Skip to main content
agentscope-ai
Perfil de creador de GitHub

agentscope-ai

Vista por repositorio de 223 skills recopiladas en 11 repositorios de GitHub.

skills recopiladas
223
repositorios
11
actualizado
11 oct 2026
mapa de repositorios

Dónde viven las skills

Repositorios principales por número de skills recopiladas, con su participación en este catálogo del creador y su variedad ocupacional.

#01
AgentTeams
60 skills · 11 oct 2026
Otras ocupaciones informáticasDesarrolladores de softwareAdministradores de redes y sistemas informáticosEspecialistas en gestión de proyectosAnalistas de garantía de calidad de software y probadores
5 categorías ocupacionales · 97 % clasificado
27 %participación
#02
QwenPaw
48 skills · 22 sept 2026
Desarrolladores de softwareOtras ocupaciones informáticasEditores de escritorioEmpleados de oficina generalesDiseñadores gráficosAdministradores de redes y sistemas informáticos
10 categorías ocupacionales · 98 % clasificado
22 %participación
#03
QwenPaw-Data
32 skills · 9 sept 2026
Científicos de datosDesarrolladores de softwareAnalistas de investigación de mercados y especialistas en marketingDesarrolladores webEspecialistas en gestión de proyectosOtras ocupaciones informáticas
6 categorías ocupacionales · 100 % clasificado
14 %participación
#04
agentscope-java
21 skills · 11 oct 2026
Desarrolladores de softwareCientíficos de datosEmpleados de oficina generalesAdministradores de redes y sistemas informáticosAnalistas de garantía de calidad de software y probadoresOtras ocupaciones informáticas
7 categorías ocupacionales · 90 % clasificado
9,4 %participación
#05
OpenJudge
21 skills · 11 sept 2026
Científicos de datosDesarrolladores de softwareOtras ocupaciones informáticasProfesores postsecundarios, todos los demásAnalistas de garantía de calidad de software y probadoresAnalistas de seguridad de la información
6 categorías ocupacionales · 100 % clasificado
9,4 %participación
#06
skills
18 skills · 10 sept 2026
Desarrolladores de softwareEmpleados de oficina generalesOtras ocupaciones informáticas
3 categorías ocupacionales · 100 % clasificado
8,1 %participación
#07
PawBench
9 skills · 19 may 2026
Desarrolladores de softwareEditores de escritorioCientíficos de datosDiseñadores gráficosRedactores técnicosTecnólogos y técnicos en ingeniería mecánica
6 categorías ocupacionales · 100 % clasificado
4 %participación
#08
ReMe
6 skills · 7 sept 2026
Desarrolladores de softwareOtras ocupaciones informáticasAdministradores de redes y sistemas informáticosAnalistas financieros y de inversiones
4 categorías ocupacionales · 100 % clasificado
2,7 %participación
Aquí se muestran los 8 repositorios principales; la lista completa continúa abajo.
explorador de repositorios

Repositorios y skills representativas

mcp-server-management
Administradores de redes y sistemas informáticos

Use when admin asks to configure an MCP tool server (e.g., GitHub, weather API), rotate credentials, grant/revoke worker access to MCP tools, or add a custom API integration via YAML.

11 oct 2026
model-switch
sin clasificar

Switch the Manager Agent's own LLM model. Use when the human admin requests changing the Manager's model.

10 oct 2026
agentteams-find-worker
Otras ocupaciones informáticas

Use as a helper when the admin is assigning work but has not specified an existing Worker, so you need to search Nacos for a suitable Worker and ask whether to import it; also use when the admin explicitly says to import a Worker from the market or gives a…

8 oct 2026
worker-management
sin clasificar

Use when admin requests hand-creating or resetting a Worker, starting/stopping a Worker, managing Worker skills, enabling peer mentions, or opening a QwenPaw console. Use agentteams-find-worker only as a helper for Nacos-backed market import or when task…

8 oct 2026
project-management
Otras ocupaciones informáticas

Use when admin asks to start a multi-worker project, when a Worker @mentions you with task completion in a project room, when project plan changes are needed, or when a blocked task needs resolution.

18 sept 2026
teamharness-task-execution
Especialistas en gestión de proyectos

Use when you act as Worker: receive TASK_ASSIGNED, acknowledge the task, work inside shared/tasks/{task-id}/, submit with taskflow submit_task, publish deliverables through submit_task, and report TASK_COMPLETED or blockers in the Task room.

16 sept 2026
teamharness-project-management
Especialistas en gestión de proyectos

Use when you act as Leader and maintain durable TeamHarness project state for Quick Task or Project Work: create_quick_project, create_project, plan_dag, plan_loop, ready_nodes, resolve_project, accept_task_result, project completion, and requester report…

15 sept 2026
teamharness-task-delegation
Especialistas en gestión de proyectos

Use when you act as Leader to turn ready Quick Task or Project Work state into Worker task instructions, send assignment messages, check submitted results, and define completion/blocker report contracts. Do not use to create projects, create rooms, or execute…

15 sept 2026
Mostrando 8 de 60 skills recopiladas.
omp-roles
sin clasificar

Use this skill whenever you need the allowed_tools / skills preset for a sub-agent role before calling spawn_subagent. Trigger especially when user mentions: "role", "spawn_subagent", "allowed_tools", or any OMP role name (executor, architect, analyst,…

22 sept 2026
professional-media-prompts
Técnicos de audio y video

为 Creator 编译制作级视觉资产图、电影分镜图和参考生视频 Prompt。适用于 角色身份板/设定图、关键帧或多宫格分镜、短片动作节拍、R2V/I2V/T2V 提示词, 尤其适合要求角色一致性、镜头语言、参考图职责、Seedance 时间段或声音设计的 任务。不用于纯素材剪辑、只查询模型参数,或只评价已经生成的成片。

17 sept 2026
visual-asset-design
Diseñadores gráficos

为角色/场景/道具设计视觉资产、编写或修复 VisualVariant 与阵容图的生成 Prompt 时使用。涵盖参考图布局(艺术身份板/序列关键帧/环境研究板/道具研究 板)、构图与镜头语言、图片审核误判规避、实体 continuity 与以主图为参考 的跨 Variant 衍生设计。不用于视频 Prompt 编译(见 professional-media-prompts)、 纯素材剪辑或只评价已生成产物。

17 sept 2026
make-skill
Otras ocupaciones informáticas

Create a focused workspace Skill from reusable decisions, knowledge, templates, or workflows in the current conversation. Use for /make-skill with a focus argument and requests such as save this workflow or turn this into a skill; do not use for one-off…

15 sept 2026
make-skill
Desarrolladores de software

将当前对话中可复用的决策、知识、模板或工作流创建为聚焦的 workspace Skill。适用于带 focus 参数的 /make-skill,以及“保存这个流程”“把它做成 skill”等请求;不适用于一次性总结或普通文件创建。

15 sept 2026
cron
Administradores de redes y sistemas informáticos

Use this skill only for scheduled or recurring tasks. Manage jobs with qwenpaw cron list/create/get/state/update/pause/resume/delete/run, and always pass --agent-id explicitly.

11 sept 2026
cron
Administradores de redes y sistemas informáticos

仅在需要未来定时执行或周期执行任务时,使用本 skill。使用 qwenpaw cron list/create/get/state/update/pause/resume/delete/run 管理任务,并始终显式传入 --agent-id。

11 sept 2026
building-native-ui
Desarrolladores web

Build a small native interface.

11 sept 2026
Mostrando 8 de 48 skills recopiladas.
runtime-guide
Desarrolladores de software

提供数据分析任务执行的强制性通用规范。在计划完成准备执行数据分析任务、或执行过程中涉及产物落盘、数据复用、异常处理、计划调整、质量自检时,必须优先调用此技能。

9 sept 2026
bi-report-generation
Científicos de datos

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。

9 sept 2026
analysis-plan-builder
Científicos de datos

将用户的数据分析需求转化为结构化的分析计划并与用户确认。用户提出 BI 业务分析、数据探索、统计建模等需要规划的分析任务时使用。简单数据查询、公式明确的定量计算等流程简单、无需规划的任务不使用。

9 sept 2026
bi-semantic-layer-guide
Científicos de datos

语义层工具使用规范。在发现语义层工具可用、需要查询指标定义/维度信息、验证业务口径、处理指标歧义时,必须优先调用此技能。无语义层工具时不调用。

9 sept 2026
bi-adaptive-threshold
Científicos de datos

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。

24 ago 2026
bi-anomaly-detection
Científicos de datos

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。

24 ago 2026
bi-attribution-analysis
Científicos de datos

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。

24 ago 2026
bi-causal-attribution
Analistas de investigación de mercados y especialistas en marketing

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。

24 ago 2026
Mostrando 8 de 32 skills recopiladas.
Mostrando 8 de 21 skills recopiladas.
00-academic-router
Profesores postsecundarios, todos los demás

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…

11 sept 2026
01-paper-review
Profesores postsecundarios, todos los demás

Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology,…

11 sept 2026
02-bib-verify
Profesores postsecundarios, todos los demás

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…

11 sept 2026
03-ref-hallucination-arena
Científicos de datos

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.…

11 sept 2026
00-arena-router
Otras ocupaciones informáticas

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.…

11 sept 2026
01-auto-arena
Otras ocupaciones informáticas

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…

11 sept 2026
02-ref-hallucination-arena
Científicos de datos

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.…

11 sept 2026
01-graders-and-pipeline
Analistas de garantía de calidad de software y probadores

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…

11 sept 2026
Mostrando 8 de 21 skills recopiladas.
browser-cdp
Desarrolladores de software

Use this skill when the user explicitly wants to connect to a running Chrome browser, scan local CDP ports, specify a `cdp_port`, or share a single browser across multiple agents/tools. By default, browser_use already launches the browser using managed CDP;…

10 sept 2026
browser-cdp
Desarrolladores de software

当用户明确希望连接到已运行的 Chrome 浏览器、扫描本地 CDP 端口、显式指定 `cdp_port`,或让多个 agent / 工具共享同一个浏览器时,使用本 skill。当前 browser_use 默认已使用 managed CDP 启动浏览器;如果用户不希望暴露浏览器历史、Cookies 等敏感信息,推荐改用 `private_mode=true` 的隐私模式。

10 sept 2026
browser-visible
Desarrolladores de software

Use this skill when the user needs to control the browser launch mode for browser_use. By default, browser_use launches the local Chrome/Chromium using managed CDP; `headed` controls whether the window is visible, and `private_mode` controls whether CDP is…

10 sept 2026
browser-visible
Desarrolladores de software

当用户需要控制 browser_use 的浏览器启动方式时,使用本 skill。当前 browser_use 默认使用 managed CDP 启动本地 Chrome/Chromium;`headed` 控制是否显示窗口,`private_mode` 控制是否禁用 CDP、改走 Playwright,`browser_args` 传入额外的 Chromium 启动参数,`executable_path` 指定自定义浏览器可执行文件路径。

10 sept 2026
chat-with-agent
Otras ocupaciones informáticas

Use this skill when you need to consult another agent, ask for help, or involve a specific agent the user asked for.

10 sept 2026
chat-with-agent
Otras ocupaciones informáticas

当你需要咨询其他 agent、寻求帮助,或用户明确要求某个 agent 参与时,使用本 skill。

10 sept 2026
cron
Desarrolladores de software

Use this skill only for scheduled or recurring tasks. Manage jobs with qwenpaw cron list/create/get/state/pause/resume/delete/run, and always pass --agent-id explicitly.

10 sept 2026
cron
Desarrolladores de software

仅在需要未来定时执行或周期执行任务时,使用本 skill。使用 qwenpaw cron list/create/get/state/pause/resume/delete/run 管理任务,并始终显式传入 --agent-id。

10 sept 2026
Mostrando 8 de 18 skills recopiladas.
java-audit-skill
Desarrolladores de software

AI驱动的Java代码安全审计技能,实现系统化、高覆盖率的漏洞挖掘。使用场景: (1) 审计Java/Kotlin项目寻找安全漏洞(0day挖掘、代码审计、安全评估) (2) 企业级代码库的安全审计(支持大型项目) (3) 需要高质量、低幻觉率的安全审计报告 (4) CI/CD集成的前期漏洞发现 触发关键词:Java审计、代码审计、安全审计、漏洞挖掘、0day、安全评估、Java security audit、code review for security

19 may 2026
pdf
Desarrolladores de software

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling…

19 may 2026
xlsx
Editores de escritorio

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting,…

19 may 2026
docx
Editores de escritorio

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of…

19 may 2026
pptx
Diseñadores gráficos

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used…

19 may 2026
video-script-generator
Redactores técnicos

生成短视频脚本和分镜。输入产品/主题描述、目标受众、时长,输出完整脚本+分镜结构(JSON/YAML)。支持多种模板:痛点-解决、反转剧情、before-after。触发词:视频脚本、短视频文案、分镜、storyboard、video script。

19 may 2026
dialogue-graph
Desarrolladores de software

A library for building, validating, visualizing, and serializing dialogue graphs. Use this when parsing scripts or creating branching narrative structures.

19 may 2026
reflow-machine-maintenance-guidance
Tecnólogos y técnicos en ingeniería mecánica

This skill should be considered when you need to answer reflow machine maintenance questions or provide detailed guidance based on thermocouple data, MES data or defect data and reflow technical handbooks. This skill covers how to obtain important concepts,…

19 may 2026
Mostrando 8 de 9 skills recopiladas.
reme-memory
Administradores de redes y sistemas informáticos

Set up and use ReMe as a file-native long-term memory system through the reme CLI. Use when an Agent needs to detect whether ReMe is installed or running, install and configure ReMe, start or verify its local service, retrieve prior context, or write and…

7 sept 2026
reme-memory
Otras ocupaciones informáticas

Use ReMe as file-native long-term memory in Claude Code. RECALL — search ReMe before answering questions about past conversations, preferences, project history, or decisions.

27 ago 2026
tushare-data
Analistas financieros y de inversiones

面向中文自然语言的 Tushare 数据研究技能。用于把“看看这只股票最近怎么样”“帮我查财报趋势”“最近哪个板块最强”“北向资金在买什么”“给我导出一份行情数据”这类请求,转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究场景。

25 jul 2026
dingtalk-message
Desarrolladores de software

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。

22 jul 2026
serper-search
Desarrolladores de software

Search the public web through Serper instead of the built-in WebSearch tool. Use when an agent needs current information, general web sources, or URLs not available from local files and project APIs. SERPER_API_KEY is available in the environment.

22 jul 2026
qwenpaw-memory
Otras ocupaciones informáticas

qwenpaw_memory

22 jun 2026
Mostrando 11 de 11 repositorios
Todos los repositorios cargados