Каталог навыков агентов

Universal documentation consolidation skill that verifies system reality before making ANY organizational decisions. Ana...

IMPLEMENT VueUse composables for browser APIs, event handling, and performance optimization. Add keyboard shortcuts, loc...

FIX port conflicts when development server won't start or tests fail. Manage port 5546 for FlowState, kill existing proc...

Deep comprehensive system status analyzer that provides honest truth reporting about entire Pomo-Flow application health...

Comprehensive visual UI/UX inconsistency detector for design system validation, accessibility compliance, and cross-view...

Comprehensive detection of competing and conflicting systems in Vue 3 + TypeScript + Pinia projects. Identifies duplicat...

When task operations don't work correctly, systematically debug:

This skill provides comprehensive resolution of generic type system issues in the persistence and backup layers of the P...

Ensure data integrity, stability, and basic security for a personal productivity app. Focus on preventing data loss, mem...

CLEAN root directory of temporary files, build artifacts, and development clutter ONLY. This skill is exclusively for re...

COMPREHENSIVE architectural cleanup using AST analysis to detect duplicates, consolidate code patterns, and implement sy...

Comprehensive production debugging and verification framework for Vue 3 + TypeScript applications. Use when facing any c...

Comprehensive data safety auditor for Vue 3 + Pinia + IndexedDB + PouchDB applications. Detects data loss risks, sync is...

This skill provides Vue 3 component development with Composition API and TypeScript for the Pomo-Flow productivity appli...

Polish office systems through the e-urzad CLI - EZD RP cases, documents and tasks, e-Doręczenia deliveries, proofs and A...

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experim...

Claude Code ecosystem expertise. Modules: CLI tool (setup, slash commands, MCP servers, hooks, plugins, CI/CD), extensib...

Universal planning for technical and non-technical projects. Domains: software implementation, business, personal, creat...

Create and enhance prompts, system instructions, and principle files. Capabilities: transform verbose prompts, add patte...

Technical research methodology with YAGNI/KISS/DRY principles. Phases: scope definition, information gathering, analysis...

Structured reflective problem-solving methodology. Process: decompose, analyze, hypothesize, verify, revise. Capabilitie...

Launch new products from idea to first customers. Use when launching products, finding early adopters, building launch w...

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, S...

- 메타 스킬은 정보를 객관적으로 바라보게 해줘서 정보의 분류나 성질을 잘 파악할 수 있게 한다. 따라서 [[생각 정리]]를 도와준다.

跨階段全域共用技能。適用於所有 SSDLC 開發階段的通用工具，包含版本控制、多 Agent 協作、程式碼差異同步、自主迭代研究與 TDD 流程。

PRD 驱动的任务调度与技能管理专家。接收完整 PRD/需求文档，负责拆解业务、选择技术栈、路由到合适的专业 Skill，并维护从方案到落地的全流程。

Use when the user wants help with academic papers or citations but it's unclear which specific workflow fits — reviewing...

Arquitecto de Soluciones Principal y Consultor Tecnológico de Andru.ia. Diagnostica y traza la hoja de ruta óptima para...

Entry-point navigator for Databricks AppKit + Lakebase development. Routes tasks to the correct skill based on keyword d...

Use when the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific workflo...

Úsala cuando el estudiante pida la skill 00 o la base del proyecto. Prepara tokens de tema, configuración, tipos, inicia...

Review code for quality, security, and best practices. Use when the user asks for code review, wants feedback on their c...

Before diving into tool-calling patterns, structured outputs, and JSON accuracy metrics, you'll build the skill that wil...

Create your model-alignment skill from TRL documentation before learning DPO theory

Create your LLMOps data engineering skill in one prompt, then learn to improve it throughout the chapter

Create a reusable skill for evaluating fine-tuned models, benchmarking performance, and detecting quality regressions

Create your llmops-fine-tuner skill from Unsloth documentation before learning fine-tuning theory

Create your agent-integration skill from OpenAI SDK and LiteLLM documentation before learning framework integration

Create your model-serving skill from Ollama documentation before learning deployment theory

Create your OpenAI Apps SDK skill in one prompt, then learn to improve it throughout the chapter

Create your ChatKit Server skill in one prompt, then learn to improve it throughout the chapter

Create your Claude Agent SDK skill in one prompt, then learn to improve it throughout the chapter

Create your cloud security skill in one prompt, then learn to improve it throughout the chapter

Create your Dapr deployment skill in one prompt, then learn to improve it throughout the chapter

Create your Docker deployment skill in one prompt, then learn to improve it throughout the chapter

Create your agent-evals skill from official documentation before learning evaluation concepts. This skill-first approach...

Create your FastAPI skill in one prompt, then learn to improve it throughout the chapter

Create your GitOps deployment skill in one prompt, then learn to improve it throughout the chapter

Create your Helm chart skill in one prompt, then learn to improve it throughout the chapter

Create your Kubernetes deployment skill in one prompt, then learn to improve it throughout the chapter

Create your MCP server building skill in one prompt, then learn to improve it throughout the chapter

Create your observability and cost engineering skill in one prompt, then learn to improve it throughout the chapter

Create your operational excellence skill in one prompt, then learn to improve it throughout the chapter

Create your RAG skill in one prompt, then learn to improve it throughout the chapter

Create your agent-tdd skill in one prompt, then learn to improve it throughout the chapter

GenAI agent skill navigator for the `genai-agents/` folder. Start here to route agent-building, MLflow GenAI, tracing, D...

Extend your existing Dapr skill with actor and workflow patterns using official documentation

Consolidate all Part 8 skills into a production-ready llmops-fine-tuner skill

Plan and run the full API-first GTM chain - the orchestrator (step 00) that turns an ICP description plus optional budge...

Dung khi can ke hoach marketing tong the cho mot ky — muc tieu, phan khuc, kenh, ngan sach, timeline, KPI va ma tran rui...

Use when the user needs an overall marketing plan for a period — objectives, segments, positioning, channel mix, content...

[00] META. Orchestrate skills into dynamic chains for complex tasks. Analyzes the task, discovers available skills, buil...

> 도메인: devian-upm-samples

Use when any agent or downstream skill needs Unity Catalog schemas and managed volumes (knowledge_sources, agent_outputs...

Inspect an unfamiliar software workspace and create or refresh a compact evidence index at .patpat/context-graph.json. U...

Validate messaging consistency across website, GitHub repos, and local documentation generating read-only discrepancy re...

[00] TnR ABSOLUTE RIGOR — Systemic Verification Doctrine. Forced cognitive exertion for high-stakes investigations. Mand...

Use when you need to generate a checklist document with embedded commands inventory, following the embedded template exa...

Currently the esper workflow has two commit-related commands:

Use when you need to generate a checklist document with Java system prompts, following the embedded template exactly and...

Use when you need to generate a checklist document with embedded agents inventory, following the embedded template exact...

Use when you need to install the embedded robot agents into either .cursor/agents or .claude/agents, selecting the desti...

Use when you need to generate a checklist document with Java system prompts from skills.xml, following the embedded sect...

Use when you need to install the embedded project commands into command directories (.github/commands, .claude/commands,...

The current esper workflow goes straight from idea to plan (/esper:plan or /esper:fix). There is no structured way to in...

Use when you need to install the embedded robot agents into either .cursor/agents or .claude/agents, selecting the desti...

Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response,...

Use when deriving a Databricks Agent Spec and Agent Tool Plan from docs/design_prd.md before building Track A agents. Co...

专门用于在项目初期或重大功能迭代时进行技术栈选择与方案评估。支持根据 PRD 自动生成 2-3 套对比方案，涵盖前端、后端、数据库及中间件，并提供优劣势分析（性能、SEO、开发成本、可维护性）和最终选型建议。

专用于在 GitHub 上搜索现有的开源库、工具、MCP Server 或最佳实践代码。当你想在开始开发前查找是否有“现成的轮子”或参考案例时使用。

規劃與需求分析階段，負責原始需求釐清、口語需求正規化、需求追溯矩陣建置、Skill 複選與階段交付物定義。

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying...

Scaffold new Databricks AppKit applications using the Databricks CLI and Agent Skills. Creates blank or plugin-enabled A...

Automatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries f...

Use when starting a new custom agent project on Databricks Apps. Clone the agent-openai-agents-sdk template, run quickst...

Scaffolds a complete .NET solution following Clean Architecture principles with proper layer separation (API, Applicatio...

Build custom LLM evaluation pipelines using the OpenJudge framework. Covers selecting and configuring graders (LLM-based...

Grain definition patterns for fact tables during the Gold layer design phase. Use when choosing grain types (transaction...

The qualification gate of the GTM chain - judges every discovered company against the client's ICP before any paid enric...

Dung khi can lich dang bai cho ca thang — chot content pillar va ti le, xep bai theo ngay va khung gio, ma tran tai su d...

[01] META. Сканирует доступные skills, создает план выполнения и идет шаг за шагом с подтверждением каждого этапа. Trigg...

Use when starting any new GenAI agent project on Databricks. Covers MLflow 3.x GenAI setup: install dependencies, enable...

Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files...

> 도메인: devian-upm-samples

Use when you need to version, manage, or load prompts for any GenAI agent on Databricks. Covers how to register prompts...

B2B company discovery and list building via the Prospeo search API. Use when the user wants to find companies from an IC...