「benchmark」の検索結果

Systematic exploration of unknown environments before starting work

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。

Working with diverse data formats: binary, text, structured, and custom

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。

Building, compiling, and resolving dependency issues across languages

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。

Thorough verification of completed work before declaring done

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 approach to diagnosing and fixing errors

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。

Writing efficient code that handles large data and tight constraints

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。

When the user wants to analyze website traffic sources, attribution, or dark traffic. Also use when the user mentions "traffic sources," "dark traffic," "direct traffic," "UTM parameters," "traffic attribution," "channel attribution," "attribution optimization," "channel analysis," "traffic analysis," "traffic diversification," "natural traffic benchmark," or "organic vs paid traffic." For GA4 setup, use analytics-tracking.

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 skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

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 comparing Scenario models on the same brief through MCP: a bake-off with shared prompts and inputs, cost, generation time and quality measured side by side, choosing a default model, testing a new release against the incumbent, or finding which model handles a style, edit, or reference image best. Keywords: model comparison, benchmark, bake-off, A/B test, contact sheet, cost per asset, latency.

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 CIS Controls v8 (CIS Top 18) advisor — implementation group scoping (IG1/IG2/IG3), control gap assessments, safeguard-level guidance, asset inventory, software inventory, data protection, secure configuration, account management, access control, continuous vulnerability management, audit log management, email and web browser protections, malware defenses, network infrastructure management, network monitoring and defense, application software security, incident response, penetration testing, and CIS Controls mapping to NIST CSF, ISO 27001, SOC 2, and CMMC. Use for any question about CIS Controls, CIS Benchmarks, Implementation Groups, or prioritized cyber hygiene for any organization size.

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 skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

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。

Comprehensive global knowledge worker salary data with total market value calculations, sector breakdowns, geographic comparisons, and authoritative sources. USE WHEN discussing knowledge worker compensation, salary benchmarking, economic analysis of professional labor markets, or AI impact on wages.

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。

Performance regression detection. Captures TTFB, FCP, LCP, bundle sizes, request counts. Regression thresholds: timing >50% or >500ms. Baseline comparison, trend tracking, budget compliance scorecard.

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。

Selects a base model for the user's use case by querying SageMaker Hub. Use when the user asks which model to use, wants to select or change their base model, mentions a model name or family (e.g., "Llama", "Mistral", "Nova"), or wants to evaluate a base model — always activate even for known model names because the exact Hub model ID must be resolved. Queries available models, presents benchmarks and licenses, and confirms selection.

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。

Generates python code that evaluates SageMaker models. Supports two evaluation types: LLM-as-Judge and Custom Scorer. Use when the user says "evaluate my model", "run a benchmark", "test model performance", "how did my model perform", "compare models", or other similar requests.

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。

Social media campaign analysis and performance tracking that calculates engagement rates, ROI, and cross-platform benchmarks. Use for analyzing social performance, calculating engagement rate, or measuring campaign ROI.

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。

Plan or audit paid ads with current platform rules and benchmarks: Google PMax/AI Max, Meta, retail. "should we use Performance Max"

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 funnel drop-offs from stage numbers you give or connected data, benchmarked, ranked by revenue. "where are we losing people"

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。

Load shared marketing context: brand profile, benchmarks, compliance rules, specs. "load my brand context"

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 the analytics layer with script-backed benchmarks: KPI trees, report templates, MMM, cookieless. "define our KPIs"

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 fable-mode execution discipline on Claude Fable 5.1 — the top of the escalation ladder and the strongest staged run available. Routes the task to the @fable-orchestrator agent with its model overridden to Fable (`model: "fable"`), which stages the work, delegates artifact production to @fable-worker-sonnet / @fable-worker-haiku, and cold-checks deliverables with @fable-verifier. Trigger when the user explicitly asks for thorough/systematic/"deep work" handling on the strongest model ("fable on fable", "stage this on fable", "deep work mode, fable", "run this on 5.1"), or when a fable-opus run reports the task exceeds Opus's ceiling. Benchmarked 2026-09-02: zero correctness delta on Fable 5.1 at ~1.1× tokens, ~2× wall — a provenance runner, not an accuracy runner. Do NOT use for ordinary single-pass tasks — prefer fable-opus, fable-sonnet, or fable-haiku when the task doesn't need peak reasoning. Fable is plan-included; bulk work still routes down-tier.

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 fable-mode execution discipline on Claude Haiku. Routes the task to the @fable-worker-haiku agent, whose definition carries the staged loop with tightened verification (no bare "unverified" allowed) and an escalate-don't-improvise rule. Trigger when the user explicitly asks for thorough/systematic handling run cheaply or fast ("fable on haiku", "deep work mode but cheap", "stage this on haiku"). For bulk mechanical work. Do NOT use for tasks needing synthesis — benchmark note: at n=1 the skill's effect on Haiku swung both directions (+25 / −17); route quality-critical work to fable-sonnet 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。

Use when the user wants to build an evaluation system for an LLM/agent application but doesn't know where to start — they have traces, prompts, RAG pipelines, or nothing at all. Also use when the user mentions evaluation, eval, benchmarking, testing LLM quality, measuring agent performance, assessing RAG accuracy, or wants to compare prompts/models. This skill is the entry router: it asks diagnostic questions then recommends which sub-skill (local workflow) to use next.

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。

Automatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects responses from all target endpoints, auto-generates evaluation rubrics, runs pairwise comparisons via a judge model, and produces win-rate rankings with reports and charts. Supports checkpoint resume, incremental endpoint addition, and judge model hot-swap. Use when the user asks to compare, benchmark, or rank multiple models or agents on a custom task, or run an arena-style 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。