subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
auth-implementation-patterns
Master authentication and authorization patterns including JWT, OAuth2, session management, and RBAC to build secure, scalable access control systems. Use when implementing auth systems, securing APIs, or debugging security issues.
hybrid-search-implementation
Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
react-agent
Pragmatic React development focused on avoiding over-engineering, effective state management, and render optimization. Use when building React components or features where you need clear guidance on (1) choosing appropriate state management solutions, (2) optimizing component rendering and performance, (3) avoiding common over-engineering patterns, (4) implementing TypeScript with React, or (5) making architectural decisions that balance simplicity with scalability.
git-conventional-commits
Professional git commit workflow with Conventional Commits format. Enforces commit type categorization (feat, fix, docs, style, refactor, perf, test, build, ci, chore), validates messages against the 7 rules of great commits, previews before committing, and supports multiple languages. Use when you need to create high-quality, traceable git commits.
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
vue3-best-practices
Vue 3 performance optimization and best practices guidelines for modern frontend applications. This skill should be used when writing, reviewing, or refactoring Vue 3 code to ensure optimal performance patterns, proper Composition API usage, and modern development practices. Triggers on tasks involving Vue 3 components, Composition API, reactivity, state management, or performance optimization.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
ai-pm
>
api-enrichment
>
figma-export
Export Figma frames as PNG images via Figma REST API. Use when you need to get a design screenshot from a Figma URL for visual comparison.
pixel-diff
Pixel-level image comparison between two screenshots. Generates a visual diff overlay highlighting differences. Use for comparing Figma designs against web implementations.
logic-coder
Vue 3 前端邏輯技能（邏輯 Agent）。接收 enriched-spec.md（含 API 對應表、State 結構定義、錯誤處理方案），將切版完成的純展示元件（Dumb Components）與 API / 狀態管理邏輯整合，產出可執行的容器層、services、composables。觸發情境包含：接續 api-enrichment 完成後的邏輯實作、「幫我串 API」、「實作資料邏輯」、「加上 loading / error 狀態」、「幫我寫 composable」、「實作 Pinia store」、提到 enriched-spec.md 或 component_paths handoff payload 的情境。
vue-layout
Vue 3 + SCSS 切版技能（切版 Agent）— 像素級精確實現。從 Figma 設計稿生成 **1:1 視覺保真的** Vue 3 純展示元件（Dumb Components）。觸發情境包含：「幫我切版」、「根據 Figma 產出元件」、「根據 spec 建立 UI」、「幫我建 Vue 元件」、「切這個畫面」、「實現 Figma 設計」、「補切版」、有提到 Figma URL 或 Node ID 加上 Vue/元件/切版等字詞。保證顏色、間距、字號、圓角、邊框等像素級精確匹配，同時支援與規格流程集成（使用 `draft-spec.md` 或 handoff payload 增強理解）或無規格快速實現。只要上游提供了核准 node 清單，就必須先做 node-to-component mapping 與 coverage 自查，未覆蓋 node 不得宣稱切版完成。僅產出 props/emits 介面的純 UI 結構，不含 API 呼叫或業務邏輯。
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
figma-implement-design
Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions "implement design", "generate code", "implement component", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`.
ai-interaction
Continuous communication channel via MCP AI Interaction tool. Activate with 'khởi động ai_interaction'. Enables real-time Vietnamese conversation with action-first principle - execute first, explain minimally.
angular-coding
Angular coding standards with version-aware patterns. Automatically detects Angular version from package.json and applies appropriate patterns. Use when writing Angular components, services, or TypeScript code.
project-scanner
Codebase analysis tool for quality-first editing. Scan before edit to understand relationships, patterns, and impact.
web-browsing
Web research with automatic fallback mechanism. WebFetch → Browser MCP → User assistance via ai_interaction. Use when need to browse web.
agent-init
Initialize or improve AGENTS.md files that define how coding agents operate in a repo. Use when asked to set up or replace an agent init command (Codex, Claude), standardize multi-agent behavior, or audit an existing AGENTS.md for clarity, commands, boundaries, and repo-specific context. For Claude Code, also create CLAUDE.md as a symlink to AGENTS.md.
extension-creator
Create AiderDesk extensions by setting up extension files, defining metadata, implementing Extension interface methods, and updating documentation. Use when building a new extension, creating extension commands, tools, or event handlers.
writing-tests
Write unit tests, component tests, and integration tests for AiderDesk using Vitest and React Testing Library. Use when creating new tests, adding test coverage, configuring mocks, setting up test files, or debugging failing tests.
agent-creator
Create and configure AiderDesk agent profiles by defining tool groups, approval rules, system prompts, subagent settings, subagent filtering, and provider/model selection. Use when setting up a new agent, creating a profile, or configuring agent tools, permissions, and subagent behavior.
theme-factory
Create new AiderDesk UI themes by defining SCSS color variables, registering theme types, and adding i18n display names. Use when adding a theme, creating a color scheme, customizing appearance, or implementing dark mode and light mode variants.
dbx-agent-handoff
Use only when the user wants to hand off the current AI agent session state to another AI agent or a future AI session, including context compaction, restart packets, resume notes, or "下个 session/agent 继续". For ambiguous "handoff/交接文档" requests, use only to ask one clarification question and stop. Do not use for human-facing workplace handoff documents, onboarding docs, project transition memos, status reports, meeting summaries, or general summaries.
dbx-aliyun-sls
>-
dbx-architecture-health
Evidence-grounded, read-only repository or module architecture health review for AI-coding-era codebases. Use when the user asks to audit architecture health, prevent repo decay, assess long-term maintainability, find source-of-truth drift, identify verification gaps, or evaluate whether a codebase is safe and effective for AI-assisted change. Do not use for concrete PR/diff review, strict Linus-style critique, implementation planning, direct code changes, release/publish checks, or skill portfolio audits.
dbx-attention-routing
Use when the user wants a reusable attention-routing workflow for mixed inbox items, saved content, tasks, ideas, signals, courses, tools, notes, or external-system metadata. Routes each item by stable attention states, grounded in visible evidence and a user-approved profile. Use high-risk prompts only to guard or safety-stop direct action requests. Do not use for ordinary summarization, one-off recommendations, product-specific automation by default, or silent external writes.
dbx-code-ratchet
>
dbx-conversation-align
Diagnose communication intent, disagreement layer, correction timing, boundary needs, and response strategy for relationship, work, and conflict conversations.
dbx-crystallize
Use when the user has a fuzzy product/software idea, feature request, issue draft, stakeholder ask, or pre-development discussion and wants to clarify it into precise, testable requirements before product judgment, design judgment, technical planning, or implementation. Produces a bounded requirement contract with user/job/context, state change, scope, non-goals, functional requirements, acceptance criteria, edge cases, assumptions, open decisions, readiness state, and handoff. Prefer dbx-product-conception when the product direction itself must still be invented or selected. Do not use for direct implementation, code review, product-worth judgment, design critique, pure brainstorming, generic PRD writing, or formal DBX software plan-first phases unless explicitly invoked as a handoff source.
dbx-decision-framing
当用户面对高影响、不确定、有真实行动后果的决策，需要在多个选项或 go/no-go 之间取舍时使用。适用于职业去留、技术架构、产品方向、团队组织、生活迁移、投资框架等。先做门禁，再决定 full_decision、quick_decision、clarification、direct_answer 或 safety_redirect。不要用于单纯概念解释、翻译润色、机械代码、一次性写作、低风险日常小事或没有行动后果的泛泛分析。
dbx-design-judgment
Use when the user asks to judge, audit, critique, review, shape, redesign, or produce a design plan for a UI, flow, PRD, screenshot, prototype, live product, component, design system, or code-backed interface, including concrete interaction feedback, control, interruption, and recovery. Grounds design judgment in target user, task path, information architecture, visual hierarchy, interaction states, visual language, design system consistency, accessibility, responsive behavior, and evidence. May read PRDs, code, screenshots, and live products and inspect read-only surfaces. Route aggregate product-outcome causes across unknown layers to dbx-product-judgment, and route technical incident diagnosis without a design decision to technical debugging. Must not edit files, write implementation code, apply patches, install packages, or commit changes.
dbx-diff-review
High-signal code change review workflow for PRs, patches, staged/index changes, working-tree diffs, commit ranges, and file-scoped review. Use when the user asks to review concrete code changes for functional/user-impact risks, data model correctness, state ownership, compatibility, or maintainability. Handles partial staged hunks and user-selected files/commits by selecting the exact review target before reading the diff. Do not use for implementation-only requests, generic code explanation, release publishing, issue triage, or plan-only Linus-style strict-pragmatic critique; for strict critique of a concrete diff, use this skill only to establish the target before dbx-linus-review.
dbx-epistemic-audit
>-
dbx-feishu-doc
Use when the user needs to read, summarize, create, append to, or safely update Feishu/Lark Docx, Wiki, or document-like resources in a development workflow. Prefer official lark-cli document operations and block-aware updates. Do not use for Feishu Project/Meegle work items, generic writing without a Feishu document target, or editing external documents without clear permission.
dbx-feishu-feedback-triage
Use when the user needs to summarize, classify, deduplicate, and triage business feedback from a bounded Feishu/Lark group chat window using a specified domain knowledge pack. It turns chat messages into evidence-backed feedback cases, separates usage questions, misuse/config issues, suspected bugs, confirmed bugs, feature requests, product gaps, documentation gaps, resolved and unresolved items, and produces a digest plus memory-update candidates. Default to read-only. Do not create Feishu Project items, reply to chats, or update accepted memory unless explicitly approved.
dbx-feishu-im
Use when the user needs to read, search, summarize, analyze, or safely write Feishu/Lark IM messages, group chats, direct messages, threads, reactions, message resources, or bounded realtime IM events in a development workflow. Default to read-only evidence collection; require explicit confirmation for sending messages, replying, pinning, urgent notifications, member/chat changes, or cross-system writes. Do not use for Feishu Project/Meegle work-item operations, domain-backed business feedback triage, or Feishu document editing unless this skill is only gathering chat evidence for another Feishu workflow.
dbx-feishu-project
Use when the user needs to read, query, create, update, comment on, attach files to, or transition Feishu Project / Lark Project / Meegle work items such as story, ticket, bug, requirement, version, iteration, task, defect, or release work. Default to read-only until a concrete write target, exact change, and user approval are clear. Do not use for Feishu documents, generic project-management advice, or code implementation without an external Feishu Project operation.
dbx-feishu-workflow
Use when the user asks to coordinate a development workflow across Feishu Project/Meegle work items, Feishu documents, and optional Feishu/Lark IM evidence, such as reading a ticket, updating a technical plan, syncing implementation progress, writing release notes, or commenting back with validation evidence. This is an orchestration skill; delegate project operations to dbx-feishu-project, document operations to dbx-feishu-doc, and chat evidence to dbx-feishu-im. Do not use for single-domain Feishu operations or generic planning without external Feishu read/write.
dbx-goal-writer
Use when the user wants to create, refine, start, or audit an OpenAI Codex goal contract for coding work, especially long-running or validation-heavy tasks. Produces copy-pasteable /goal commands, optional GOAL.md files, and only for large or strict tasks a goal package directory with plan, acceptance, validation, and status files. Do not implement the coding task unless explicitly asked.
dbx-learn
当用户明确想通过 AI 提升自己对某个概念、技术主题、资料集或技能的长期理解与可迁移能力时使用。适用于系统学习、讲透一个概念、建立 mental model、深度研究、把资料转成练习、复习测验、学习路线、学习记录候选和可持续学习 workspace。默认轻量、无预配置、少打扰。不要用于普通事实查询、单篇普通总结、泛泛推荐、直接代码实现或调试、产品/设计/架构决策、skill 创建、一次性润色，或用户只想要答案而非学习过程的请求。
dbx-linus-review
Strict pragmatic, evidence-driven technical review for code changes, architecture plans, data models, and implementation proposals. Use when the user explicitly requests Linus-style review, harsh/strict review, pragmatic critique, over-engineering judgment, merge/readiness judgment, or asks whether a technical plan or code change is good enough. It may also act as a read-only reviewer provider when an already user-authorized controller explicitly delegates a full or scoped strict review with artifact identity, scope, evidence boundary, and write prohibition. Shares judgment principles with dbx-diff-review but uses a stricter artifact-agnostic critique loop. Do not use for ordinary code explanation, implementation-only requests, generic encouragement, interpersonal judgment, or normal diff review unless strict/pragmatic critique is explicitly requested.
dbx-open-source-commit-pr
Generate or review concise English commit messages and PR descriptions for public or open-source repositories. Use when the user asks for commit text, PR body, release-style change summary, or validation wording based on a final diff, staged changes, working tree changes, or a specific commit. Do not use for internal M-xxx work PR contracts, generic code review, or explanations of what commits are.
dbx-plan-convergence
Explicit-only, provider-agnostic controller for bounded convergence of an existing technical plan, architecture proposal, migration plan, ADR draft, or implementation proposal. Use when the user explicitly asks for 方案收敛, plan convergence, 方案棘轮, or a controlled review-revision loop, or when an already user-authorized parent workflow explicitly delegates that convergence step with artifact, scope, provider bindings, budget, and modification authority. It decides whether to obtain review, revise locally, gather evidence, request a decision, explore alternatives, pivot, finalize, or stop. Do not use for first-draft planning, standalone review, generic brainstorming, code repair, implementation, or open-ended autonomous loops.
dbx-product-conception
Use when the user wants to discover, invent, reframe, or converge what a not-yet-defined product should be from weak signals, enabling technology, changing behavior, latent human capability, or competing concepts. Produces distinct product logics, concrete experience specimens, a selected product thesis, deliberate non-goals, and a prototype/validation handoff through evidence-labeled creative selection. Prefer dbx-product-judgment when a defined product, feature, PRD, roadmap, or live experience already exists and the question is whether it is valuable, coherent, usable, viable, or worth building. Prefer dbx-crystallize when direction is chosen and requirements or scope need precision. Do not use for generic idea lists, Steve Jobs impersonation, pure design critique, implementation, or unsupported novelty claims.
dbx-product-judgment
Use when the user asks to judge whether a product, feature, PRD, information architecture, content, interaction, UI flow, live product, implementation, roadmap, or competitor position is right, good, usable, valuable, coherent, worth building, product-ready, or why an aggregate user outcome or product decision is failing across unknown layers. Grounds judgment in target user, job/context, evidence, alternatives, critical path, trust, and implementation alignment. Ask blocking questions or collect evidence before judging when background is missing. Prefer dbx-product-conception when inventing or reframing an undefined direction; prefer dbx-design-judgment when product intent and rules are fixed and the concrete design surface dominates. Do not use for pure implementation, technical malfunction or incident diagnosis without product judgment, generic UI inspiration, ordinary code review without product judgment, generic market summaries, pure theory, or unsupported guesses.
dbx-read
>
Page 601 of 1646 · 82255 results