「eval」の検索結果

ベクトルデータベースとセマンティック検索を使用してLLMアプリケーションのためのRetrieval-Augmented Generation（RAG）システムを構築します。知識に基づいたAI、ドキュメントQ&Aシステムの構築、またはLLMと外部ナレッジベースの統合時に使用します。

Marp形式プレゼンテーションの専門レビュー・評価・改善スキル。 10軸スコアリング（100点満点）で品質を定量評価し、具体的な改善コード付きで提案する。 Use when the user asks to: - Review, evaluate, or critique a Marp presentation / プレゼンをレビュー / 評価 / 添削 - Improve, polish, or upgrade existing slides / スライドを改善 / ブラッシュアップ - Check slide quality, score slides, or audit a deck / スライドの品質チェック / 採点 - "このプレゼンどう？" "スライドを見てほしい" "プレゼン資料のフィードバック" Reads .md files with Marp frontmatter, scores across 10 dimensions, and outputs a detailed review report with concrete before/after code improvements. Works as a companion to the marp-slides skill (generation → review → improvement cycle).

Azure Resource Manager SDK for Arize AI Observability and Evaluation (.NET).

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 working with Azure Policy Deep — azure Policy deep compliance and governance management. Covers policy definitions, initiatives, assignments, compliance evaluation, exemptions, remediation tasks, custom policies, and regulatory compliance. Use when managing Azure governance at scale, reviewing compliance states, creating custom policies, or troubleshooting policy evaluation results.

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 working with Kubescape — kubescape Kubernetes security posture analysis. Covers NSA/CISA framework assessment, MITRE ATT&CK mapping, CIS Kubernetes benchmarks, workload scanning, RBAC analysis, and network policy evaluation. Use when assessing Kubernetes cluster security, evaluating compliance frameworks, or analyzing workload configurations.

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。

lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).

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。

Hijacking, Red-Team Evals, and Continuous Evaluation A technical reference on agent hijacking, red-t

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。

Cache dynamic and static responses on Netlify's CDN from Functions, Edge Functions, and proxies. Use when you add caching or cache-control headers to a function response, tune cache TTL or stale-while-revalidate, set up the durable cache, vary a cache key by query/header/cookie/country/language, purge or invalidate the cache by site or cache tag, use the programmatic Cache API (caches.open/match/put) or @netlify/cache helpers (fetchWithCache/cacheHeaders/getCacheStatus), speed up an expensive API call, add ISR or on-demand revalidation, or debug why a response is or isn't cached via the Cache-Status header.

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。

Caching Specialist IA — Expert en caching (Redis, Memcached, CDN, HTTP caching, stale-while-revalidate)

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 en RAG agentique (retrieval multi-étapes, self-query, chunking adaptatif, tool-augmented generation)

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 en systèmes de mémoire pour agents IA (court terme, long terme, épisodique, sémantique, vector retrieval, RAG)

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。

Detects MSBuild projects with conflicting OutputPath or IntermediateOutputPath. Only activate in MSBuild/.NET build context. USE FOR: builds failing with 'Cannot create a file when that file already exists', 'The process cannot access the file because it is being used by another process', intermittent build failures that succeed on retry, missing outputs in multi-project builds, multi-targeting builds where project.assets.json conflicts. Diagnoses when multiple projects or TFMs write to the same bin/obj directories due to shared OutputPath, missing AppendTargetFrameworkToOutputPath, or extra global properties like PublishReadyToRun creating redundant evaluations. DO NOT USE FOR: file access errors unrelated to MSBuild (OS-level locking), single-project single-TFM builds, non-MSBuild build systems. INVOKES: binlog MCP server tools (overview, projects, evaluations, properties, double_writes); falls back to dotnet msbuild binlog replay + grep when the MCP is unavailable.

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。

Guide for optimizing MSBuild incremental builds. Only activate in MSBuild/.NET build context. USE FOR: builds slower than expected on subsequent runs, 'nothing changed but it rebuilds anyway', diagnosing why targets re-execute unnecessarily, fixing broken no-op builds. Covers 8 common causes: missing Inputs/Outputs on custom targets, volatile properties in output paths (timestamps/GUIDs), file writes outside tracked Outputs, missing FileWrites registration, glob changes, Visual Studio Fast Up-to-Date Check (FUTDC) issues. Key diagnostic: look for 'Building target completely' vs 'Skipping target' in binlog. DO NOT USE FOR: first-time build slowness (use build-perf-baseline), parallelism issues (use build-parallelism), evaluation-phase slowness (use eval-performance), non-MSBuild build systems. INVOKES: binlog MCP server tools (overview, search, target details); falls back to dotnet build /bl, binlog replay with diagnostic verbosity.

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。

MSBuild property definition patterns: conditional defaults, composition/concatenation, path normalization, trailing slash handling, TFM detection helpers, and property evaluation order. Only activate in MSBuild/.NET build context. USE FOR: diagnosing and fixing MSBuild property definition issues in .props or .csproj files, reviewing and fixing shared property configuration anti-patterns, fixing DefineConstants or NoWarn being overwritten instead of appended, fixing unconditional property assignments that prevent project-level overrides, fixing unquoted conditions that fail when properties are empty, fixing hardcoded paths that break cross-platform builds, setting property defaults that can be overridden, understanding property evaluation order and last-write-wins semantics. DO NOT USE FOR: props vs targets placement (use directory-build-organization), item operations (use item-management), target structure (use target-authoring), general anti-patterns (use msbuild-antipatterns), non-MSBuild build 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。

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.

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。

RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval 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。

Understand the constraints a design was built under and evaluate quality within that context. Use when reviewing work that had limited time, budget, or team size, or when assessing whether constraints were handled well.

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 design quality evaluation. Hierarchy, type, color, space, craft, system. Use when evaluating whether a design is ready to ship, running quality audits, or setting quality standards.

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。

Break a design system into its constituent decisions and evaluate each one. Use when auditing design systems, evaluating consistency, or understanding how a product maintains quality at scale.

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 in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.

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。

RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval 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。

Create new Claude Code Agent Skills in Japanese with proper SKILL.md format, trigger design, and evaluation methods. Triggers on requests for スキル作成, 新しいスキルを作る, SKILL.md作成, Agent Skill テンプレート, スキルの書き方.

Apply critical rationalist epistemology (Popper, Deutsch) to evaluate reasoning, identify errors, and refine understanding. Use when the user explicitly requests help with reasoning - phrases like "help me think this through", "does this make sense", "any flaws in this", "what am I missing", "critique this", "is this reasoning sound", "stress test this idea", "devil's advocate", or any request to evaluate arguments, identify logical problems, or improve thinking. Also use when errors in reasoning are significant enough to materially affect the user's goals, even if not explicitly requested.

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。

Run a 3-leg evaluation against a newly released LLM. Leg 1 is trap questions with deterministic answers, leg 2 is an agentic orchestration task with a planted failure, leg 3 is a brownfield feature build in a real repo. Use when the user wants to vibe-check, test, evaluate, or compare a new frontier model, or mentions model-bench, model vibe check, or launch-day protocol.

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。