zhu1090093659

Automates pre-development workflow for large-scale complex tasks. Use when the user mentions "rewrite", "migrate", "overhaul", "refactor entire project", "transform", "rebuild in [language]", "spec-driven", or describes any large-scale project transformation…

结构化深度讨论 Skill，用于与用户进行多轮问题分析和方案设计。当用户描述一个问题现象、故障表现、 技术困惑、方案选择困难，或明确说"讨论一下"、"帮我分析"、"我遇到一个问题"、"你觉得怎么样"、 "帮我想想"、"我在纠结"时，必须使用本 skill。当用户提供了一段描述（可能附带截图）并期望深入分析 而非直接给答案时，也应触发本 skill。即使用户只是抛出一个现象描述没有明确提问，也要使用本 skill 来引导结构化思考。不要在简单的事实查询（"X是什么"）或明确的执行指令（"帮我写个脚本"）上触发。

Findings-first code review workflow for AI coding agents. Use when the user asks to review uncommitted changes, commits in a date range, or a branch compared to the main branch / PR-style diff. Focuses on bugs, regressions, correctness risks, missing tests,…

Automates pre-development workflow for large-scale complex tasks. Use when the user mentions "rewrite", "migrate", "overhaul", "refactor entire project", "transform", "rebuild in [language]", "spec-driven", or describes any large-scale project transformation…

Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.

3D Morph PPT — extends morph-ppt with GLB model insertion, cinematographic camera, model-content layout, and enriched visual design system.

Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition',…

Use this skill to build academic-style .docx output: journal / conference / thesis chapters carrying formal citation style (APA, Chicago, IEEE, MLA), numbered equations, figure & table cross-references, footnotes/endnotes, bibliography, or multi-column…

Release and publish the dsh-web monorepo (DSH Web GUI plugin family + skin collection) — bump all packages to one unified version, commit and tag (tags are cut from main after dev integration; dev is the integration branch), push the vX.Y.Z tag that triggers…

Safely select and install a compatible official @deepseek-ai SDK release for dsh plugin projects (dsh-web, dsh-trading, and similar monorepos) from npm using an isolated worktree, explicit cohort review, CI-equivalent validation, and controlled rollout —…

Use for an implementation, maintenance, or configuration task in the dsh-web monorepo. Establishes the project-specific Agent Coding workflow and routes to focused skills.

Use before pushing, opening or updating a pull request, or claiming dsh-web checks pass. Selects the required repository gates and diff-specific generation, build, and GUI evidence.

Adapt and repair dsh-web after an approved official @deepseek-ai SDK/runtime cohort is selected or installed. Compare public API, type, service-injection, module-table, protocol, and behavior changes; map every change to repository consumers; implement the…

Develop a DSH community plugin and register it in the dsh-web Community Plugins index — author the plugin in the contributor's own repository following the official cordis bundle standard, add its entry to packages/dsh-community-plugins/community.json,…

Build a new skin for the dsh-web skin collection (DSH Web GUI) and publish it into the Skin Center — the first-level settings section — scaffold with scripts/dsh-skin-new, author the v2 skin.json manifest plus skin.css token remap (pure asset directory, no…

Use when reviewing uncommitted changes, a branch, or a pull request for dsh-web. Focuses on correctness, plugin boundaries, browser behavior, security, generated artifacts, and missing evidence.

Interactive assistant creator for CodeConductor. Use when users want to create a new custom assistant, design an AI persona, or configure a specialized helper. Triggers on: "create an assistant", "make a new helper", "design an AI that...", "I need an…

Browser automation via the agent-browser CLI for navigation, interaction, snapshots, extraction, screenshots, network controls, storage, tabs, frames, and debugging. Use when tasks require automated web UI actions, form filling, scraping, state capture, or…

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying…

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other…

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

抽象升级 skill。当用户的代码/设计已经 work 了，但感觉结构不够好、想问"还有没有更好的抽象"、"要不要重构"、"这里是不是该提取一个 xxx"、"这段结构有点怪"、"好像重复了"、"这个设计是不是还能更简洁"时，必须使用本 skill。本 skill 不直接给重构方案，而是逼用户自己看清当前抽象的问题、识别更深层的结构模式、判断升级方向是否值得。注意：抽象升级有时意味着**增加**一层，有时意味着**删掉**一层——本 skill…

意图精炼 skill。当用户描述一个想做的事但表述模糊、想定义一个需求/spec、在纠结某个目标怎么表达、说"我想做个 XX"、"帮我定义一下 XX"、"我要实现的是 XX"、"我的目标是 XX"、"这个需求应该怎么写"时，必须使用本 skill。本 skill 不帮用户写需求，而是通过逼问把用户模糊的意图炼成精确、可验证、无歧义的一句话 spec。适用于做产品需求、定义 skill、写 API 合约、设计实验、制定个人目标等场景。不要在用户已经提供了清晰 spec 并要求执行的场景下触发。

判断红队 skill。当用户做出某个决策、倾向某个方案、要下判断、说"我决定做 X"、"我觉得应该 Y"、"我想选 Z"、"我的判断是……"、"我要 xxx 了"时，必须使用本 skill。本 skill 不帮用户做判断，而是扮演最锋利的反对者，系统性攻击用户的决策，逼用户看清自己的盲点、前提漏洞、失败场景。适用于技术选型、架构决策、职业选择、投资决定、产品方向等一切需要下注的场景。不要在用户只是在征求信息（"X 是什么"）或明确请求 Claude 给建议的场景下触发。

品味审查 skill。当用户展示一段代码、一个设计、一个架构方案、一个 API，或者一段文字内容（文档、文案、邮件），并想判断"这东西好不好"、"是不是还能更优雅"、"有没有哪里丑"时，必须使用本 skill。当用户说"你帮我看看这个"、"这样写对吗"、"有没有更好的写法"、"这个设计怎么样"时，也应触发。本 skill 不给评价，不给答案——它只问问题，逼用户自己看出美丑。不要在用户明确要求"直接给建议"或"帮我写"的场景下触发。

Automates pre-development workflow for large-scale complex tasks. Use when the user mentions "rewrite", "migrate", "overhaul", "refactor entire project", "transform", "rebuild in [language]", "spec-driven", or describes any large-scale project transformation…

结构化深度讨论 Skill，用于与用户进行多轮问题分析和方案设计。当用户描述一个问题现象、故障表现、 技术困惑、方案选择困难，或明确说"讨论一下"、"帮我分析"、"我遇到一个问题"、"你觉得怎么样"、 "帮我想想"、"我在纠结"时，必须使用本 skill。当用户提供了一段描述（可能附带截图）并期望深入分析 而非直接给答案时，也应触发本 skill。即使用户只是抛出一个现象描述没有明确提问，也要使用本 skill 来引导结构化思考。不要在简单的事实查询（"X是什么"）或明确的执行指令（"帮我写个脚本"）上触发。

Findings-first code review workflow for AI coding agents. Use when the user asks to review uncommitted changes, commits in a date range, or a branch compared to the main branch / PR-style diff. Focuses on bugs, regressions, correctness risks, missing tests,…