В каталоге 183 730 навыков в 14 категориях.
Plan development tasks into clear, low-risk, reviewable increments. Use when the user wants an implementation plan, brea...
Use when a development pod begins or hands off implementation, QA, or design work.
detailed development workflow with modular patterns for git, code review, testing, documentation, and deployment
Use when choosing a branching strategy, writing a commit message, opening or reviewing a pull request, setting up commit...
Development Workflow Orchestrator
Design a developmental band system mapping student growth from early childhood through upper secondary. Use when buildin...
Tags harness-decomposed curriculum items (KUDs, LTs, criteria) with a school's developmental band metadata while preserv...
Synthesise completed KUD charts into a developmental progression matrix and per-competency narrative sections. Use when...
Lifespan development from prenatal through aging. Covers Piaget's stages of cognitive development (sensorimotor, preoper...
Developer experience audit and improvement skill. Use when the user wants to review their API, CLI, SDK, or docs from a...
Establish and scale a Developer Experience (DevEx) program to remove engineering friction and boost productivity. Use th...
Live developer experience audit. Uses the browse tool to actually TEST the developer experience: navigates docs, tries t...
Live developer experience audit. (gstack)
开发者体验实测审计。使用 browse 工具真正去 TEST 开发者体验： 浏览文档、尝试 getting started、计时 TTHW、截图错误信息、评估 CLI help。 输出带证据的 DX scorecard，并与 /plan-d...
Developer experience (DX) engineering, SDK design patterns, API ergonomics, CLI tooling design, documentation-driven dev...
Create or analyze Developer Experience surveys. Creation mode outputs a 9-question HaTS-aligned survey; Analysis mode ou...
This skill should be used for development tasks that require detailed technical planning with persistent documentation....
Import DevExpert testimonials from Google Sheets (gog) or pasted TSV lists, format text with line breaks, crop profile i...
USE FOR: Building enterprise .NET applications using DevExpress UI components for Blazor, WinForms, WPF, or ASP.NET. Use...
Standards for using DevExpress (DEXT) components in Delphi VCL applications
End-to-end agent development process. Use when coordinating work, dispatching agents, or reviewing PRs.
Generate devhub.toml configuration files and manage multi-project development environments. Use when setting up projects...
Control Devialet Phantom speakers via HTTP API. Use for: play/pause, volume control, mute/unmute, source selection, and...
| SSOT | skills/devian-core/03-ssot — 모든 정책/경로/규칙의 정본 |
Handle unexpected work during execution. Use when encountering bugs, missing features, blockers, or architectural change...
Guidelines for coder agents on when to auto-fix issues vs when to pause and escalate. Enables autonomous work within saf...
Use when authoring a plan or implementation prompt - Deviations-from-Source block format, required even when empty.
Read cached contacts and calendar events from Muse storage. Delete Muse's local copy of either source without modifying...
Develop a request-specific app with the mounted device SDK, inspect relevant API documentation, exercise interactions, a...
This skill should be used when the user asks to "implement device auth", "add device authorization", "authenticate deskt...
デバイスクレデンシャル（Device Credential）機能の開発・修正を行う際に使用。デバイスシークレット発行、JWT Bearer Grant、CIBAデバイス認証、セキュリティ実装時に役立つ。
Execute comprehensive L1-L4 network device inspection. Use when user asks to "inspect all devices", "run comprehensive h...
Verify device legitimacy and app integrity using DeviceCheck (DCDevice per-device bits) and App Attest (DCAppAttestServi...
Verify iOS app behavior on device or simulator via screenshots, UI hierarchy, and touch interactions.
Verify app behavior on device or simulator via screenshots, UI hierarchy, and touch interactions.
Use for Windows, CachyOS, and TLS trust-store maintenance.
Manage device adoption and onboarding, maintain device inventory, and monitor device configurations across your UniFi Pr...
Manage device adoption and onboarding, maintain device inventory, and monitor device configurations across your UniFi ne...
['需要填写描述']
Probe and test SDR hardware capabilities (RTL-SDR, SDRplay, HackRF, etc.). Use when verifying device detection, discover...
Author and test an original JavaScript program for the declared device SDK.
This skill should be used when capturing screenshots from connected devices during development. Use this when users requ...
How a setting that belongs to the machine rather than to the account is stored and read: one module signal in src/compon...
Настройки устройства в settings.json, пути и конфигурация бэкенда. Использовать при добавлении настройки, правке setting...
Interact with iOS simulators and verify app behavior using xcobra
Devicetree management for Zephyr RTOS. Covers syntax, bindings, overlays, Hardware Model v2 (HWMv2), and advanced node/p...
Reviews a product document (PRD, spec, design brief) BEFORE implementation to surface holes — undefined edge cases, miss...
意見を出す前に、切り離した反論エージェントに主張を潰させ、返ってきた反証条件を確認してから答える。後戻りコストの高い相談（設計・技術選定・方針決め）で使う。「devil」「反論して」「この意見を潰して」と指示されたとき。
Constructive critic and stress-tester for ideas and proposals. Use when the user needs someone to challenge their thinki...
Constructive critic and stress-tester for ideas and proposals. Use when the user needs to challenge assumptions, find we...
Challenges recommendations, designs, or synthesis by adversarial review across 5 dimensions. Use before shipping any sig...
I play the devil's advocate to challenge and stress-test your ideas by finding flaws, risks, and edge cases
Use when challenging a prevailing analytical judgment, the user asks "what is the opposing case?" / "argue the other sid...
Challenge slide design with 5-7 pedagogical questions. Checks ordering, prerequisites, and cognitive load.
Use before design phase to challenge assumptions and surface risks
Challenge ideas, find weaknesses, and stress-test solutions before implementation
Use this skill whenever the user wants their thinking, request, design, plan, or position challenged. Triggers include:...
Use when substantive documents (reviews, analyses, synthesis documents) need adversarial review to strengthen arguments,...
Use when the user asks for the case against a campaign or marketing idea — e.g. 'attack this idea', 'play devil's advoca...
Systematically challenge current assumptions before major decisions. Counters confirmation bias, groupthink, and overcon...
Stress-test an idea or hypothesis. Build the strongest possible case AGAINST it, find disconfirming evidence, and surfac...
Use when a proposal has unanimous support or relies on a single high-impact assumption—constructs the strongest possible...
Utiliser avant toute décision importante pour faire jouer à l'IA le rôle d'un sceptique professionnel. Produit les trois...
Argues the strongest honest case against a decision, plan, belief, hire, pricing move, strategy, or piece of work the us...
Adversarial 5-7 question challenge to a deck's pedagogical choices — ordering, prerequisites, cognitive load, motivation...
Systematically challenges a plan, decision, or proposal — identifying assumptions, failure modes, and stronger alternati...
Get an outside-Anthropic second opinion on any piece of work by sending it to Google Gemini with an adversarial critique...
Argue hard against whatever you just concluded — so your decision has to survive a real challenge instead of an echo cha...
The strongest possible case AGAINST what you just wrote — argued to win, not to check a box. Use when a document is abou...
Start and boundedly follow a remote Devin development task. Use when the user types /devin with implementation instructi...
Reference system prompt and tool schemas for Devin AI. Use when imitating, comparing, or analyzing Devin AI's prompting...
Delegate bounded coding tasks to the local Devin CLI over ACP from a supervising agent such as Claude Code or Codex. Use...
Run a Devin Fusion session — pair a frontier main agent with a cheap sidekick agent to reduce cost while keeping frontie...
Devin CLI의 프로젝트별 Mnemo 대화 저장, 검색, 설치 상태를 설정하거나 진단할 때 사용한다. Devin 훅과 로컬 세션 DB를 공통 MEMORY.md·conversations/ 저장소에 연결한다.
DevelopersIO article writing and Contentful publishing assistant. Use "/devio article <topic>" to draft a new article, o...
Symbolic PDE solver with automatic code generation for finite-difference computations. Use when Claude needs to: (1) Per...
Trace and verify every consumer before changing a public signature in src/devkit/ (env.py, db.py, oauth.py, mcpsecurity....
Create a new AIWG skill with AI-guided design
Validates a skill against DevKit standards (requirements, template, dependencies)
AI Agent / LLM 应用工程化方法论。指导如何把一个 AI 智能体应用"拆成哪几块 + 如何避免重走老路"：分层管道、规则优先+LLM兜底、多模型触点路由、Prompt 统一治理、超时/缓存/降级、评测闭环、多厂商 SDK 适配。...
Review completed dev sessions to decide whether work should be distilled into devlab-* assets (skills, CLI tools, MCP se...
Provider-neutral CI/CD onboarding workflow for repository analysis, pipeline design, configuration boundaries, and relea...
前后端契约规范技能（contract 技能簇首个，定位介于 devlab-srv-* 与 devlab-web-* 之间）。约束大型前后端分离项目的接口/序列化契约、字段类型一致性、错误码与配置分层，提供契约校验与联调防错清单。Trigge...
DAO 层通用 SQL 方言兼容性检查 + 系统性修复工作流。支持 MyBatis/JPA/MyBatis-Plus/SQLAlchemy 四种持久层框架，扫描源码识别 Oracle/PostgreSQL/MySQL 方言混用风险，自动修复...
数据库数据层安全迁移专家技能。覆盖 schema 演进（加列/改约束/建索引）与数据搬迁的完整安全流程：备份→幂等检测→迁移→验证→失败回滚。当项目需要变更已有表结构、生产报 no such column / 唯一约束冲突、或需编写独立迁移...
eval 自评测体系驱动的 AI Agent 生产体系方法论。以评测集为核心资产，建立"评测集组织 + Mock 隔离 + 标准化比对 + 自动评测脚本 + 回归门禁"闭环；L0-L4 分层评测（确定性单测/轨迹评测/输出评测/生产回归/安...
全栈集成测试专家技能。支持多服务 Docker Compose 部署场景，基于 Testcontainers + Mock Server 实现端到端集成测试。
后端 API 测试专家技能。支持 Java（JUnit）/ Python（pytest）/ Node.js（supertest + jest）后端项目的接口测试、Mock 服务、测试数据管理。
技术债全生命周期运维：审计分析→建议报告→确认后重构（微观+宏观）→回归验证。覆盖从“发现债务”到“安全消除”的闭环。Triggers on "重构", "技术债", "技术债审计", "audit", "god class 太大", "拆...
测试专家知识库。包含测试最佳实践、故障排查指南、测试策略设计、性能优化建议等专家级知识，供其他测试技能引用。
AI 驱动的分层测试体系顶层路由编排。根据项目特征（前端/后端/全栈/微服务）智能识别测试需求，路由到对应子技能（devlab-web-test-e2e / devlab-srv-test-api / devlab-integration-...
前端项目上下文理解规则资产（<domain>-context 家族首个成员）：双模式（模式 A 规则包被 devlab-context-bootstrap 文件契约委托 / 模式 B 独立四步渐进式理解），产出前端 context 画像（7...
存量 Web 系统深度功能验收方法论（L1-L4）。registry 功能点驱动 + 唯一入口执行器 + 假成功嗅探 + 三对齐审计，覆盖盘点建模、用例固化、失败五分类路由、多会话认领协作。与 devlab-web-test-e2e（绿fi...
ECharts 在 Astro/前端项目中的完整集成指南，包含 tree-shaking、IntersectionObserver 按需加载、自定义系列集成、拓扑图实现、雷达图配置、Astro Islands 数据传递、调试经验。
Web / 前端工程化能力层（Frontend Engineering Capability）。语言无关覆盖六域：Project Bootstrap、Build、Dependency、Packaging、Runtime/Environmen...
Use when building a browser/web extension from scratch, especially one that extracts, downloads, or enhances data from a...
前端 SkyWalking RUM 接入技能。凡是用户提到前端监控、RUM、skywalking-client-js、Web Vitals 采集、浏览器端链路追踪、前端错误上报时触发。框架无关，支持 Vue/React/Angular/Sv...
Web E2E 测试专家技能。专注 Vue/React 前端项目的浏览器端到端测试能力，基于 Playwright + AI Agent 实现测试计划生成 → 代码生成 → 失败修复的完整闭环。
Web 视觉化操作（Web Visual Operations）：对 Web 应用做 Observe/Navigate/Interact/Inspect/Validate/Capture 的 day-2 操作手册。Router 层统一编排...
@xyflow/react 使用指南：核心概念、自定义节点、Astro Islands 集成、6 条踩坑经验。