories directory", "progressive disclosure", "remember across sessions", or "capture learnings". Complements the autonomous-loop skill: loops handle intra-task state (progress.txt), memory systems handle institutional knowledge that accumulates over the lifetime of a project.

interview-designer

by mikonos

Analyze resumes and design interview strategies using evidence-based methodology. Transforms interview prep from "read resume → ask questions" into "define standard → forensic evidence → future simulation". Combines Geoff Smart's Topgrading, Lou Adler's performance-based hiring, and Daniel Kahneman's bias control. Use when preparing for interviews, creating structured interview guides, or designing questions to validate candidate competencies.

react-router-loader-performance

by adrianbrowning

React Router v7 loader performance optimization techniques. Use when optimizing TTFB, eliminating waterfalls, consolidating database queries, or streaming secondary data in loaders. Triggers on "slow loaders", "optimize TTFB", "speed up React Router", "loader performance", or when loaders exceed 500ms response time.

goldy

by SacredTexts

"Global planning/orchestration skill. Use for: (1) Gold Standard plan creation and phased execution, (2) stack-aware decisions across TanStack/React/Neon/Drizzle/WorkOS/Radix/shadcn and other stacks, (3) session memory and deterministic resume capsules, (4) long-running /goldy-loop phase automation with checkpoints and resume chaining, (5) UI/UX module reuse from ui-ux-pro-max when design output is needed, (6) browser-based bug investigation and smoke testing via auto-detected backend (Chrome Extension for Claude Code, Playwright for Codex). Trigger for planning, roadmap, phase, architecture, implementation sequencing, or when user asks for /goldy or /goldy-loop behavior. Also auto-invokes on any coding work that lacks a pre-existing plan: fix, bug, implement, build, add, create, refactor, migrate, update, upgrade, feature, endpoint, component, test, debug, deploy, optimize, integrate, change, modify, remove, delete."

distributor

by esmondo

supabase-postgres-best-practices

by pm-minji

Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.

Engram Conditional Memory (N-gram Hash Lookup + Offload/Prefetch)

by sovr610

This skill should be used when the user asks to "implement engram memory", "add N-gram hash lookup", "implement tokenizer compression", "add engram layer", "implement CPU offload embeddings", "add async prefetch", "implement multi-head hashing", "add context-aware gating", "implement depthwise causal conv", "add engram encoder", "implement hash embedding retrieval", "add collision mitigation", "implement offloadable embedding", "add prefetch scheduler", "implement engram augmented layer", "add residual fusion", "implement RMSNorm gating", "add engram telemetry", "implement streaming N-gram cache", "add prime-sized hash tables", "implement tokenizer equivalence merging", or mentions engram memory, N-gram hashing, deterministic addressing, CPU offload + prefetch, tokenizer compression, context-aware gating, depthwise causal convolution, hash embedding, encoder-competition mode, layer-augmentation mode, or DeepSeek-style conditional memory in the cognitive pipeline.

hiram-performance

by christopheraaronhogg

Provides expert performance analysis, bottleneck identification, and optimization assessment. Use this skill when the user needs performance audit, Core Web Vitals review, or scalability evaluation. Triggers include requests for performance review, load testing guidance, or when asked to identify bottlenecks. Produces detailed consultant-style reports with findings and prioritized recommendations — does NOT write implementation code.

waterware

by sri

Engineering guardrails for building this project with Go, TypeScript, and SQLite 3.

difficult-workplace-conversations

by VisualxIntelligence

Structured approach to workplace conflicts, performance discussions, and challenging feedback using preparation-delivery-followup framework. Use when preparing for tough conversations, addressing conflicts, giving critical feedback, or navigating sensitive workplace discussions.

chrOno somnia — OpenClaw Skill

by LittleJakub

${OPENCLAW_STATE_DIR:-$HOME/.openclaw}

Gradient Checkpointing (Activation Recomputation)

by sovr610

This skill should be used when the user asks to "enable gradient checkpointing", "reduce training memory", "activation checkpointing", "torch.utils.checkpoint", "memory-compute tradeoff", "checkpoint sequential layers", "selective checkpointing", "recomputation strategy", "activation memory profiling", "per-layer memory budget", "checkpoint_sequential", "checkpoint_wrapper", "SAC selective activation checkpointing", "SNN timestep checkpoint", "FSDP activation checkpointing", "checkpoint per timestep", "memory-efficient training", "recompute activations in backward", or needs guidance on trading compute for memory during training, per-layer memory profiling, selective recomputation strategies, or integration with distributed training wrappers.

concurrency-lock-vs-lockfree

by erikhuizinga

Language-agnostic guidance for lock-vs-lock-free (lockfree/lockless) concurrency decisions, atomic primitives, and memory-ordering risk evaluation. Use when tasks mention atomics, CAS/compare-and-swap, lock-free queues/stacks/pools, memory ordering or memory fences, ABA, weak-memory behavior, or replacing mutexes/locks for performance. Also use when designing custom synchronization primitives or debugging rare concurrency bugs caused by thread interleavings.

local-ppc-ads

by garrettjsmith

When the user wants to run geographically targeted Google Ads (PPC) campaigns for a local business. Also use when the user mentions "local PPC," "geotargeted ads," "radius targeting," "Google Ads for local business," "local search campaigns," "geographic PPC," or "Google Ads location targeting." For LSAs (pay-per-lead), see lsa-ads. For map pack ads specifically, see local-search-ads.

ask-questions-if-underspecified

by aiagentskills

Clarify requirements before implementing. Use when serious doubts araise.

Compute/Throughput Baseline & Regression Gate

by sovr610

This skill should be used when the user asks to "add performance benchmarks", "create a regression gate", "measure training throughput", "compute MFU", "benchmark step time", "profile training loop", "set up CI perf gate", "compare against baseline", "collect environment info", "machine profile", "tokens per second measurement", "CUDA sync timing", "PyTorch profiler traces", "TensorBoard trace handler", "eval harness", "perplexity gate", "update performance baseline", "scaling efficiency test", or needs guidance on repeatable performance measurement, baseline storage, regression detection, profiling integration, or CI-gated throughput checks.

local-memory-search

by blackbasilisk

Local, offline semantic search over OpenClaw memory files (MEMORY.md and memory/*.md) using Python embeddings + FAISS (no online LLM/API). Use when Dave asks for "memory search" without cloud billing, wants semantic recall across notes, or wants to share a reusable local-memory semantic search skill.

memory-consolidation

by kimasplund

Periodic "sleep-like" memory optimization. Detects patterns, resolves conflicts, applies decay, and transfers knowledge across contexts.

presentation-planner

by tomwangowa

Use before creating presentations — transforms a topic or rough outline into a complete Slide Plan with narrative strategy, audience analysis, and per-slide detail. Auto-chains to interactive-presentation-generator for production.