252 件 ・ 関連度順
概要と使いどころ
Text-prompted image zone detection using TIPSv2 B/14 on CPU. Produces `focus_targets` / `focus_edges` bbox lists from natural-language labels, ready to feed into `svg-portrait-mode`. Use when you want automatic foreground/background separation from prompts like "dog face" + "wooden floor" instead of hand-annotating bboxes.
日本語の概要は準備中です。原文の説明を表示しています。
Performance profiling and optimization for web apps — Core Web Vitals (LCP, INP, CLS), Lighthouse audits, bundle analysis, backend profiling (CPU, memory, DB queries), N+1 detection, caching strategies (Redis, CDN, HTTP), and performance budgets. Use when user asks to improve performance, run Lighthouse audit, profile a Node.js app, optimize Core Web Vitals, reduce bundle size, or investigate slow response times. Do NOT use for database schema optimization (use db-sculptor), Docker image optimization (use docker), or CDN configuration.
日本語の概要は準備中です。原文の説明を表示しています。
Use when writing or changing PyTorch code — model, Dataset/DataLoader, training and evaluation loops, determinism, mixed precision, torch.compile, checkpoints with safetensors, Hugging Face models, ONNX export, and tests that run on CPU
日本語の概要は準備中です。原文の説明を表示しています。
Diagnoses and improves measured latency, throughput, memory, CPU, bundle, rendering, query, or resource performance by defining a target, profiling a representative workload, locating the bottleneck, making one change at a time, and comparing before/after evidence. Use for performance work or regressions. Not for guessing optimizations without a reproducible workload or for generic refactoring.
日本語の概要は準備中です。原文の説明を表示しています。
Foundations of digital signal processing — sampling, aliasing, the Nyquist criterion, quantization, convolution, the discrete Fourier transform, FFT, FIR and IIR filter design, windowing, spectral leakage, and practical issues in fixed-point versus floating-point implementation. Use when designing filters, analyzing spectra, choosing sample rates, reasoning about aliasing, or implementing DSP algorithms on a microcontroller, DSP chip, or host CPU.
日本語の概要は準備中です。原文の説明を表示しています。
Understanding how digital systems actually work -- hardware, operating systems, networks, and information representation -- at a depth sufficient to reason about them rather than just use them. Covers CPU/RAM/storage/GPU roles, what an OS does, how packets travel the internet, and how computers represent numbers, text, images, and sound as binary. Use when a learner needs to build a mental model of computing rather than memorize menu paths.
日本語の概要は準備中です。原文の説明を表示しています。
OpenStack capacity planning operations skill for resource planning, quota management, and scaling decisions. Covers compute capacity (allocation ratios, vCPU/RAM utilization, host aggregates, availability zones), storage capacity (Cinder pool sizing, thin provisioning, Glance storage, Swift rings), network capacity (floating IP pools, port quotas, subnet sizing), project quota management (templates for small/medium/large profiles), flavor sizing strategy, utilization analysis with placement service, growth forecasting from historical metrics, and right-sizing recommendations for underutilized resources.
日本語の概要は準備中です。原文の説明を表示しています。
OpenStack Nova compute service skill for deploying, configuring, operating, and troubleshooting cloud compute infrastructure. Covers instance lifecycle management (create/stop/start/reboot/resize/migrate/evacuate), compute scheduling with filters and weights, flavor management, live migration procedures, hypervisor management (KVM/QEMU via libvirt), placement service for resource tracking, CPU pinning, NUMA topology, huge pages, cell mapping, VNC/SPICE console access, and capacity planning. Use when deploying compute via Kolla-Ansible, managing instances, debugging scheduler failures, or planning compute capacity.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill when controlling the AltirraSDL Atari emulator programmatically — driving the simulator from a script, capturing screenshots from a running Atari, injecting joystick/keyboard input, frame-stepping for deterministic testing, reading or writing CPU/memory/chip state, setting breakpoints or watchpoints, profiling 6502 code, loading symbols, or building automated tests against an Atari binary. Triggers on phrases like "AltirraBridge", "AltirraSDL --bridge", "AltirraBridgeServer", "Altirra Python SDK", "headless Atari emulator", "screenshot the Atari", "automate AltirraSDL", "drive the emulator from Python", "Atari debugger over a socket", "altirra_bridge package", as well as on tasks involving the bridge protocol, the Python `altirra_bridge` package, or the C `altirra_bridge.h` SDK.
日本語の概要は準備中です。原文の説明を表示しています。
将文案与用户自己的参考录音合成为配音、SRT 和可交接时间轴。默认使用 MiniMax 与用户自己的音色；可显式选择免费本地 Qwen3-TTS（Apple Silicon 用 MLX）或 Nano CPU。适用于口播配音、声音复刻，以及为网页视频演示准备最终音频和字幕。
日本語の概要は準備中です。原文の説明を表示しています。
调用 Yosys 0.35 对 RTL 进行逻辑综合并技术映射到 ASAP7 标准单元，产出门级网表 + QoR 报告。支持并行综合（基于空闲CPU数量）。Workflow: (1)生成综合脚本;(2)并行执行综合;(3)LLM检查结果并迭代优化。触发场景：(1) bba-guru-synthesis 已完成 SDC 与 CDC 检查、需要生成 netlist；(2) PD 反馈 area/path 超标需要重综合；(3) 显式 /bb-invoke-yosys。
日本語の概要は準備中です。原文の説明を表示しています。
Systems-level performance engineer: identifies hotspots, provides optimized code with resource justifications.
日本語の概要は準備中です。原文の説明を表示しています。
Forecast infrastructure and application metrics using Prophet or statsmodels for capacity planning, cost optimization, and proactive scaling. Visualize predictions in Grafana and set up alerts for projected resource exhaustion. Use when forecasting infrastructure capacity needs for CPU, memory, or disk, planning hardware procurement for next quarter, predicting cost trends to optimize cloud spending, or setting up proactive scaling policies based on predicted load.
日本語の概要は準備中です。原文の説明を表示しています。
Use when configuring DMA channels, circular buffer mode, double buffering, memory-to-peripheral transfers, or DMA IRQ completion on bare-metal MCUs. Not for cache theory: use cpu-cache-opt.
日本語の概要は準備中です。原文の説明を表示しています。
Use when explaining pipeline stages, data or control hazards, forwarding, stalls, or superscalar basics behind a counter reading. Not for mispredict cost: use branch-prediction-and-speculation.
日本語の概要は準備中です。原文の説明を表示しています。
Use when diagnosing cache misses with perf, fixing false sharing, choosing AoS or SoA layout, or adding software prefetch. Not for cache theory: use memory-hierarchy-and-caches.
日本語の概要は準備中です。原文の説明を表示しています。
Use when explaining branch predictors, mispredict penalties, speculative execution, Spectre or Meltdown mitigations, or branchless code. Not for pipeline stage theory: use cpu-pipelines-and-hazards.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a rendering path needs stable frame-time, CPU, GPU, and memory evidence against fixed targets. Not for one-shot profiling or visual quality review.
日本語の概要は準備中です。原文の説明を表示しています。
RFDB server becomes unresponsive (60s+ timeouts) during enricher addEdges write storms. Use when: (1) RFDB CPU spikes to 60-90% after addEdges calls; (2) subsequent reads time out at 60s; (3) server stays catatonic for 5-15 min after a write storm; (4) Tokio main thread parked (write-lock contention). Root cause: add_edges() calls maybe_auto_flush() which has a memory-pressure path that fires on NODE count — not edge count — and holds the exclusive write lock during disk I/O. Fix: separate maybe_auto_flush_edges() uses byte-limit only.
日本語の概要は準備中です。原文の説明を表示しています。
Diagnose React + Three.js (or any browser canvas) frame stutter by capturing a CDP CPU profile via Playwright instead of guessing from `[perf]` console logs. Use when: (1) frame time is bad but `[perf]` instrumentation doesn't pinpoint the offender, (2) you've spent more than ~30 minutes "fixing" suspects without measuring, (3) hot paths involve animation systems, allocation bursts, or invisible scene-graph traversal, (4) you need self-time per function with line numbers, not aggregate "render slow". The `console.warn` pattern is good for monitoring; CDP is needed for diagnosis. Covers script template, sourcemap setup so minified function names are decoded, and interactive variant where the user drives the interaction and signals stop via `touch /tmp/<flag>`.
日本語の概要は準備中です。原文の説明を表示しています。
为 msModelSlim 适配器实现逐层量化（按层加载/懒加载）能力。仅在用户明确要求逐层量化或基础适配因 CPU 内存不足无法全量加载权重时使用。该特性为高阶可选项，不是基础适配必需项。
日本語の概要は準備中です。原文の説明を表示しています。
Analyze Ascend NPU computation-side profiling data for single-card runs or a selected rank from multi-card runs. Use this skill when the user asks to diagnose computation bottlenecks, AI Core / AI Vector / AICPU hotspots, dynamic shape overhead, block dim issues, redundant TransData/Transpose/Cast, cross-stream waits, frequency/runtime-state issues, or fusion opportunities.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a PlayCanvas app has too many draw calls or is CPU-bound, before hand-merging meshes or writing custom renderers.
日本語の概要は準備中です。原文の説明を表示しています。
Emulates position-independent shellcode in a controlled CPU emulator (Unicorn) to trace executed instructions, memory writes, and decoded second stages without running it on a real host. Activates for requests to emulate shellcode, trace a decoder stub, or recover a stage unpacked at runtime by shellcode.
日本語の概要は準備中です。原文の説明を表示しています。