1,111 件 ・ 関連度順
概要と使いどころ
Data ingestion patterns for loading data from cloud storage, APIs, files, and streaming sources into databases. Use when importing CSV/JSON/Parquet files, pulling from S3/GCS buckets, consuming API feeds, or building ETL pipelines.
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。
Optimize cloud infrastructure costs through FinOps practices, commitment discounts, right-sizing, and automated cost management. Use when reducing cloud spend, implementing budget controls, or establishing cost visibility across AWS, Azure, GCP, and Kubernetes environments.
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。
LLM and ML model deployment for inference. Use when serving models in production, building AI APIs, or optimizing inference. Covers vLLM (LLM serving), TensorRT-LLM (GPU optimization), Ollama (local), BentoML (ML deployment), Triton (multi-model), LangChain (orchestration), LlamaIndex (RAG), and streaming patterns.
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。
Transform a UI screenshot into a structured Cinema4D/Octane JSON render prompt for photorealistic 3D poster art. Use this skill whenever the user uploads a UI screenshot (app, website, tool, dashboard) and wants a Cinema4D render prompt, 3D poster, AIGC image prompt, or any photorealistic visualization of an interface. The output is always a clean JSON file — never prose or Midjourney text strings.
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 dotnet-diagnostics-mcp for MCP-driven .NET CPU, allocation, GC, and test-host profiling. USE FOR: profiling unit tests or investigating runtime bottlenecks. DO NOT USE FOR: writing test assertions, coverage collection, or precise microbenchmark timing. INVOKES: connect the MCP server, select target processes, collect bounded profiles, and attribute hotspots to source.
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 `pvanalyze` to inspect existing .NET `.nettrace` files from the command line, including GC, JIT, CPU stacks, allocation, DATAS, events, exceptions, timeline, and call-tree analysis with JSON or SpeedScope. USE FOR: the user mentions pvanalyze, PerfView-style CLI trace analysis, or cross-platform .nettrace inspection; the task starts from an existing .nettrace file and needs. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
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 the free official .NET diagnostics CLI tools for profiling and runtime investigation in .NET repositories. USE FOR: the repo needs performance or runtime profiling for a .NET application; the user asks about slow code, high CPU, GC pressure, allocation growth, exception storms, lock. DO NOT USE FOR: replacing realistic performance tests or load tests with ad-hoc tracing alone; production heap collection when the pause risk has not been. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
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。
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app crash from a tombstone, resolving native backtrace frames in libmonosgen-2.0.so or libcoreclr.so to .NET runtime source code, or investigating SIGABRT, SIGSEGV, or other native signals originating from the .NET runtime on Android. DO NOT USE FOR pure Java/Kotlin crashes, managed .NET exceptions that are already captured in logcat, or iOS crash logs. INVOKES Symbolicate-Tombstone.ps1 script, llvm-symbolizer, Microsoft symbol server.
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。
Guidance for .NET MAUI XAML and C# data bindings — compiled bindings, INotifyPropertyChanged / ObservableObject, value converters, binding modes, multi-binding, relative bindings, fallbacks, and MVVM best practices. USE FOR: setting up compiled bindings with x:DataType, implementing INotifyPropertyChanged or CommunityToolkit ObservableObject, creating IValueConverter / IMultiValueConverter, choosing binding modes, configuring BindingContext, relative bindings, binding fallbacks, StringFormat, code-behind SetBinding with lambdas, and enforcing XC0022/XC0025 warnings. DO NOT USE FOR: CollectionView item templates and layouts (use maui-collectionview), Shell navigation data passing (use maui-shell-navigation), dependency injection (use maui-dependency-injection), or animations triggered by property changes (use .NET MAUI animation APIs).
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。
Guidance for configuring dependency injection in .NET MAUI apps — service registration in MauiProgram.cs, lifetime selection (Singleton / Transient / Scoped), constructor injection, Shell navigation auto-resolution, platform-specific registrations, and testability patterns. USE FOR: "dependency injection", "DI setup", "AddSingleton", "AddTransient", "AddScoped", "service registration", "constructor injection", "IServiceProvider", "MauiProgram DI", "register services", "BindingContext injection". DO NOT USE FOR: data binding (use maui-data-binding), Shell route configuration (use maui-shell-navigation), unit-test mocking frameworks (use standard xUnit and NSubstitute patterns).
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 native C/C++ app, service, or user-mode driver host (including UMDF) crashes with a structured exception in a dump or WinDbg session, including native faults inside managed processes. Not for managed .NET exceptions, WinUI/XAML app errors, or kernel bugchecks.
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 kernel dump contains Driver Verifier violations; inspect flags, bugcheck subcodes, and available I/O shadow state. Not for Application Verifier user-mode stops or inferring a violation from enabled flags alone.
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-LLM collaborative brainstorming and planning. Use when user explicitly requests consultation with multiple AI models (ChatGPT, Gemini, other LLMs) before presenting an implementation plan, or asks to "consult the council", "ask other models", or "get perspectives from other AIs". Queries external LLM APIs, synthesizes their perspectives, and presents an adapted implementation plan.
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 you need to analyze Java profiling data collected during the detection phase — including interpreting flamegraphs, memory allocation patterns, CPU hotspots, threading issues, systematic problem categorization, evidence documentation with profiling-problem-analysis and profiling-solutions markdown files, or prioritizing fixes using Impact/Effort scoring. This should trigger for requests such as Analyze JFR profile; Analyze the profile; Analyze the performance; Analyze the memory; Analyze the threading; Analyze GC logs from profiling; Prioritize Java profiling bottlenecks by impact. Part of Plinth Toolkit
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 you need to set up Java application profiling to detect and measure performance issues — including trusted preinstalled async-profiler v4.x setup, problem-driven profiling (CPU, memory, threading, GC, I/O), interactive profiling scripts, JFR integration with Java 25 (JEP 518, JEP 520), or collecting profiling data with flamegraphs and JFR recordings. This should trigger for requests such as Improve the code with profiling; Apply Profiling; Refactor the code with profiling; Add profiling support; Collect JFR or async-profiler data for Java performance. Part of Plinth Toolkit
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。
Tool skill — the *first move* in any LM-debugging session: dump the actual rendered prompt the framework sent to the model, before changing anything else. Activate when an LM call produced an unexpected output (wrong answer, schema violation, refusal, truncation, cost spike, latency spike, infinite loop, "model got dumber after upgrade"). The skill enforces a 30-second inspect step BEFORE any prompt edit, model swap, retry, or temperature tweak. Cross-framework cheat sheet: DSPy `inspect_history`, LangGraph `get_state_history`, CrewAI `step_callback`, LangChain `set_debug`/`set_verbose`, Aider `/diff`+`--verbose`, raw OpenAI/Anthropic via `OPENAI_LOG=debug`/`ANTHROPIC_LOG=debug` or HTTPX event hooks. Do NOT activate for first-time prompt authoring, exploratory prompt design, or non-LM bugs.
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。
Enhancement-overlay skill — the DECISION + WIRING layer for LM observability that the single-backend skills [[langsmith]], [[phoenix]], [[mlflow]] do NOT cover. Each of those installs one backend; none of them help you DECIDE which backend fits your stack/scale/budget, nor give you a one-line autolog that turns it on fast. Use when starting any LM project, before the first deploy, or the moment someone asks "why did it do that?" and there are no traces to answer with. The skill picks a backend by stack (LangSmith for LangChain/LangGraph; Phoenix for OSS/local OpenTelemetry; MLflow for ML-shops already on MLflow; Langfuse for self-host), wires one-line autolog, verifies traces land, and adds eval hooks — instrumenting BEFORE you need it. Cross-links the first-debug-move skill [[agentsop-prompt-history-inspect]]. Do NOT activate to re-teach a backend you already chose (defer to its own skill), or for non-LM ML experiment tracking with no LLM calls (that is plain MLflow).
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。
Security-first SOP for multi-tenant RAG systems. Activate when a calling agent is building, reviewing, or debugging any retrieval pipeline whose vector store is shared across more than one user, organisation, workspace, customer, or permission scope. Encodes the single non-negotiable rule — **filter at the vector store query, never after retrieval / never after rerank** — together with the per-vendor query-time filter APIs (Pinecone namespaces + `$eq`/`$in`, Weaviate `multiTenancyConfig` + tenant handle, Qdrant `is_tenant` payload index + `Filter.must`, Chroma `where`, pgvector RLS), and the cross-framework adapters (LlamaIndex `MetadataFilters`, LangChain `filter=` dict). Frame the work as preventing CVE-2024-41892 / EchoLeak / Slack-AI-class cross-tenant leakage, not as "adding a filter for relevance".
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。
Operating-system distillation of LlamaIndex — the leading RAG / document-agent framework. Activate when the calling agent must build, debug, harden, or evaluate a Retrieval-Augmented Generation pipeline over unstructured/private data, decide between RAG primitives (Index types, retrievers, query engines, routers, agents), or pick LlamaIndex vs LangChain / Haystack / raw vector store for a coding task. Encodes the 5-layer mental model (Documents → Nodes → Indices → Retrievers → Query Engines / Response Synthesizers), the canonical RAG bootstrap SOP from baseline `VectorStoreIndex` through hybrid + reranker + eval-loop hardening, the official 13-failure-mode checklist, and 5 dilemma cases distilled from docs, GitHub issues, and 2025 production post-mortems.
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。
Re-ingest-correctness SOP for production RAG. Activate when a calling agent builds, reviews, or debugs an ingestion pipeline that runs more than once over a changing corpus — scheduled re-index, incremental updates, CI re-ingest, or a "retrieval has duplicates / shows deleted docs" bug. Encodes the rule — **ingestion must be idempotent: a document's content hash decides insert/update/skip, so re-running over unchanged docs is a no-op** — plus the docstore + doc-hash upsert machinery (LlamaIndex `IngestionPipeline` + `DocstoreStrategy`), the delete-propagation problem, and cross-framework equivalents (LangChain `index()` + `RecordManager`, manual hash table). ENHANCE overlay over [[llamaindex]]: the IngestionPipeline exists in the base skill but the re-ingest-correctness contract is not surfaced.
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。
Enhancement overlay for multi-agent / tool-using coder agents. Encodes the per-agent tool- scoping discipline that role-based frameworks (CrewAI, LangChain) document only as a passing best-practice: which agent gets which tool, and why blanket-sharing every tool to every agent is a correctness and blast-radius risk. Activates when an agent system has tools AND there is more than one agent (or one agent holding many tools). Treat a tool as a capability grant; scope by least-privilege. ENHANCE overlay — read alongside [[crewai]], [[agentsop-http-tool-wrapping]], [[agentsop-llm-tool-idempotency]]. Search keywords: which tools per agent, least-privilege agent, agent tool access, tool permissions, limit agent tools, scope tools to roles.overlay_type: enhancement
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。
Enhancement-overlay decision protocol for STREAMING the output of long-running LLM / agent runs from the *backend*, not just wiring a typing animation in the UI. Activates when a coder agent must stream final tokens to a chat client, surface intermediate agent steps (which tool, which node, partial reasoning), emit custom tool-progress events, choose a transport (SSE vs WebSocket), or decide what to do when the client disconnects mid-stream. The langchain / langgraph skills mention stream modes but stop at "you can stream"; this skill encodes *what to stream, over what transport, and how to fail safely*.
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。
Operating SOP for DSPy (Stanford NLP) — the declarative framework for "programming, not prompting" language models. Activate when the user says any of: "use DSPy", "compile a prompt", "optimize prompts/programs", "MIPRO/MIPROv2", "BootstrapFewShot", "GEPA", "Signatures + Modules", "teleprompter", "auto-tune prompts for a different LM", or whenever a brittle hand-crafted prompt pipeline needs to be turned into a *compiled*, measurable, swappable program. Do NOT activate for one-shot prompt tweaks, no-metric exploratory work, or pipelines where prompts must remain human-authored verbatim — use raw prompting or LangChain templates instead.
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。
Neutral, framework-agnostic decision tree for project kickoff: "which agent / RAG / LLM framework should I reach for?" Synthesizes the ecosystem sections of 7 landmark-project SOPs (LangGraph, LlamaIndex, DSPy, CrewAI, vLLM, Aider, Dify) into one layered rubric. Core stance: frameworks are LAYERS, not competitors — a real project usually combines DSPy (compile) + LlamaIndex (retrieve) + LangGraph (orchestrate) + vLLM (serve), and you choose ONE per layer, not one to rule all. Use when starting any LLM/agent/RAG project, or whenever the "which framework?" question is asked. Deliberately neutral — unlike vendor docs and the LangChain-biased `framework-selection` on skill.sh, this skill has no horse in the race.
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。