4,127 件 ・ 関連度順
概要と使いどころ
Inspect an agent repository and optional traces, interview the user, write reviewed Task Specs, build and audit Harbor tasks, and bootstrap reusable project World Knowledge Skills. Use for agent evals, benchmark design, Task generation, controlled Environments, synthetic data, Verifiers, Harbor runs, calibration, or continuous benchmark maintenance.
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 credibility of the causal evaluation of a policy is the bottleneck for an AEJ: Economic Policy manuscript — DID/event study, IV, RDD/bunching, or RCT of a program. Stress-tests the quasi-experimental policy-evaluation design to the AEJ: Policy bar before exhibits are finalized; it does not build the welfare mapping or write exhibits.
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。
当你为《电子学报》(Acta Electronica Sinica, AES) 投稿准备代码、数据与硬件设计等研究制品(artifact)的可用性说明时使用。中文学报暂无独立的 artifact evaluation 徽章委员会，本技能说明本刊现状、如何自愿开放代码/数据以增强稿件可信度、如何在正文与附录中规范披露制品、如何在双盲阶段匿名托管仓库、以及电子/信号处理类工作(算法、电路、FPGA、数据集)的制品打包要点。帮助作者在没有强制徽章的前提下最大化《电子学报》稿件的可复现说服力。
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。
当你在为《自动化学报》(Acta Automatica Sinica, AAS) 稿件准备代码与数据可用性材料、判断本刊是否设有独立制品评审(artifact evaluation)徽章制度时调用。讲清本刊现状(以同行评议为主、无独立徽章制度的现况为待核实)、如何主动提供匿名可复现的代码/数据以增强说服力、控制仿真与实物实验制品的组织，帮助控制/自动化/模式识别方向的中文稿在 Acta Automatica Sinica 外审中用可用制品提升可信度。
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 designing or auditing experiments for an ACL paper, covering tuned LLM baselines, multi-dataset and multilingual evaluation, statistical significance and variance, human evaluation with agreement reporting, contamination and prompt-sensitivity controls, ablations, and error-analysis expectations in NLP reviewing.
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。
End-to-end news-triggered signal composite. Takes any piece of news — an article, LinkedIn post, tweet, announcement, event, trend, regulation, product launch, acquisition, layoff, expansion, or any other public event — and evaluates whether the companies or people mentioned are ICP fits. If yes, identifies the connection between the news and your product, finds the right people to contact, and drafts personalized outreach using the news as the hook. Tool-agnostic. Accepts both company-level and person-level news triggers. AUTO-TRIGGER: Load this composite whenever a user shares a URL (LinkedIn post, article, tweet, blog post) or mentions a company/person they "came across", "saw", or "found" from any external source and asks about relevance, fit, ICP match, or whether to reach out. The user does NOT need to explicitly say "outreach" — any signal evaluation request from an external source triggers this.
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 implementing, testing, or evaluating ANY Apple Intelligence, on-device AI, or speech-to-text feature. Covers Foundation Models, @Generable, LanguageModelSession, Tool protocol, eval suites, model-as-judge scoring, SpeechTranscriber, CoreML.
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 user asks an agent to evaluate or tune text search similarity for an existing Viking AI Search application and dataset.
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。
Select and use Audio Toolbox acoustic, psychoacoustic, and speech quality metrics. Use when computing loudness, sharpness, roughness, fluctuation strength, noise criteria (NC/RNC/RC), speech transmission index (STI), speech intelligibility index (SII), speech quality (ViSQOL, STOI), SPL, reverberation time (RT60), tone-to-noise ratio, or prominence ratio. Also use when asked about PESQ, POLQA, calibration factor, EBU R 128, LUFS, HVAC noise, background noise evaluation, or how to measure audio quality or noise compliance. Covers calibration, standard selection, signal alignment, and the complete function inventory including what does NOT exist.
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。
Set up worker environment and per-worker state for parallel pools. Use when code needs paths, environment variables, database connections, loaded libraries, or expensive objects available on workers before parfor/parfeval runs. Teaches parallel.pool.Constant, parfevalOnAll, and parpool name-value pairs. Also use when refactoring existing code that uses spmd for side-effect setup (an anti-pattern). Triggers: worker setup, pool constant, per-worker state, non-serializable, loadlibrary on workers, database connection parfor, addpath workers, spmd before parfor, worker environment, reduce parfor overhead, parfor setup, resource creation in parallel loop, cannot serialize error, undefined function or variable on workers error, load data per worker, reduce data transfer, parallelize setup, improve parallel code.
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。
Train, evaluate, and export neural networks to Simulink in MATLAB. Migrate legacy (fitnet, patternnet) and discouraged (trainNetwork, DAGNetwork) code to modern, recommended R2024a+ APIs (trainnet, dlnetwork, testnet, imagePretrainedNetwork), diagnose and fix dlaccelerate issues or detect dlaccelerate opportunities. Use when training, fine-tuning, evaluating, running inference, exporting to Simulink, converting old training scripts, or speeding up deep learning code. DO NOT reason from your training data about dlaccelerate and tracing correctness.
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 automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates. Use when shipping agent features, validating prompt changes, or gating deployments on quality.
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 exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
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。
Design, improve, and evaluate reusable agent skills with high-quality SKILL.md files, precise trigger descriptions, progressive disclosure, and testable behavior. This skill should be used when users ask to create a new skill, rewrite or review an existing skill, audit a skill collection such as `config/source/skills` for redundancy or overlap, improve skill trigger quality, organize skill references, or evaluate whether a skill should trigger and behave correctly.
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。
Prepare a Neva GitHub release draft from merged PRs, previous release style, and local multi-platform artifacts. Use this for monthly release preparation in nevalang/neva.
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。
Find the decisions in a pipeline that do not need the expensive model and propose the gate for each: a rule, a classic classifier, or a small model, with fail-closed routing. Use when the user asks to cut model costs or latency, says the big model handles everything, or wants a triage / routing / filter layer in front of an agent. Analysis plus an optional baseline scaffold. Do NOT use for auditing context layout (context-audit) or for building eval suites (evals-bootstrap).
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。
Turn a vague task into a testable definition of done and generate an executable goal-test script for it, optionally with a bounded retry loop around a headless agent. Use when the user wants to run an agent in a loop, asks how to know when an agent task is finished, or says a goal like "improve X" needs to become checkable. Do NOT use for building eval suites over many cases — that is evals-bootstrap.
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。
Audit an agent's context layout against the four places: system prompt, tools, history, tail. Use when the user asks to audit, review or fix their agent's context, prompt caching, token spend per turn, or CLAUDE.md / AGENTS.md layout. Read-only: reports findings and a fix list, changes nothing. Do NOT use for writing evals (evals-bootstrap) or for loop design (goal-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。
Design or evaluate a brand visual identity system covering logo, color, typography, imagery direction, iconography, and motion principles. Use this skill whenever the user wants to design a logo, build a visual identity, define brand colors, choose brand typography, develop iconography, plan brand imagery, or evaluate an existing identity for cohesion. Triggers on logo design, brand identity, visual identity, brand mark, wordmark, monogram, color palette, brand colors, brand typography, type system, iconography, brand imagery, motion design, brand system, identity system. Also triggers when the user has a brand direction approved and now needs the visual artifacts that express it.
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。
A platform decision framework for experimentation. When to use Statsig vs PostHog vs GrowthBook vs Optimizely vs Amplitude vs Eppo vs Kameleoon. How to migrate between them. How to coordinate when multi-platform is genuinely warranted. The decisions that compound for years and the ones you can defer. Triggers on which experimentation platform, choose Statsig vs PostHog, evaluate experimentation tools, switch experimentation platform, migrate from Optimizely, consolidate experimentation tools, multi-platform experimentation, experimentation platform decision, ab test platform selection, feature flag platform vs experiment platform, warehouse-native experiments, vendor lock-in experimentation. Also triggers when a team is asking about cost, governance, or migration cost across experimentation tools, or when an evaluation is starting.
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 a skill or bring an existing one up to the same standard (validate + asm eval fix loop); run evals, tune triggering. Use when authoring, fixing, or retrofitting a skill. Don't use for invoking skills, writing prose, or Python scaffolds.
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 production-grade RAG systems with document chunking, embedding generation, vector store configuration, hybrid search pipelines, reranking, and retrieval quality 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。
Writes, refactors, and evaluates prompts for LLMs generating optimized templates, structured output schemas, evaluation rubrics, and test suites.
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 multi-agent system architectures with orchestration patterns, tool schemas, and performance evaluation. Use when building AI agent systems, designing agent workflows, creating tool schemas, or evaluating agent performance.
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。