2,450 件 ・ 関連度順
概要と使いどころ
Graduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement. Use when the user runs /si:promote or asks to make a learned behavior permanent.
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。
Systematic performance profiling for Node.js, Python, and Go applications. Identifies CPU, memory, and I/O bottlenecks, generates flamegraphs, analyzes bundle sizes, optimizes database queries, runs load tests with k6 and Artillery. Always measures before and after. Use when investigating a slow endpoint, planning a performance budget, or hunting a memory leak in production.
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。
Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl), per-user profiles, and per-group fact memory (memory.md) across runs, with privacy guardrails baked in. Use when the user asks to "总结群聊", "群聊精华", "群聊摘要", "summarize group chat", "group chat digest", mentions a WeChat group name with a time range, says "帮我看看 XX 群最近聊了什么", "XX 群有什么值得看的", or asks to "回溯画像" / "初始化画像" / "backfill profiles". Adds the roast version when the user says "毒舌版", "roast 版", "再来个毒舌的", or similar.
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。
Query the user's local and synced-device data via the screenpipe REST API at localhost:3030 — recordings, audio, UI, meetings, connected services, and memory. Use for starred work, screen activity, other-device or cross-device history, productivity, media export, connections, durable memory, or discovering and automating saved workflows.
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 prevents vbar_control_agent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbar_control_agent crashes, memory cgroup OOMs in serial console logs, tpu-device-plugin metrics checksum corruption errors, or custom TPU metrics collection conflicts on GKE TPU v6e nodes. Don't use for general non-TPU container OOM troubleshooting or standard GKE node lifecycle operations.
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。
Legal document drafting -- contracts, memos, briefs, complaints, demand letters, opinions, discovery, settlements, ToS, privacy policies. Full pipeline: document structure, per-section writing, Bluebook citation, case law lookup (CourtListener API), regulation lookup (eCFR API), DOCX output, and TDD-style verification (defined terms, cross-references, placeholders, boilerplate, citation format). Triggers on: 'draft a contract', 'write a legal memo', 'create an NDA', 'write a brief', 'legal document about', 'draft a complaint', 'terms of service', 'privacy policy', 'demand letter', 'settlement agreement', 'legal opinion', 'discovery requests', any request to produce a legal or law-related document.
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。
Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training instabilities, NaN/Inf, and hardware/job failures; checkpointing and fault tolerance; inference performance and memory; debugging multi-node/ multi-GPU hangs; and writing/running tests. Use when the user is training or fine-tuning large models, hits low TFLOPS/MFU, OOM, slow dataloading, a loss spike/divergence, a NCCL/InfiniBand or multi-node hang, node/GPU failures, checkpoint or preemption problems, storage/network bottlenecks, or needs to pick GPUs/cloud/file-systems or size inference latency/throughput. Distilled from "Machine Learning Engineering", the latest version of which can be found at https://github.com/stas00/ml-engineering The latest SKILL.md version can be found at https://github.com/stas00/ml-engineering/blob/master/skills/ml-engineering/SKILL.md
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 the user wants Codex to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, wants Codex to review past sessions, learn preferences, consolidate memory/skills, run dry-run/run/adopt/status for SkillOpt-Sleep, or schedule background self-optimization. Drives the skillopt_sleep engine: harvest past sessions -> mine recurring tasks -> replay through a selected backend -> consolidate validated memory + skills behind a held-out gate.
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。
This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce worker tokens", "cross-agent memory without summarization", or discusses Attention Matching compaction, recursive language models with workers, or token explosion in hierarchical agents.
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。
This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent orchestration attacking a hard problem: pseudo-formal task briefs that define terms and an exact success predicate linguistically, enumerate non-counting outcomes, set persistence rules with explicit stop and return conditions and effort floors, manage a diverse portfolio of parallel approaches with an approach registry and blocked-route bookkeeping, and gate the return on adversarial audit. Route agent topology and coordination protocols to multi-agent-patterns, runtime control surfaces and loop governance to harness-engineering, evaluator and quality-gate construction to evaluation, judge design to advanced-evaluation, and compaction or memory mechanics to context-compression and memory-systems.
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。
Maintain the plugins bundled in this repository (htpasswd, local-storage, auth-memory, memory, audit, package-filter, ui-theme) and the plugin contracts in @verdaccio/core — fix a bundled plugin, change a pluginUtils interface safely, diagnose why a plugin does not load, or verify a plugin with @verdaccio/plugin-verifier. Use when a task touches packages/plugins, packages/loaders, pluginUtils, or a plugin loading problem. Requests to add a new bundled plugin are gated on an accepted discussion thread; this skill says how to handle them.
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。
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.
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。
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.
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。
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
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。
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
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。
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
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。
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
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。
Structural feedback on a legal writing draft (memo, brief, paper, exam essay) — organization, analysis depth, clarity, citation form. NEVER rewrites the draft. Use when the user says "feedback on my memo", "read my draft", or "critique my brief".
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。
Generate or drill flashcards for black-letter memorization — Leitner-style buckets, per-subject markdown storage, drill mode with self-assessment. Use when the user says "drill flashcards", "make flashcards from", "quiz me on cards", or wants to memorize rules.
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。
Draft an audience-specific summary from the privileged investigation memo — HR, leadership, or outside counsel versions. Use when an investigation memo needs to be communicated to an audience that should not see the full privileged work product.
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。
Decision needed + recommendation + evidence + tradeoffs, 把复杂材料压成可拍板的一页
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。
Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively suggest at the start of a new task if you haven't checked your hive inbox in this conversation. (munder-difflin)
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。
Review auto-memory entries and propose promotions to OPENSPACE.md, OPENSPACE.local.md, or retained auto-memory topics; detect duplicates, stale facts, conflicts, and ambiguous entries before making changes.
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。
Read how a game actually works so a mod can hook it. Decompile .NET/Mono (ILSpy), IL2CPP (Cpp2IL, Il2CppDumper), Java (Vineflower) and native code (Ghidra, IDA, via MCP servers); dump data and asset formats; reverse-engineer a binary file format and prove it with a round trip; read live memory (Cheat Engine, Frida, x64dbg); find render passes (RenderDoc). Use when a mod needs game internals, e.g. "how does the boss AI work", "find the damage function", "what format is this .sld/.pak/.dat", "where is the player position in memory".
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。