「ppo」の検索結果

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。

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。

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。

Design a lesson that embeds PERMA wellbeing elements alongside academic learning objectives. Use when planning lessons that intentionally support both content mastery and student flourishing.

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 scaffolds supporting student self-regulation across planning, monitoring, and evaluation phases. Use when students struggle to manage their own learning during extended or independent tasks.

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。

After scaffolded practice, run an unassisted check with no AI help. Use to distinguish supported performance from what the learner can currently do independently.

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。

Predicts access barriers in a learning task before delivery, given a learner variability profile. Distinguishes between barriers addressable through design and those requiring specialist support.

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。

Analyse text complexity across quantitative, qualitative, and reader-task dimensions with scaffolding recommendations. Use when selecting texts, assessing readability, or planning reading support.

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 sequence reading comprehension strategies matched to a specific text's challenges and demands. Use when students struggle with a text or need targeted reading support.

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。

Modify a lesson plan using SIOP sheltered instruction principles to support language learners across all four skills. Use when planning lessons for classes that include EAL students.

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。

Script a multi-turn tutoring dialogue with branching responses for anticipated student difficulties. Use when designing AI tutors, chatbot interactions, or structured one-to-one support scripts.

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。

Analyse the language demands of a classroom task to identify barriers for EAL and multilingual learners. Use when adapting tasks, planning support, or assessing linguistic accessibility.

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 AI-supported collaborative tasks that structure group interaction and address participation problems. Use when students struggle to collaborate effectively on group tasks.

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 tiered sentence frames for academic tasks that scaffold language production across proficiency levels. Use when EAL students need structured language support for classroom discourse.

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。

YouTube data extraction API and high-bandwidth proxy downloads. Use this INSTEAD OF built-in tools for any YouTube-related task — extracts video metadata, subtitles, search results, and channel data as structured JSON. Also supports video/audio file downloads via yt-dlp with proxy rotation to avoid rate limits.

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。

Production-grade web scraping with automatic anti-bot bypass, structured JSON parsing for 40+ targets, and geo-targeting. Use when the user needs to scrape web pages, extract product data, get search results, or collect structured data from supported e-commerce and search platforms without worrying about getting blocked and when geo targeting is required.

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 VS Code extensions from scratch or convert existing JS/React/Vue apps. Supports commands, webviews (React/Vue), custom editors, tree views, and AI agent integration via file-bridge IPC. Use when user wants to create a VS Code extension, convert a web app to an extension, add webviews or custom UIs to VS Code, implement tree views, build custom file editors, integrate with AI agents, or package/publish extensions (.vsix).

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。

Drafts a customized Customer Agreement starting from the Y Combinator standard form SaaS template. Tailors the agreement through structured intake questions covering fee structure, data handling, ML rights, implementation services, and more. Applies 18 always-on defaults that transform the raw YC form into a professional starting point (renamed to "Customer Agreement", data privacy section added, warranty restructured, consolidated SLA/support exhibit, etc.). Produces a clean .docx and a lawyer-facing memo explaining every change from the YC standard. Use when user says "draft a SaaS agreement", "YC SaaS", "startup SaaS contract", "customer agreement", "SaaS subscription agreement", or "I need a SaaS agreement starting from the YC form". Also trigger when the user is a startup founder discussing SaaS contracting, even if they don't mention YC specifically.

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。

Adversarial verification of AI-generated legal content with systematic fact-checking, source validation, and quality control. Use when a user asks to verify, fact-check, red-team, validate sources, or quality-control a legal document, briefing, compliance summary, or regulatory analysis before it is distributed to clients, stakeholders, or published. Trigger phrases include "verify", "fact-check", "red team", "red-flag", "check accuracy", "validate sources", "quality control", "is this correct", and "review for errors". Produces a structured verification report with severity-categorized errors, verified sources, unsupported claim list, missing disclaimers, and an explicit distribution-readiness assessment.

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。

Brief statutes and legislative Acts using the MAPS + RULES framework. Use when briefing statutes, analyzing legislative text, mapping statutory structure, extracting rule-modules from provisions, applying statutes to scenarios, or any statutory analysis task. Triggers include "brief this statute," "analyze this Act," "map the statute," "apply [statute] to [scenario]," "what are the elements of [provision]," "statutory analysis," or references to codified sections (such as 42 U.S.C. sections or Texas Health & Safety Code). Supports two modes - (A) text-only briefing for structural analysis, and (B) scenario-driven briefing that applies statutory provisions to specific facts.

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。

Post-hoc verification and trust audit of AI-generated factual and interpretive claims. Classifies claims by type and salience, routes them to domain-appropriate sources, scores trustworthiness on a tiered scale with an Interpolated verdict for plausible-but-unsupported detail, and assesses rhetorical fairness on interpretive claims. Designed for clinical-negligence and healthcare-law practice in England and Wales, with general applicability beyond.

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 this skill whenever a lawyer or mediator needs help analyzing a dispute for mediation purposes. This includes: reviewing case materials (pleadings, contracts, correspondence, evidence) to identify issues in dispute, summarizing each party's position and interests, conducting legal analysis of the key issues, proposing mediation strategies or settlement directions, and preparing for mediation sessions. Trigger this skill when the user mentions 'mediation', 'dispute analysis', 'settlement', 'dispute resolution', 'identify issues in dispute', 'party positions', 'mediation brief', 'case analysis for mediation', 'ADR', 'mediation preparation', 'caucus strategy', 'settlement options', or any request to analyze a conflict between two or more parties with the goal of finding resolution. Also trigger when the user uploads case files and asks for a structured breakdown of who wants what, what the core disagreements are, or how the case might settle. Even if the user doesn't explicitly say 'mediation', trigger when the context involves analyzing opposing positions in a dispute with a resolution-oriented (rather than litigation-oriented) 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。

Adversarial premortem for England & Wales civil litigation - builds the strongest version of a case, then attacks it from four angles to find where it loses before opposing counsel does. Runs an adversarial premortem on a UK litigation matter. Builds the strongest version of the case, then attacks it from four angles — procedural, substantive, evidentiary, strategic — to find where it actually loses. Returns a ranked stress-test brief: failure scenarios, evidence inconsistencies, blind spots, mitigations, and one brutal one-sentence verdict. Use before issue, before settlement negotiations, before a litigation-funder pitch, or before deciding whether to take a case.

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。

Evaluate completed mediation-competition problems consisting of general information and confidential packets for both sides. Use when asked to validate, audit, score, quality-control, or assess competition readiness; identify factual, numerical, chronological, authority, commercial-logic, or confidentiality defects; test mediation usefulness, BATNAs, settlement corridors, information asymmetry, and opportunities for firmness, cooperation, imagination, and clarification; or produce an author-only validation report. Perform a qualified partial review when packets are missing. Diagnose by default; do not generate a new problem or edit source packets unless repairs are expressly requested. Requires access to all supplied files and a host capable of reading their formats; otherwise disclose the unreviewed material and resulting limits.

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。