forge_test-driven-development
Use when 需要以测试先行方式实现功能、修复 bug 或重构行为，严格执行 Red-Green-Refactor 循环，先写失败测试再写最小生产代码并完成重构验证。触发词：TDD、测试先行、红绿重构、先写测试。
forge_refine-trpc-best-practice
Must follow when 在 React 组件中进行数据获取，确保通过 Refine hooks（useList/useOne 等）经由 DataProvider 访问数据，禁止直接调用 trpc 客户端。
forge_storybook-best-practice
Must follow when 创建或维护 Storybook Stories，确保组件文档命名、参数定义和装饰器配置符合项目 Storybook 编写规范。
forge_generate-preview
Use when 需要对 React 组件文件生成结构化 .json 描述和可视化 .md 目录树预览，用于组件拆分前的详细结构分析、复杂度评估与规划。触发词：生成组件预览文档、拆分前分析、组件结构可视化。
forge_check-props-drilling
Use when 需要检查代码中是否存在 Props Drilling（透传 Props）问题，识别那些本应从 Zustand Store 直接获取却通过多层组件传递的数据。触发词：检查 props 透传、props drilling、消除透传、检查组件依赖。
forge_zod-infer-type-best-practice
Must follow when 项目中存在 Zod Schema 定义时，禁止重复声明可推导的业务类型；可推导类型使用 z.infer，跨层 contract 保持独立职责。
forge_writing-plans
Use when 需要将已批准的设计规格拆解为可执行实现计划，按最小任务粒度给出文件路径、完整代码、验证命令、依赖上下文和完成标准，便于低上下文执行者稳定落地实现。触发词：写计划、实现计划、任务拆解、plan。
forge_use-store-not-props-best-practice
Must follow when 设计组件数据流——优先通过 Store 访问全局状态，不得通过 Props 层层传递；适用于代码审查和新功能设计阶段。
forge_i18n-best-practice
Must follow when 创建或重构 i18n 国际化代码，确保遵循 react-i18next 最佳实践（初始化配置、翻译文件结构、组件用法、SSR 同步、语言切换与测试 Mock）。
forge_check-hardcode
Use when 需要检查代码中是否存在硬编码内容，包括魔法数字、路径、URL、密钥、环境变量、响应消息等；确保所有可配置值都使用常量或配置文件管理。触发词：硬编码、hard code、magic number。
forge_ui-components-best-practice
Must follow when 创建或审查 UI 组件代码，确保在标准场景下使用项目组件库组件（如 shadcn/ui），禁止直接使用原生 HTML 元素。
forge_svg-icon-best-practice
Must follow when 管理或新增 React TypeScript 项目中的 SVG 图标组件，确保命名、封装方式和导出规范遵循项目标准规范。
forge_subagent-driven-development
Use when 需要把已批准的实现计划拆成独立任务并分派给子代理执行，通过规格一致性审查与代码质量审查双阶段把关，确保并行实现结果与设计、计划和验收标准保持一致。触发词：子代理开发、分派任务、并行实现、subagent。
forge_skill-best-practice
Must follow when 创建或修改 Skill 后执行质量验证，涵盖命名、目录结构、元数据完整性、临时文件清理和依赖格式共 16 项检查。
cloudflare
Use this when asked to make a cloudflare worker
qt-translation-helper
|
qt-unittest-make
Use when users request generating unit tests for Qt modules or classes, completing test cases, or creating test files. Supports module batch generation and incremental completion.
skills-best-practices
Use when creating, extracting, reviewing, or refactoring agent skills. Covers self-contained skill packaging, SKILL.md structure, trigger descriptions, progressive disclosure, gotchas, defaults, bundled scripts, eval design, and with-skill vs baseline iteration. Use this whenever the user asks to turn docs or a workflow into a skill, improve a SKILL.md, audit skill quality, or make a skill pack more self-contained.
qt-unittest-build
为 Qt 项目生成单元测试框架。包含完整依赖、子 Agent 和固定脚本，一键生成 autotests 测试框架。
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
qtbug-upstream-fixer
Use when fixing upstream Qt Jira defects, handling AUTOSUITE-* or QTBUG-* bug reports, preparing Qt Gerrit patches, using git review, or submitting fixes to codereview.qt-project.org.
qt-cpp-bug-fixer
Use when encountering compilation errors, runtime crashes, memory leaks, UI issues, or threading problems in Qt C++ projects. Also use when MOC errors, undefined vtable references, missing Q_OBJECT macros, or signal-slot connection failures occur.
mermaid-syntax
This skill should be used when the user asks to "create a mermaid diagram", "fix mermaid error", "mermaid syntax error", "diagram not rendering", "flowchart not working", "sequence diagram broken", "escape special characters in mermaid", or mentions "mermaid", "flowchart", "sequence diagram", "class diagram", "state diagram", "ER diagram", "gantt chart". Prevents common syntax errors with special characters, reserved words, escaping rules, and provides v11 syntax support.
create-release-tags
Use when releasing new versions for Debian projects with optional linglong.yaml support, updating debian/changelog, incrementing patch versions automatically, and creating git commits
qt-compatibility-build
Use when maintaining Debian packages that need Qt5/Qt6 dual support, CMakeLists.txt has hard-coded Qt5/Qt6 or DTK5/DTK6 versions, or projects need dynamic library linking based on detected Qt version for deepin V25/V20 compatibility
github-review-report
Use when generating Chinese format Excel reports from GitHub code reviews with AI analysis and filtering by date, branch, or reviewers
ai-agent-fixer
Use when fixing issues in AI-related repositories.
5-Whys Root Cause Analysis
This skill should be used when the user asks to "find the root cause", "找根因", "为什么会出现这个问题", "why did this happen", "debug this issue", "排查问题", "analyze this bug", "分析这个bug", "what's causing this", "问题出在哪", "dig deeper", "深挖原因", or needs to systematically trace a problem back to its fundamental cause rather than just addressing symptoms.
herdr-orchestrator
Orchestrate multiple AI coding agents from inside herdr. The current agent becomes a pure supervisor that spawns workers, assigns structured tasks, monitors execution, reads results, and reclaims panes. MANDATORY trigger on 'orchestrate', 'spawn workers', 'parallel execution', 'dispatch tasks', 'manage agents', 'split work', or when the agent detects a task is large enough to benefit from parallel execution. ALSO trigger when the agent is working inside herdr (HERDR_ENV=1) and identifies 3+ independent work units — proactively suggest orchestration to the user.
deepin-dde-expert
Use when developing Deepin/UOS desktop applications with DTK widgets, GVfs file operations, DBus system integration, or Polkit authentication. Qt6/Qt5 dual support.
drawio
Use when user requests diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Generates .drawio XML files and exports to PNG/SVG/PDF locally using the native draw.io desktop CLI.
commit-submit
Use when user asks to "commit", "提交", "stage", "暂存", or "git status"
karpathy-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
issue-fixer
>
code-review-excellence
|
gemini-api
Google Gemini API integration for building AI-powered applications. Use when working with Google's Gemini API, Python SDK (google-genai), TypeScript SDK (@google/genai), multimodal inputs (image, video, audio, PDF), thinking/reasoning features, streaming responses, structured outputs with JSON schemas, multi-turn chat, system instructions, image generation (Nano Banana), video generation (Veo), music generation (Lyria), embeddings, document/PDF processing, or any Gemini API integration task. Triggers on mentions of Gemini, Gemini 3, Gemini 2.5, Google AI, Nano Banana, Veo, Lyria, google-genai, or @google/genai SDK usage.
unhobble-agent-context
Audits and designs lean, coherent context across system prompts, persistent instructions, repository guidance, skills, tool descriptions, memory, and references. Use for context engineering; creating, reviewing, simplifying, or reorganizing agent context; resolving conflicting, duplicated, bloated, stale, or misplaced guidance; designing progressive disclosure; or deciding where shared information should live.
gogopowermanager
Orchestrates and ships a milestone, release, issue set, or multi-workstream engineering goal through one manager and bounded parallel workers. Use when the user asks to manage a milestone, build a dependency graph, execute independent issues in parallel, coordinate threads, sessions, subagents, or worktrees, recover a stopped delivery, or invokes /gogopowermanager.
ios-design-review
>
mikrotik-routeros
Configures and automates MikroTik RouterOS routers through the terminal, command line interface, .rsc imports, /system script repository, Scheduler, Netwatch, firewall, NAT, DHCP, DNS, bridge, VLAN, routing, VPN, device-mode, backup/export, and RouterOS scripting. Use this skill whenever the user mentions MikroTik, Mikrotik, RouterOS, WinBox terminal, router CLI, router scripts, .rsc files, or configuring MikroTik services from the command line.
orbstack-cli
>-
package-private-ml-artifacts
Inventories, hashes, scans, and verifies datasets, adapters, checkpoints, logs, and evaluation evidence before an explicitly approved private upload. Use when ephemeral jobs or handoffs require durable ML artifacts without exposing credentials or unapproved data.
prepare-training-corpus
Builds and freezes deterministic train, validation, and test corpora with provenance, group-safe splits, manifests, hashes, and prompt-leakage checks. Use before teacher labeling, fine-tuning, or comparing models on generated or retrieved examples.
proxmox-admin
Administers Proxmox VE hosts, creates and manages VMs with qm, manages LXC containers with pct, configures storage, networking, clusters, and automates provisioning tasks via the Proxmox CLI.
review-ios-ui-apple-hig
Review iOS app UI against Apple Human Interface Guidelines and iOS platform conventions. Use when asked for an Apple HIG-based iOS UI, UX, SwiftUI, UIKit, screenshot, simulator, accessibility, Dynamic Type, navigation, layout, controls, color, typography, or platform-conventions review, especially when the user wants critique or prioritized findings grounded in Apple's interface guidance instead of project-specific design docs.
review-training-data-quality
Audits a candidate or labeled training corpus for distribution collapse, ambiguity, context sufficiency, hard-negative quality, abstention behavior, leakage, and stable label defensibility. Use before scaling teacher calls or starting fine-tuning.
validate-structured-model-output
Validates JSON or tool-call model outputs without repair, separating parse, schema, supplied-identifier, semantic, replay, and safety failures. Use for first-attempt benchmarks, teacher-label pipelines, and bounded model tool selection.
write-a-prompt
Creates a copy-ready prompt from a rough request, notes, source material, or the current conversation using OpenAI's prompting guidance. Use when the user invokes $write-a-prompt or /write-a-prompt, types a common misspelling such as /write-a-promopt or /wite-a-prompt, asks to "write a prompt for me," asks to turn the conversation into a prompt, or wants a prompt tailored for Chat, ChatGPT Work, or Codex. It writes the prompt without performing the underlying task.
topydo
Manages todo.txt tasks using topydo CLI. Adds, lists, completes, prioritizes, tags, and organizes tasks with dependencies, due dates, recurrence, and projects. Use for any task management, todo lists, or when the user mentions tasks, todos, or todo.txt. Requires Python 3 and pip. Works on macOS, Linux, and Windows.
tmuxinator
Helps create, edit, and debug tmuxinator project configurations, set up complex tmux session layouts, and automate development environment startup with multiple windows and panes.
Page 1164 of 1711 · 85506 results
