By agentscope-ai

Guidance for writing and testing Terraform and OpenTofu code: module structure, naming, test approaches, CI/CD workflows, state handling and security scanning.

agentscope-ai/QwenPaw

Turns reusable decisions, templates or workflows from the current conversation into a new workspace skill through plan, approval, draft, validation and publication.

agentscope-ai/QwenPaw

Creates a focused workspace skill from the current conversation in QwenPaw, moving through a planning, approval, drafting, validation and publishing script pipeline.

agentscope-ai/QwenPaw

钉钉消息发送技能。支持企业内部机器人（批量单聊/群聊）和 Webhook 自定义机器人两种接入方式，支持多机器人管理，支持文本、Markdown、链接、ActionCard、FeedCard等多种消息类型。

agentscope-ai/ReMe

Creates and manages scheduled or recurring jobs with the qwenpaw cron commands, always tied to an explicit agent ID and a confirmed target channel.

agentscope-ai/QwenPaw

Search the public web through Serper instead of the built-in WebSearch tool.

agentscope-ai/ReMe

Creates, reads and edits Word .docx files, including tracked changes and comments, using docx-js for new files and XML editing for existing ones.

agentscope-ai/QwenPaw

Generates English pull request titles and bodies by comparing the current branch with main.

agentscope-ai/agentscope-spark-design

A skill your agent uses 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…

agentscope-ai/OpenJudge

Connects, registers, and operates a personal mailbox, reading, searching, sending, and organizing, through a managed mail server for nine domains.

agentscope-ai/QwenPaw

Use ReMe as file-native long-term memory in Claude Code. An agent skill from agentscope-ai/ReMe.

agentscope-ai/ReMe

Gives the allowed_tools and skills preset for each OMP sub-agent role, to apply when calling spawn_subagent.

agentscope-ai/QwenPaw

A skill your agent uses 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.

agentscope-ai/OpenJudge

Handles PDF tasks with Python libraries and command-line tools: extract text and tables, merge, split, rotate, create, fill forms and more.

agentscope-ai/QwenPaw

A skill your agent uses when the user has a RAG (Retrieval-Augmented Generation) system and wants to evaluate its quality — separating retrieval issues from generation issues.

agentscope-ai/OpenJudge

Chinese-language guide for reading, editing and building PowerPoint decks: text extraction, template editing and from-scratch creation with pptxgenjs.

agentscope-ai/QwenPaw

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.

agentscope-ai/OpenJudge

将 BI 数据分析结果组织成可视化 HTML 报告。当分析完成、需要生成报告时调用. An agent skill from agentscope-ai/QwenPaw-Data.

agentscope-ai/QwenPaw-Data

A skill your agent uses when the user needs to design evaluation datasets, create test cases, stratify samples, generate adversarial examples, extract eval dimensions from traces/specs, or build a…

agentscope-ai/OpenJudge

Detects whether Terraform is installed, installs it with the right method for macOS or Linux, then runs and verifies terraform init, leaving provider credentials to a separate skill.

agentscope-ai/QwenPaw

取数 / 查数据 / 拉数据 / 跑 SQL。把自然语言取数需求转为 SQL，经数据湖仓执行后返回查询结果供下游分析。任何需要业务数据的任务在工作区缺少对应文件时都必须先调用此技能——覆盖 BI 业务分析、留存 / 转化 / 同期群分析、数据探索 EDA、统计建模、定量计算、元数据查询、数据查询。命中任一即触发：(1) 直接索要指标或记录，如「DAU 多少」「上月销售额」「3…

agentscope-ai/QwenPaw-Data

Creates, edits, cleans and analyzes Excel and CSV files with openpyxl and pandas, recalculating formulas through LibreOffice so files are delivered without formula errors.

agentscope-ai/QwenPaw

Build and debug Python applications using AgentScope 2.x. An agent skill from agentscope-ai/skills.

agentscope-ai/skills

Chinese-language guide to creating and managing scheduled or recurring tasks with the qwenpaw cron commands, always with an explicit agent id.

agentscope-ai/QwenPaw

通过 IMAP/SMTP 管理邮件的命令行工具。使用 himalaya 可以在终端中列出、阅读、撰写、回复、转发、搜索和整理邮件。支持多账户和使用 MML（MIME Meta Language）撰写邮件。

agentscope-ai/skills

通过量化历史数据的自然波动幅度，自适应计算判定阈值。当需要从数据本身确定阈值（如波动阈值、影响度阈值等）、而非使用固定值时调用。仅适用于日/周粒度阈值确定。

agentscope-ai/QwenPaw-Data

Discover and recommend combinations of agent skills to complete complex, multi-faceted tasks.

agentscope-ai/OpenJudge

A skill your agent uses 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…

agentscope-ai/OpenJudge

Answers questions about installing and configuring QwenPaw by locating and reading its local documentation first, with the official website as a fallback.

agentscope-ai/QwenPaw

Chinese-language edition of the QwenPaw setup Q&A skill: it checks local docs before answering, replies in the asker's language and falls back to the official site.

agentscope-ai/QwenPaw

Single entry point for email tasks in QwenPaw through qwenpawmail-mcp: read, search, send, reply, organize, and bind or register a personal mailbox.

agentscope-ai/QwenPaw

基于阈值检测时间序列中的显著异常波动点。当需要找出指标异常波动日期、识别数据异动时调用. An agent skill from agentscope-ai/QwenPaw-Data.

agentscope-ai/QwenPaw-Data

A skill your agent uses 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…

agentscope-ai/OpenJudge

Drives a live browser with async Python through QwenPaw's built-in Browser SDK, in a perceive, act, verify loop with handoff for logins and captchas.

agentscope-ai/QwenPaw

Chinese-language edition of the QwenPaw browser skill: async Python control of a live browser with a perceive, act, verify loop and human handoff.

agentscope-ai/QwenPaw

Domain guidance for turning one math problem into a step-by-step explainer video in Chinese, with scene timing, narration rules and KaTeX-style layout.

agentscope-ai/QwenPaw

Compiles production-grade prompts for character identity boards, cinematic storyboards and reference-to-video generation, keeping characters and shots consistent.

agentscope-ai/QwenPaw

Guides writing and repairing image prompts for character, scene and prop reference sheets, including layout, camera language and continuity across variants.

agentscope-ai/QwenPaw

计算各维度（组）值对指标变动的贡献度，支持可加型量值指标和加权平均型/率值指标。当需要计算贡献度、解释指标"为什么涨/跌"时调用。

agentscope-ai/QwenPaw-Data

Automatically evaluate and compare multiple AI models or agents without pre-existing test data.

agentscope-ai/OpenJudge

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。

agentscope-ai/QwenPaw-Data

Build custom LLM evaluation pipelines using the OpenJudge framework.

agentscope-ai/OpenJudge

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。

agentscope-ai/QwenPaw-Data

Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline.

agentscope-ai/OpenJudge

为用户从指定新闻网站查找最新新闻。提供政治、财经、社会、国际、科技、体育和娱乐类别的权威 URL。使用 browseruse 打开每个 URL 并通过 snapshot 获取内容，然后为用户总结。

agentscope-ai/skills

分析观测数据在不同区间维度上的分布特征。触发条件：当任务强调数据分布特征分析时调用，如出现“数据分布”、“分布情况”等词时触发。

agentscope-ai/QwenPaw-Data

Verify a BibTeX file for hallucinated or fabricated references by cross-checking every entry against CrossRef, arXiv, and DBLP.

agentscope-ai/OpenJudge

Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP.

agentscope-ai/OpenJudge