AgentScope-AI

Use when the user has changed a prompt (system prompt, RAG template, agent instruction, etc.) and wants to know whether the candidate is better or worse than the baseline. Also use when the user mentions prompt A/B testing, prompt comparison, prompt optimization validation, "did my prompt change help," or prompt regression testing. Outputs per-dimension win rates with statistical significance using OpenJudge PairwiseAnalyzer.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build custom LLM evaluation pipelines using the OpenJudge framework. Covers selecting and configuring graders (LLM-based, function-based, agentic), running batch evaluations with GradingRunner, combining scores with aggregators, applying evaluation strategies (voting, average), auto-generating graders from data, and analyzing results (pairwise win rates, statistics, validation metrics). Use when the user wants to evaluate LLM outputs, compare multiple models, design scoring criteria, or build an automated evaluation system.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win rate across group rollouts); generating preference pairs for DPO/RLAIF; and normalizing scores for training stability. Use when building reward models, scoring rollouts for GRPO/REINFORCE, generating preference data for DPO, or doing Best-of-N selection.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when the user has a judge/grader and human-labeled data, and wants to measure how well the judge agrees with humans, detect systematic biases, determine whether automatic evaluation can replace human review, or build a human-reduction roadmap. Also use when the user mentions calibration, TPR/TNR, judge validation, inter-rater agreement, Cohen's kappa, bias detection, or "is my automatic evaluation trustworthy." Merges the calibrate and align functions into one skill.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when the user has nothing — no traces, no labels, no eval set — and needs to build a v0 evaluation from scratch. Also use when the user says "I need to start evaluating my app but don't know where to begin," "I want to set up eval for a new product," or has just identified failure modes and needs to turn them into principles. Outputs a v0 grader in 30 minutes using OpenJudge SimpleRubricsGenerator, plus a roadmap to reach calibrated evaluation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Generates English pull request titles and bodies by comparing the current branch with main. Use when the user asks to draft PR content, summarize branch changes, or produce a PR title/body from git diff.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Guidelines for handling CSV/Excel files

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Guidelines for handling image files

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Guildlines for handling json files

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Guidelines for handling databases

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Guidelines for handling text files

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

从运营周报、活动文档、对话输入或文档工具 API 中提取业务事件，与指标异常时间窗口对齐，生成有证据支撑的因果归因假设并排序。当已知指标存在异常波动、需要从外部文档证据中解释"为什么"时调用。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

对用户、产品等业务对象做分群：用波士顿矩阵法做象限分群，或用分层聚类、K-means、DBSCAN 等聚类技术分群。当需要做客群/产品分群、象限策略、画像或密度型子结构发现时调用。触发条件：当对话中出现“分群”、“分类”、“聚类”、“不同类型”、“不同场景”等体现分群分析词语时触发。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

对不同时间、群体、地区、渠道、版本之间的指标差异性的定量分析。触发条件：当分析任务需要通过定量比较多个对象来进行分析时触发，例如，对话包含“分析差异”、“衡量增长/下降”、“评估优劣/一致性“、“对比“等相似词语时触发。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

从接触目标行为到完成目标行为的转化率计算。触发条件：需计算转化率时触发，如对话包含“转化率”、“转化情况”等词时触发。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

将 BI 数据分析结果构建为可筛选的交互式 HTML 看板。触发条件：① 用户显式要求「给我看板」时无条件触发；② 取数结果满足以下任一时自动触发——结果集行数>10行、存在可筛选维度（产品线/地域/时间粒度等）、涉及多张表数据、时序跨度长。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

对指标按维度逐层下拆，通过单维度扫描、交叉分析和层级下钻定位关键维度（组）值。当需要知道"从哪些维度拆解、按什么顺序拆解来定位指标变动来源"时调用。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.