「judge」の検索結果

Use when an agent drives Maxon ZBrush 2026 for any task (sculpt in ZBrush, DynaMesh, ZRemesher, UVs, export, polypaint, posing, 3D print, clean up an AI mesh in ZBrush), when writing ZBrush Python (zbrush.commands) or ZScript, when the ZBrush bridge is not answering, a palette path or set() does nothing, a scripted stroke does not sculpt or a dialog blocks a script, or when a ZBrush result has to be judged the way a professional artist would.

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 doing any 3D work in Blender through Python or an MCP bridge, headless or in a live session: modeling, sculpting a character or head, retopology, UV unwrapping, baking, texturing, rigging, animating, previs, geometry nodes, lighting and rendering, grease pencil, or finishing an AI-generated mesh into a production asset. Also when a bpy script fails on Blender 5.x API changes, a brush or sculpt operator fails or crashes headless, or a result has to be judged like a professional 3D artist would.

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。

Creates a reusable use case specification file that defines the business problem, stakeholders, and measurable success criteria for model customization, as recommended by the AWS Responsible AI Lens. Use as the default first step in any model customization plan. Skip only if the user explicitly declines or already has a use case specification to reuse. Captures problem statement, primary users, and LLM-as-a-Judge success tenets.

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。

Lock one primary goal per brand and judge ideas or drafts against it. "does this fit our goal"

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 test their LLM/agent application for safety and security vulnerabilities — jailbreaks, prompt injection, PII extraction, harmful content generation, or evaluator gaming. Also use when the user mentions security testing, adversarial testing, red teaming, safety evaluation, ASR (Attack Success Rate), or "is my app safe to deploy." Outputs ASR paired with over-refusal rate and an audit document.

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。

Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the user asks to evaluate, benchmark, or compare models on academic reference hallucination, literature recommendation quality, or citation 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。

Detect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the claude-verify project. Also extracts injected system prompts from providers that override Claude's identity. Fully self-contained — copy the code below and run, no extra packages beyond httpx. Use when the user wants to verify a Claude API key or endpoint, check if a third-party Claude service is authentic, audit API providers for Claude authenticity, test multiple models in parallel, or discover what system prompt a provider has injected.

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 has a RAG (Retrieval-Augmented Generation) system and wants to evaluate its quality — separating retrieval issues from generation issues. Also use when the user mentions RAG evaluation, faithfulness checking, hallucination detection in RAG, retrieval quality, chunking optimization, or "is my RAG pipeline working." Outputs a diagnostic matrix that pinpoints whether problems are in retrieval or 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。

Discover and recommend **combinations** of agent skills to complete complex, multi-faceted tasks. Provides two recommendation strategies — **Maximum Quality** (best skill per subtask) and **Minimum Dependencies** (fewest installs). Use this skill whenever the user wants to find skills, asks "how do I do X", "find a skill for X", or describes a task that likely requires multiple capabilities working together. Also use when the user mentions composing workflows, building pipelines, or needs help across several domains at once — even if they only say "find me a skill". This skill supersedes simple single-skill search by decomposing the task into subtasks and assembling an optimal skill portfolio.

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 has run multiple evaluation skills and wants a comprehensive analysis — maturity assessment, cross-skill signals, trends, prioritized actions, and an executive summary. Also use when the user mentions eval health check, evaluation audit, ship readiness, evaluation maturity, or "how good is my evaluation system itself." This is a read-only analysis skill.

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。

Verify a BibTeX file for hallucinated or fabricated references by cross-checking every entry against CrossRef, arXiv, and DBLP. Reports each reference as verified, suspect, or not found, with field-level mismatch details (title, authors, year, DOI). Use when the user wants to check a .bib file for fake citations, validate references in a paper, or audit bibliography entries for 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。

Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the user asks to evaluate, benchmark, or compare models on academic reference hallucination, literature recommendation quality, or citation 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 the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific workflow fits — a general-purpose win-rate comparison on a custom task, or a benchmark specifically about reference/citation hallucination rate. Also use when the user mentions model arena, agent arena, pairwise model comparison, win-rate ranking, or comparing models on a task and hasn't specified whether that task is generic or about citation accuracy. This skill is the entry router for the arena-eval suite: it asks one diagnostic question when needed, then recommends the workflow or workflows needed to cover the request.

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 help with academic papers or citations but it's unclear which specific workflow fits — reviewing a paper, checking a BibTeX file for fake references, or benchmarking multiple LLMs on reference-recommendation accuracy. Also use when the user mentions paper review, peer review, BibTeX verification, citation checking, reference hallucination, or academic literature accuracy and hasn't specified which of those three tasks they mean. This skill is the entry router for the academic-eval suite: it asks one diagnostic question then routes to the right sub-skill.

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。

Generate text, images, video, speech, and music via the MiniMax AI platform. Covers text generation (MiniMax-M3 model), image generation (image-01), video generation (Hailuo-2.3), speech synthesis (speech-2.8-hd, 300+ voices), music generation (music-2.6 with lyrics, cover, and instrumental), and web search. Use when the user needs to create AI-generated multimedia content, produce narrated audio from text, compose music, or search the web through MiniMax AI services.

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。

Writes a settlement letter on the right footing — and warns you when marking it 'without prejudice' won't actually keep it out of court. A genuine settlement letter is normally protected (the judge can't see it), but only if the substance is a real attempt to settle, and even then there are exceptions. The skill picks the correct footing — without prejudice (WP), without prejudice save as to costs (WPSATC / Calderbank), or open — drafts the finished letter, and surfaces the Unilever v Procter & Gamble exceptions that get WP material admitted despite the label, which a plain template won't flag. Built for juniors and in-house counsel drafting a settlement or Calderbank offer who need the footing right the first time. Use when the user asks to draft a WP letter, a Calderbank, a settlement letter, or wants to know whether material is likely protected from disclosure.

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。

Act as experienced opposing counsel to attack, undermine, and expose weaknesses in a legal argument, submission, witness statement, or structured reasoning. Produces a six-part adversarial analysis: 1. A core theory of attack identifying the single most effective way to defeat the argument; 2. A reconstructed version of the opposing argument stripped of rhetoric to expose its fragility; 3. Primary lines of attack grouped by category (legal misstatement, evidential gaps, causation failures, internal inconsistency, over-reliance on assertion, procedural weakness); 4. An "if I were the judge" section showing how a sceptical tribunal would dismantle the argument; 5. Surgical strikes - 3 to 5 high-impact points ready for oral submissions; and 6. An analysis of what the argument is trying to hide. Written in formal, adversarial British English for a legally trained audience.

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。

Assesses a legal argument, submission, or piece of structured reasoning from the perspective of a judge reading it cold under time pressure. Produces a structured seven-part assessment: what the case appears to be about, immediate points of confusion, what feels strong, what feels weak, what is assumed but unproved, a provisional confidence level (low/medium/high), and what would be needed to persuade. The skill does not rewrite, improve, or attack the argument — it tells you how it actually lands on a sceptical, experienced reader with no prior context. Works on skeleton arguments, witness statements, letters before action, position statements, academic articles, and non-legal structured reasoning.

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。

Turns one customer case study into the tightest list of companies that would read that case study and see themselves. Decomposes WHY the case-study company resonates into concrete attributes, translates those attributes into database filters, intersects them with a lookalike anchor, then widens with a model judge. Triggers on "find more companies like our best customer", "who would our case study land with", "lookalikes of X", "build a list around this case study", "companies like our happiest client", "expand this list, it is too small". Outputs a filter set plus one merge field naming which case study to cite.

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。

Split the Plan/Act/Verify loop across three model tiers — frontier planner, cheap executor, frontier judge — via env vars read by run.sh.

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 a repeatable eval loop that grades agent output with an LLM judge, so prompt/skill changes get scored against a baseline instead of eyeballed. Reuses loopkit's verifier subagent as the grader — do not build a new one.

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。

Monthly, on the last weekday, file work only, no browser at all. Folds the decision ledger, scores this Employee's own judgement against the metric files that measured it rather than against its own predictions, appends one outcome line per closed decision, retires a move proposed three times and never accepted, and rewrites the priorities where the evidence disagrees with them. It refuses to publish a calibration figure on too few closed decisions, changes nothing outside its own folder, proposes nothing to anybody, sends only where you released the channel, spends only where you released it, and never touches a credential.

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。