В каталоге 183 730 навыков в 14 категориях.
Define MVP scope, success metrics, and explicit out-of-scope items to focus on the smallest testable product. Use when u...
Publish JavaScript/TypeScript packages to the npm registry with consistent metadata, versioning, and release checks. Use...
Create/Updates detailed user personas and prioritized user stories based on target users and market research. Use when u...
Create comprehensive Product Requirements Document (PRD) defining product behavior, functional and non-functional requir...
Archive the current project so the repo is ready for a brand-new project start from ideas.md. Use when user asks to arch...
Plan sprints and backlogs in an AI-Driven Development workflow. Define features (backlogs), organize sprints as cumulati...
Restore a project from 99-archive, a remote git repo, or a local codebase back to the workspace root, including reconstr...
Review and refine MCP skill descriptions to follow the agent skill specification, and record approved overrides in dev-s...
Capture and inspect specific screen regions (e.g., mobile simulators, app windows) using a background streaming process....
Create custom slash commands for popular AI agents (Claude Code, Codex, Gemini CLI). Use when user asks to create slash...
Define technical specifications including tech stack, security, theme standards (from UX mockup), coding standards, and...
Control the computer by taking screenshots, moving the mouse, clicking, and typing. Use this skill when you need to inte...
Design user experience including flows, interactions, mockups, and accessibility. Use when user asks to design UX, creat...
This skill should be used when the user asks to "implement using TDD", "test-driven development", "RED-GREEN-REFACTOR",...
Test-driven development workflow. Auto-detects backend (.NET) and frontend (Angular/TypeScript) from project files. Loop...
Test-driven development workflow for C#/.NET using xUnit, NSubstitute, and event sourcing (EventSourcing). Covers aggreg...
Test-driven development workflow for Angular/TypeScript using Vitest, @testing-library/angular, Angular TestBed, and Pla...
開發團隊：任務池架構，由 Team Lead（Opus）規劃任務並管理品質閘門， challenger（Sonnet）持續質疑，workers（Sonnet）自取任務並行開發。 TL spawn 一次性 QA sub-agents 審查已完...
Simulate a collaborative dev team session where multiple role-based personas (PM, Architect, Developer, QA) respond to t...
Multi-agent development team orchestration. Use when managing coding agents (Codex, Claude Code, Gemini, Cursor) for aut...
Simulate a collaborative dev team session
根据设计补充Dev视角的技术细节（数据库/API/通信协议），帮助Dev快速进入实施。当L1/L2设计缺乏技术细节、或准备向Dev交付前使用。
This skill should be used when the user needs to 'debug web applications', 'test UI interactions', 'capture screenshots...
Chrome MCP browser testing. Console/network debugging, JS execution, GIF recording.
This skill should be used when the user asks to "test Electron app", "automate Electron desktop app", "debug Electron re...
This skill should be used when validating test coverage against requirements, after implementation tasks complete (Phase...
This skill should be used when the user asks to "debug macOS app", "test native app", "automate macOS workflow", "test n...
This skill should be used when the user asks to "test Linux desktop apps", "automate GTK/Qt applications", "test with yd...
Playwright MCP browser testing. Headless E2E, cross-browser, CI/CD automation.
기능 개발을 위한 테스트 케이스 및 시나리오 문서를 작성한다. AI가 스펙의 인수 조건에서 테스트 케이스를 자동 도출하고, 사용자가 누락 여부와 AC 매핑을 검증한다. 사용 시점: "테스트 케이스 만들어줘", "TC...
AI DevKit · Testing phase guidance for adding and validating feature test coverage. Use when the user wants to write tes...
Gate 3 of development cycle - ensures unit test coverage meets threshold (85%+)for all acceptance criteria using TDD met...
When the user wants to publish on Dev.to, Hashnode, or other developer blogging platforms. Trigger phrases include "Dev....
Development skills for Bun CLI, runtime workflows, and developer experience patterns
This skill should be used when the user asks 'what development tools are available', 'list dev plugins', 'what MCP serve...
Developer tools for The Fold - protocols (extensible dispatch), protocol bundles, refactoring toolkit (rename, move, dea...
Run CLI dev tools for game development (world inspection, benchmarks, assets, simulation). Use when user wants to 'check...
Developer tools — systematic debugging (4-phase root cause), test-driven development, code quality gates (critic-gate, o...
Use when the user says "use the DevTools skill" or when they need help debugging a web app with Chrome DevTools MCP (UI...
Guide for development and code tools skills including document processing, browser automation, testing frameworks, and I...
FIX TypeScript errors, WRITE better types, and CONVERT JavaScript to TypeScript. Use when encountering type errors, impr...
Advanced TypeScript patterns - generics, utility types, React patterns. Use for complex type scenarios.
Core TypeScript patterns for game development. Use when defining types and interfaces.
Add a UI lesson — TTF parsing, font rasterization, immediate-mode UI controls, layout
Code quality, correctness, and documentation review for UI lessons — run before dev-final-pass
Update the current working branch with the latest main. Fetches origin/main, updates local main, and merges main into th...
Report bugs and improvement ideas found in Takazudo's own upstream packages as GitHub issues on the upstream repo. The c...
Development cycle validation gate (Gate 5) - validates all acceptance criteria are metand requires explicit user approva...
Quality standards that must pass before commit
Post-change verification for C#/.NET backend code — build, Roslyn analyzers, dotnet format, xUnit tests with coverage, N...
Post-change verification for Angular/TypeScript frontend code — build, TypeScript type check, ESLint, unit tests with co...
This skill should be used when the user asks to 'verify completion', 'check that tests pass', 'confirm feature works', o...
Post-change verification for the project. Auto-detects backend (.NET) and frontend (Angular/TypeScript) from project fil...
Create, modify, and maintain Vue 3 components with TypeScript and SCSS. Use when building Vue components, modifying .vue...
Development workflow commands for the Guren monorepo. Handles building packages, running tests (smart targeted or full s...
Agent điều phối toàn bộ quy trình phát triển Frontend 5 bước: B0-Clone giao diện tham khảo → B1-Đọc inbox tạo tài liệu →...
Valid workflow state transitions for TDD feature/defect development. Use when determining which building block to invoke...
Run the project's validation pipeline (lint → format → typecheck → unit tests) with auto-fixes, then optionally stage an...
Use this Skill when the user asks to:
SDLC workflow with MCP tools. Triggers on "start", "implement", "work on", or unclear workflow.
Route planning, design, prototypes, implementation, review, commits, and pull requests through a project's delivery life...
Development Workflow Skill
Comprehensive TDD development workflow for FuzzyCat. Enforces test-driven development, post-implementation review, rippl...
项目开发工作流技能。在以下场景自动调用： (1) 编写或修改任何 crates/*/src/ 或 examples/ 下的代码 (2) 添加新依赖、改 feature flag 或修改配置文件 (3) 完成一个 feature 或修复一个...
Create a GitHub pull request using the gh CLI. Analyzes changes from base branch, generates a description following the...
Run the full ticket lifecycle end-to-end (Jira or GitHub issue). Chains initialize, start-work, prepare-commit, create-p...
Start working on a Jira ticket or GitHub issue by fetching details and creating a git branch in a new worktree. Use when...
Orchestrate PRD creation, task generation, and gated task processing with user confirmations between phases.
Structured development workflows using /brainstorm, /write-plan, and /execute-plan patterns. Transform ad-hoc conversati...
Prepare code for commit with quality checks and conventional commit message generation. Use when the user asks to prepar...
Review GitHub pull requests using the gh CLI. Fetches PR diff and details, optional Jira or GitHub issue context from br...
Start or resume work on a Jira ticket or GitHub issue by extracting the ID from the branch name, fetching requirements v...
AI DevKit · Worktree setup and resume guidance for isolated feature work. Use when starting, resuming, switching, or ver...
This skill should be used when the user asks to "create an isolated worktree", "set up worktree for feature", "create a...
Use when the user wants to smoke-test the evolve pipeline, test tools, or verify the plugin works end-to-end. Also use w...
Use when the user wants to release a new version, publish to npm, create a GitHub release, bump version, or tag a releas...
Use when the user wants to validate the plugin, check integrity, verify cross-references, or before a release. Also use...
This skill should be used when the user wants to add a LICENSE file to their repository. Currently supports Apache Licen...
devbooks-archiver：归档阶段的唯一入口，负责完整的归档闭环（自动回写→规格合并→文档同步检查→变更包归档移动）。用户说"归档/archive/收尾/闭环/合并到真理"等时使用。
devbooks-coder：以 Coder 角色严格按 tasks.md 实现功能并跑闸门，禁止修改 tests/，以测试/静态检查为唯一完成判据。用户说"按计划实现/修复测试失败/让闸门全绿/实现任务项/不改测试"，或在 DevBook...
devbooks-convergence-audit：以证据优先、声明存疑的原则评估 DevBooks 工作流收敛性，检测"西西弗斯反模式"和"假完成"。主动验证而非信任文档声明。用户说"评估收敛性/检查升级健康度/西西弗斯检测/工作流审计...
devbooks-design-doc：产出变更包的设计文档（design.md），只写 What/Constraints 与 AC-xxx，不写实现步骤。用户说"写设计文档/Design Doc/架构设计/约束/验收标准/AC/C4 De...
devbooks-docs-consistency：检查并维护项目文档与代码的一致性，支持增量扫描、自定义规则与完备性检查。可在变更包内按需运行或全局检查。旧名称 devbooks-docs-sync 保留为别名并输出弃用提示。
devbooks-entropy-monitor：定期采集系统熵度量（结构熵/变更熵/测试熵/依赖熵），生成量化报告，当指标超阈值时建议重构。用户说"熵度量/复杂度趋势/重构预警/代码健康/技术债务度量"等时使用。
devbooks-impact-analysis：跨模块/跨文件/对外契约变更前做影响分析，产出可直接写入 proposal.md 的 Impact 部分（Scope/Impacts/Risks/Minimal Diff/Open Ques...
devbooks-implementation-plan：从设计文档推导编码计划（tasks.md），输出可跟踪的主线计划/临时计划/断点区，并绑定验收锚点。用户说"写编码计划/Implementation Plan/tasks.md/任务...
devbooks-knife：把 Epic 级需求切成可拓扑排序的 Slice 队列，并落盘机读 Knife Plan（用于高风险/史诗级变更的 G3 强制闸门）。
devbooks-proposal-author：撰写变更提案 proposal.md（Why/What/Impact + Debate Packet），作为后续 Design/Spec/Plan 的入口。对设计性决策会呈现选项给用户选择。...
devbooks-proposal-challenger：对 proposal.md 发起质疑（Challenger）+ 查漏补缺，指出风险/遗漏/不一致并给结论，发现缺失的验收标准和未覆盖场景。用户说"质疑提案/挑刺/风险评估/提案对辩...
devbooks-proposal-judge：对 proposal 阶段进行裁决（Judge），输出 Approved/Revise/Rejected 并写回 proposal.md 的 Decision Log。用户说"裁决提案/提案评...
devbooks-reviewer：以 Reviewer 角色做可读性/一致性/依赖健康/坏味道审查，只输出审查意见与可执行建议，不讨论业务正确性。用户说"帮我做代码评审/review 可维护性/坏味道/依赖风险/一致性建议"，或在 Dev...
devbooks-test-owner：以 Test Owner 角色把设计/规格转成可执行验收测试与追溯文档（verification.md），强调与实现（Coder）独立对话、先跑出 Red 基线。用户说"写测试/验收测试/追溯矩阵/v...
devbooks-test-reviewer：以 Test Reviewer 角色评审 tests/ 测试质量（覆盖、边界、可读性、可维护性），只输出评审意见，不修改代码。用户说“测试评审/评审测试质量/覆盖率/边界条件”等时使用。
devbooks-void：Void 协议执行器：处理高熵/不确定/多方案争议问题，只产出 research_report + ADR + Freeze/Thaw 工件，不产出生产代码。用户说"进入 void/卡住了/不确定/需要调研/冻结...
This skill should be used when performing any coding task including implementing features, fixing bugs, refactoring code...
Install VS Code/Cursor extensions from a local .vsix via CLI (code, code-insiders, cursor, cursor-nightly). Use whenever...
Invoke DEVCOM_RESEARCH for deep research, cross-disciplinary analysis, and novel problem solving. Use when exploring cut...
Wire up DevContainers / GitHub Codespaces — `devcontainer.json`, container images, secrets, VS Code features, port forwa...
Diagnose devcontainer configuration problems and guide development environment setup. This skill should be used when the...