1,116 件 ・ 関連度順
概要と使いどころ
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
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。
Test coverage quality analysis — behavioral coverage, critical gap identification, test resilience evaluation.
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。
ThoughtWorks Radar model, technology evaluation framework, ADR format, and stack compatibility analysis
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。
CTO-level advisory - build vs buy decisions, tech debt quantification, team scaling, ADRs, technology evaluation (RICE), budget planning, TCO, vendor management, DORA/SPACE metrics
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。
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
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。
Write one survey-quality paragraph from evidence packs (tension → contrast → evaluation anchor → limitation).
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 per-subsection evidence packs (NO PROSE): claim candidates, concrete comparisons, evaluation protocol, limitations, plus citation-backed evidence snippets with provenance.
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. 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.
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 fixes skills in the dotnet/skills repository that lose to their own baseline, fail to activate, time out, or return "no credible improvement". Use when an evaluation verdict is a regression or underpowered, when a skill regressed after a change, when /evaluate reports no results, or when deciding whether a weak skill should be strengthened or retired. Do not use for scaffolding a brand-new skill (use create-skill) or a brand-new eval (use create-skill-test).
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。
Own MSBuild generated-artifact integration. USE FOR: a target that creates or should create source, Content, None, or another physical file but the artifact is missing from compilation or output; target timing; evaluation-time glob misses; $(IntermediateOutputPath) placement; and FileWrites clean tracking. The prompt may describe the generated artifact without naming the producing task. DO NOT USE when the primary defect is general Include/Remove/Update semantics, item metadata or batching, duplicate/overlapping declarations, or a generated-item identity relationship; use item-management. Exclude Roslyn source-generator internals and non-MSBuild 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。
Scaffolds new agent skills for the dotnet/skills repository. Use when creating a new skill, generating SKILL.md files, writing a skill description that the runtime will actually route to, or setting up skill directory structures. Handles frontmatter generation, section templates, and validation guidance. Do not use for fixing a skill that already fails its evaluation (use improve-skill-quality) or for writing eval.yaml (use create-skill-test).
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。
Build provider-agnostic .NET AI integrations with `Microsoft.Extensions.AI`, `IChatClient`, embeddings, middleware, structured output, vector search, and evaluation. USE FOR: building or reviewing .NET code that uses Microsoft.Extensions.AI, Microsoft.Extensions.AI.Abstractions, IChatClient, IEmbeddingGenerator, ChatOptions, or AIFunction;. 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 only for MSBuild failure investigation, build-performance analysis, or review of existing build XML/extension contracts. A plan to convert a working legacy/non-SDK project to SDK style or migrate packages.config is a project-system migration, NOT a build-file review: do not activate, even to check scope. Framework/API upgrades are also excluded. Activate for advisory Import/Exists hook and NuGet packed-import questions even without a checkout or failed build; .csproj/.fsproj/.vbproj/.props/.targets conditions; custom-target inputs/outputs; .binlog capture/replay; failing dotnet build/restore/pack/publish or MSBuild-based test builds; slow evaluation, compilation, copying, or no-change builds; and controlled timing comparisons. Exclude SDK installation alone, C# refactoring, runtime profiling, assertions after successful builds, and non-MSBuild builds.
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 ML.NET to train, evaluate, or integrate machine-learning models into .NET applications with realistic data preparation, inference, and deployment expectations. USE FOR: ML.NET integration; local model training or retraining; inference pipelines, model loading, evaluation, and deployment review. 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 when a problem under exploration needs its quality attributes (non-functional requirements) identified and prioritized before architecture and design begin. This should trigger when an issue's Quality Attribute Discovery point of view needs evaluation, or when a maintainer directly asks to discover and prioritize candidate quality attributes for a problem, before any ADR or design work starts. 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 a framed problem needs root-cause investigation rather than a symptom-level fix, applying Five Whys, Fishbone (Ishikawa), Current Reality Tree, and constraint identification. This should trigger when an issue's Root Cause Analysis point of view needs evaluation, or when a maintainer directly asks to find the root cause of a problem before proposing a fix. 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 a problem or issue needs explicit framing before deeper analysis begins — establishing the Problem statement, Current state, Desired state, Stakeholders, and Success criteria. This should trigger when an issue's Problem Framing point of view needs evaluation, or when a maintainer directly asks to frame a problem before root-cause analysis, design, or planning begins. 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 a framed and root-caused problem needs its assumptions made explicit before design or planning begins — explicit Assumptions, Unknowns, and a Validation plan. This should trigger when an issue's Assumption Analysis point of view needs evaluation, or when a maintainer directly asks to surface hidden assumptions and unknowns before committing to an approach. 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 a problem under exploration needs its surrounding system context identified before design begins — Existing systems, Integrations, Ownership, and External dependencies. This should trigger when an issue's Context Mapping point of view needs evaluation, or when a maintainer directly asks to map the systems, integrations, owners, and external dependencies relevant to a problem. 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。
Project-kickoff rubric for the self-host vs managed-cloud decision — when is running your own inference engine / LLM platform worth the ops cost vs paying per-token for a managed API? Decide on two axes — VOLUME (a cost-crossover slider) and COMPLIANCE (a hard gate). Use at kickoff when choosing where to run inference, or when cost / data-residency pressure forces a re-evaluation.
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。
Universal discipline for any LM-driven loop — agent retries, plan-act-observe, multi-agent handoffs, optimiser passes, test-fix cycles. Encodes the one rule every framework documents quietly and every team relearns expensively: the LM in the loop is NEVER a reliable terminator. Termination must be provided by an explicit counter + exit predicate + stagnation signal + escalation path that live OUTSIDE the LM's control. This is a tool- level, framework-agnostic skill. It maps onto LangGraph (recursion_limit + state counter + interrupt), CrewAI (max_iter + max_rpm + human_input), Claude / OpenAI SDKs (max_iterations + tool_use_budget), DSPy (declared evaluation budget), Aider (REPL + explicit retry cap), and AutoGen (max_consecutive_auto_reply). Search keywords: infinite loop, recursion limit, recursion_limit, GraphRecursionError, max iterations, max_iter, agent stuck, agent won't stop, runaway agent, ReAct loop not terminating, agent repeating itself.
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。
Build and govern a 50-200 example domain-specific held-out benchmark sampled from real traffic. Distinct from public benchmarks (MMLU/HumanEval/GSM8K via lm-evaluation-harness) which measure GENERAL capability. Only a held-out domain set predicts whether THIS system works on YOUR data. Collect real examples, label, hold out (never train/prompt on it), size 50-200, version it, refresh on drift.
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。
Designs multiscale chunking for RAG by embedding small units for retrieval precision and returning larger context for synthesis. Use when fixed-size chunks either lose surrounding context or dilute relevance in long documents, manuals, filings, or codebases. Covers sentence-window and parent-child or auto-merging strategies, base chunk sizing, and evaluation. Do not use when a single chunk scale already meets retrieval and generation needs.
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。
Decomposed, multi-criteria metric design for LLM pipelines. The metric IS the model — change the metric and the optimizer changes behavior. Decompose by default; bool during compile, float during eval; calibrate against human; mitigate judge bias. Search keywords: LLM-as-judge, llm as judge, eval metric, evaluation score, scoring function, rubric, RAGAS, G-Eval, judge bias, verbosity bias, how to evaluate LLM output.
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。