性能
性能分析与优化
image-evaluation
ppdbxdawj
Provides reference for evaluating AI-generated images and text-to-image (T2I) models. Covers mainstream benchmarks (PartiPrompt, GenAI-Bench, VQAScore, ImageEval, DrawBench, T2I-CompBench++, HRSBench, RAHF, BodyMetric, Human Distortion, Reason-Edit, etc.), metrics (FID, CLIPScore, VQAScore, human alignment, realism), and dataset scales. Use when the user asks about AI image evaluation, T2I benchmarks, image quality metrics, 图像评估, 文生图评测, benchmark, VQAScore, FID, 图文对齐, or how to evaluate generated images.
mcp-memory-gateway
IgorGanapolsky
The Agentic Feedback Studio & Veto Layer. Persistent agent memory, high-density context packs, and Agentic Guardrails (V2V) for Claude Code, Codex, and Gemini.
Agent Memory
IgorGanapolsky
Give your agent persistent cross-session memory — recall what went wrong on similar tasks before starting, then capture whether the work succeeded or failed so repeated mistakes auto-promote into prevention rules. Runs locally via the ThumbGate MCP server (recall, capture_feedback, prevention_rules, feedback_stats) — no API key needed. Use when the user says "recall", "what went wrong last time", "remember this for next time", "capture feedback", "thumbs up/down on that", or at the start of a new task or session. Do NOT use when the user wants to force one specific mistake into an enforced block gate (use the thumbgate-guard skill), to list rules that already exist (thumbgate-rules), or to check ThumbGate wiring (thumbgate-doctor).
geo-strategy
yaojingang
Build an offline GEO optimization plan from explicit goals, diagnosis actions, approved evidence IDs, and a measured baseline. Use for GEO strategy, roadmap, experiment planning, intervention candidates, 策略, 路线图, and 优化实验. Exclude autonomous publication, fabricated outcome evidence, and memory promotion without positive external measurement.
memory/capture-discipline
frankxai
Use when designing daily capture, note-taking, or personal-knowledge operations — defines the discipline of when, what, and where to capture. Tool-agnostic; the practice survives tool changes. Default skill for Starlight Second Brain.
memory/memory-consolidation
frankxai
Use when optimizing vault storage, archiving stale data, or deduplicating entries — consolidates related entries and ensures memory remains high-quality and retrievable. Inspired by AI-Ops working/episodic/semantic/procedural patterns. Default skill for Starlight Prime.
memory/vault-management
frankxai
Use when storing, retrieving, or managing persistent memory across the Starlight Vaults — handles reading, writing, querying, and organizing entries across all vaults. Default skill for Starlight Prime and Starlight Sage.
golang-testing-strategies
bobmatnyc
"Comprehensive Go testing strategies including table-driven tests, testify assertions, gomock interface mocking, benchmark testing, and CI/CD integration"
react-flow
framara
"Expert guidance for React Flow (@xyflow/react): building interactive node-based graphs, custom nodes and edges, handles, state management, layouting, TypeScript patterns, performance optimization, and theming. Use when writing React Flow code, creating custom nodes or edges, debugging flow issues, optimizing graph performance, integrating with Zustand, or building canvas-based UIs with React Flow."
mpm-doctor
bobmatnyc
Run diagnostic checks on Claude MPM installation
mpm-status
bobmatnyc
Display Claude MPM system status
toolchains-golang-core
bobmatnyc
"Go 1.22+ core patterns for minimalism, efficiency, code reuse, and performance"
rust-desktop-applications
bobmatnyc
Build cross-platform desktop applications with Rust using Tauri framework and native GUI alternatives
memory/insight-distillation
frankxai
Use during periodic review sessions (weekly/monthly/quarterly) to turn raw captures into reusable frameworks — patterns captured ≥3 times become named, documented, ready-to-reuse frameworks. Default skill for Starlight Second Brain.
vm-create
RHEcosystemAppEng
Create new virtual machines in OpenShift Virtualization with automatic instance type resolution and OS selection. Use this skill when users request: - "Create a new VM" - "Deploy a virtual machine with [OS]" - "Set up a VM in namespace [name]" - "Provision a [size] VM" This skill handles VM creation with intelligent defaults for OpenShift Virtualization. NOT for managing existing VMs (use vm-lifecycle-manager or vm-delete instead).
vm-rebalance
RHEcosystemAppEng
Orchestrate VM migrations across cluster nodes for load balancing, maintenance, and resource optimization. Use when: - "Move VM database-01 to worker-03" - "Rebalance VMs to optimize CPU load" - "Drain worker-02 for maintenance" - "Automatically rebalance the cluster" Supports Manual (user-driven) and Automatic (AI-driven) modes. NOT for creating VMs (use vm-create) or lifecycle only (use vm-lifecycle-manager).
peft
wundercorp
Fine-tune large LLMs with LoRA on limited GPU memory.
serving-llms-vllm
wundercorp
"vLLM: high-throughput LLM serving, OpenAI API, quantization."
meeting-notes
CuriousLearner
Convert meeting discussions into clear, actionable notes with tasks, decisions, and follow-ups fo...
whoop
diegosouzapw
Fetch WHOOP health data including recovery scores, sleep metrics, workouts, cycles, and profile. Use when user asks about WHOOP data, recovery, HRV, sleep analysis, or fitness metrics.
accelint-ts-performance
gohypergiant
"Systematic JavaScript/TypeScript performance audit and optimization using V8 profiling and runtime patterns. Use when (1) Users say 'optimize performance', 'audit performance', 'this is slow', 'reduce allocations', 'improve speed', 'check performance', (2) Analyzing code for performance anti-patterns (O(n²) complexity, excessive allocations, I/O blocking, template literal waste), (3) Optimizing functions regardless of current usage context - utilities, formatters, parsers are often called in hot paths even when they appear simple, (4) Fixing V8 deoptimization (monomorphic/polymorphic issues, inline caching). Audits ALL code for anti-patterns and reports findings with expected gains. Covers loops, caching, batching, memory locality, algorithmic complexity fixes with ❌/✅ patterns."
godot-expert
nguyenthienthanh
"Godot game development expert. PROACTIVELY use when working with Godot, GDScript, game projects. Triggers: godot, gdscript, .gd, .tscn, game, scene, node"
performance-optimizer
nguyenthienthanh
"Identify and resolve performance bottlenecks through profiling, measurement, and targeted optimization."
accelint-persona-review
gohypergiant
Evaluate Figma designs from operator persona perspectives through design critique and user experience evaluation. Use when reviewing UX for specific user roles (e.g., air-surveillance-tech, weapons-director), conducting design reviews, or evaluating operator interfaces. Analyzes cognitive load, communication patterns, pain points, and system visibility. Works with Figma MCP (desktop/URL) and Outline docs.