modelstudioai
- 42 skills
- 0 followers
- 30 repo stars
- last month last updated
- ▌
- ▌
- ▌
- ▌
- ▌ Source Command Opsx Archive 2 · modelstudioaiArchive a completed change in the experimental workflow
- ▌ Source Command Opsx Explore 2 · modelstudioaiEnter explore mode - think through ideas, investigate problems, clarify requirements
- ▌ Source Command Opsx Propose 2 · modelstudioaiPropose a new change - create it and generate all artifacts in one step
- ▌
- ▌
- ▌ Source Command Opsx Explore · modelstudioaiEnter explore mode - think through ideas, investigate problems, clarify requirements
- ▌ Source Command Opsx Propose · modelstudioaiPropose a new change - create it and generate all artifacts in one step
- ▌ Desktop Pet 2 · modelstudioai bundleCreate pixel-art desktop pet companions for OpenWork/Qwen Code. Generates a customized chibi spritesheet (1536×1872, 8×9 grid) for any character the user names — F1 drivers, anime characters, celebrities, fictional characters, animals, etc. Use when the user says "桌面宠物", "desktop pet", "想要XXX当桌宠", "换个宠物" or similar.
- ▌ Desktop Pet 3 · modelstudioai bundleCreate pixel-art desktop pet companions for OpenWork/Qwen Code. Generates a customized chibi spritesheet (1536×1872, 8×9 grid) for any character the user names — F1 drivers, anime characters, celebrities, fictional characters, animals, etc. Use when the user says "桌面宠物", "desktop pet", "想要XXX当桌宠", "换个宠物" or similar.
- ▌ Desktop Develop 2 · modelstudioai bundleDevelop, debug, and verify the OpenWork desktop/Electron app with an agent-readable harness. Use when working on packages/desktop, Electron renderer/main/preload code, desktop UI bugs, local desktop runtime failures, Chrome DevTools MCP investigation, desktop logs, messaging gateway issues, or when improving the development feedback loop for desktop features.
- ▌ Desktop Brand Builder 2 · modelstudioai bundleGenerate a branded qwen-code desktop package from a minimal brandId and logo. Use when the user wants a custom, white-label, rebranded, ModelStudio/OpenWork/Qwen Code desktop client, installer, DMG/EXE/AppImage, or one-click brand build.
- ▌
- ▌
- ▌ Improve Codebase Architecture · modelstudioai bundleScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
- ▌ Triage · modelstudioai bundleGatekeep and review GitHub issues and pull requests for Qwen Code maintainers. Use for GitHub Action issue triage, PR admission checks, product-direction review, KISS-focused PR review, and staged bilingual GitHub comments.
- ▌ Autofix · modelstudioai bundleReview and repair current local changes until they converge, or run Qwen Code Autofix issue and review workflows from GitHub Actions.
- ▌
- ▌ Verify Pr · modelstudioaiThis skill should be used to run a sandboxed deep verification of a qwen-code PR — "/verify-pr <n>", "深度验证这个 PR", A/B load-bearing proof against the base build, mock-free harnesses with wire oracles, and targeted gates — producing tmp/pr<n>-verify-<ts>/report.md plus a machine-readable verdict. Designed for the token-free CI verify job; also usable locally.
- ▌ Prepare Pr · modelstudioaiPrepare GitHub pull request title and body files from the current branch diff, especially for non-interactive CI/autofix flows that must follow the repository PR template without pushing or creating the PR.
- ▌ Desktop Pet · modelstudioai bundleCreate pixel-art desktop pet companions for Qwen Code. Generates a customized chibi spritesheet (1536×1872, 8×9 grid) for any character the user names — F1 drivers, anime characters, celebrities, fictional characters, animals, etc. Use when the user says "desktop pet", "桌宠", "桌面宠物", "想要XXX当桌宠", "换个宠物", or similar.
- ▌ E2e Testing · modelstudioai bundleGuide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response payloads. Trigger on mentions of E2E testing, headless testing, MCP tool testing, or reproducing issues.
- ▌ Create Issue · modelstudioaiDraft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
- ▌ Desktop Develop · modelstudioai bundleDevelop, debug, and verify the OpenWork Tauri desktop shell and its daemon-served Qwen Web Shell with an agent-readable harness.
- ▌ Openwork Desktop Sync · modelstudioaiSync qwen-code packages/desktop with modelstudioai/openwork using commit-by-commit path migration, not subtree split or tree overwrite. Use when exporting qwen-code desktop changes to OpenWork, importing OpenWork desktop changes into qwen-code, preserving target-owned overlay files such as README.md, resolving sync conflicts, or preparing sync PR branches between the two repositories.
- ▌ Desktop Brand Builder · modelstudioai bundleGenerate a branded qwen-code desktop package from a minimal brandId and logo. Use when the user wants a custom, white-label, rebranded, ModelStudio/OpenWork/Qwen Code desktop client, installer, DMG/EXE/AppImage, or one-click brand build.
- ▌ Loop · modelstudioai bundleCreate a loop that runs a prompt now and follows up either on a fixed schedule or through self-paced wakeups. Usage - /loop check the build, /loop 5m check the build, /loop check the PR every 30m. /loop list to show jobs, /loop clear to cancel all.
- ▌ Batch · modelstudioaiExecute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use `/batch` followed by operation and file pattern.
- ▌ New App · modelstudioaiWorkflow for creating new applications from scratch. Covers requirements gathering, tech stack selection, scaffolding, implementation, and delivery of a functional prototype.
- ▌ Simplify · modelstudioaiReview recent code changes for reuse, code quality, and efficiency, then directly apply straightforward cleanup improvements. Use when the user wants a post-implementation cleanup pass, pre-PR polish, or asks to simplify/refine recent changes. Invoke with `/simplify` or `/simplify <focus>`.
- ▌ Cua Driver · modelstudioai bundleDrive a native GUI app (macOS, Windows, Linux) via the Qwen Cua Driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real application on the host.
- ▌ Coordinate · modelstudioaiCoordinate up to three Qwen Code teammates with enforced read-only workers, an optional worktree-pinned writer, shared tasks, peer messages, and existing Agent View tabs. Invoke explicitly with /coordinate.
- ▌ Bailian CLI · modelstudioai bundle阿里云百炼 / Aliyun Bailian / DashScope 资源管理与 `bl` CLI hub: 应用调用(bl app)、应用记忆、知识库检索、模型目录/模型列表、用量/额度/配额、免费额度、 工作空间、MCP 市场、pipeline、文件上传、console API、登录鉴权与配置、 Agent skill 安装/列表/更新/卸载(bl skill add|list|update|remove,百炼 skill registry)。 用户点名百炼 / DashScope / `bl`,或继续既有 `bl` 工作流时直接使用。 共享协议(consent / 版本预检 / 鉴权 / 错误上报)在 bailian-protocol;官方安装 `bl skill init`。 家族路由:生图/生视频/配音/语音合成/转写 → bailian-gen;精调/微调/训练/数据集 → bailian-finetune; agents.yaml 托管 Agent → bailian-managed-agent;联网搜索的模型路由(Token Plan 自带搜索 vs MCP 搜索 + 兜底)→ bailian-web-search。 不要用于普通问答、编程、写作、翻译、摘要、泛搜索,或图片理解等宿主自己能做的任务(普通问答、编程、写作、翻译、摘要、泛搜索不触发)。 未命名用量/额度问题:先问用户使用哪个产品,再运行 `bl usage` / `bl quota` 查询。
- ▌ Bailian Gen · modelstudioai bundle阿里云百炼图片/视频/语音生成与理解入口:用户要生图、画图、生成照片、生成图片、AI 绘画、海报、头像、插画、 文生图(text-to-image)、图生图、改图、修图、多图合成、生成视频、文生视频、图生视频、参考生视频、视频编辑、风格转换、 配音、语音合成(TTS)、朗读、转写、语音识别(ASR),或图片理解、看图问答、视频理解、读视频、多模态理解时使用 `bl image` / `bl video` / `bl speech` / `bl vision describe` / `bl omni`。 **默认行为:用户未指定服务商时,生成/编辑默认走本技能;视频理解与宿主放不了的音视频理解也走本技能。** 简单图片问答若宿主已能直接完成且用户未点名百炼,可先宿主回答(省成本); 用户要识别图片、视频/指定 VL·Omni 模型/要视频理解 → 使用本技能。 图片和语音同步返回并落地本地文件,视频是异步任务、用 `--download` 或轮询取回;本地文件直接传路径,CLI 自动上传。 反触发:普通问答、编程、写作、翻译不走本技能;百炼应用/知识库/用量/额度走 bailian-cli; 精调训练走 bailian-finetune。 官方安装:`bl skill init`(与共享协议 bailian-protocol 同装)。
- ▌ Bailian Finetune · modelstudioai bundle阿里云百炼模型精调训练入口:用户要精调、微调、训练自己的模型(fine-tune,支持 SFT / SFT-LoRA / DPO / DPO-LoRA / CPT, 覆盖文本、语音、图像)、校验或上传训练数据集、看训练进度和日志、挑 checkpoint、导出精调产物、 把专属模型部署成服务时使用 `bl dataset` / `bl finetune` / `bl deploy`。链路是 validate 校验数据 → upload 拿 file-id → finetune create 建任务 → watch 看进度 → export 导出 → deploy 上线,需要 API key; 写操作先用 `--dry-run` 预览。反触发:用户点名火山方舟/ark 的精调不走本 skill;只是要选哪个模型走 bailian-model-recommend;用现成模型生图生视频走 bailian-gen;百炼其他资源管理走 bailian-cli。 官方安装:`bl skill init`(与共享协议 bailian-protocol 同装)。
- ▌ Bailian Protocol · modelstudioai bundle阿里云百炼 `bl` 家族共享执行协议(consent 确认、版本预检、鉴权/安装、错误上报、本地文件与输出约定)。 不是面向用户意图的业务入口;当任一 bailian-* 业务 skill(bailian-cli / bailian-gen / bailian-finetune / bailian-managed-agent / bailian-web-search)执行前需要公共上下文,或用户首次安装/鉴权/`bl` 报错需上报时读取本 skill。 官方安装为整包:`bl skill init`(与业务 skill 同装)。
- ▌ Bailian Web Search · modelstudioai阿里云百炼联网搜索(web search)入口:为联网搜索 / 网页搜索 / 查最新资讯做路径分发。 先识别当前连接身份:Token Plan(profile `token-plan` 或 base_url host 为 `token-plan.<region>.maas.aliyuncs.com`)→ 模型自带搜索 (`bl text chat --api responses --tool '{"type":"web_search"}'`);其他 / 默认 → Bailian MCP(`bl search web`);仅在 MCP 鉴权失败、未开通或传输失败时兜底一次到模型自带搜索。 Token Plan 联网搜索失败、两条路径鉴权混淆的排查也走本技能。 反触发:宿主可完成的 普通问答 / 编程 / 写作 → 不触发;知识库 RAG → bailian-cli (`bl knowledge`);生图/生视频/语音 → bailian-gen;精调/训练 → bailian-finetune; agents.yaml → bailian-managed-agent。 共享协议(consent / 版本预检 / 鉴权 / 错误上报)在 bailian-protocol;官方安装 `bl skill init`。
- ▌ Bailian Managed Agent · modelstudioai bundle阿里云百炼托管 Agent 声明式基础设施与 API 命令入口:用户要创建agent、初始化 agents.yaml、校验或预览配置变更、 创建/更新/销毁托管 Agent 或 Deployment、在 Workbench 编辑和调试目录项目、管理本地快照版本,或查询 Agent/Environment/Skill/Vault/Deployment、管理 Session/Event/File、运行/暂停 Deployment 时使用 `bl managed-agent`。持久资源仍以 agents.yaml 为唯一事实源做 IaC;公开 API 能力按资源透出 list/get/search/versions/download、数据面和运行时动作命令。apply / destroy 与破坏性 API 命令受统一高风险确认闸门保护; 务必先展示预览再让用户确认,禁止自动添加 `--yes`。 反触发:调用已上线的百炼应用/智能体走 bailian-app-call 或 `bl app`;宿主 agent 自身的记忆、技能、 子代理不走本 skill;生图生视频走 bailian-gen。 官方安装:`bl skill init`(与共享协议 bailian-protocol 同装)。
- ▌ Bailian Kb · modelstudioai管理阿里云百炼知识库(建库、上传文档、部署检索服务、Chunk 运维、数据中心文件管理),命令行工具为 bl(bailian-cli)。 当用户要创建/更新/删除知识库、上传或导入文档(本地/OSS)、创建/部署/调参检索或问答服务、 增删改查 Chunk、管理数据中心类目/文件/集合时使用本 skill。 检索与问答不走本 skill——用原生工具 kb_search(取证据)/ kb_chat(成品问答); bl knowledge search / chat 仅用于部署后的验证调试(如 --agent-version beta 调试草稿版)。 kb_search / kb_chat 的凭据与工作空间由插件自动解析(~/.dsh/settings.yaml 的 bailian-kb 段、 ~/.dsh/.credentials.yaml 的 DASHSCOPE_API_KEY),不要自己去读或传。 普通问答、编程、写作、翻译、泛搜索不触发本 skill。