AI Agent Builder
Skill VerificadoBuild AI agents with tools, memory, and multi-step reasoning - ChatGPT, Claude, Gemini integration patterns
This skill provides in-depth explanations and examples of AI agent architecture, including core components, agent types, tool definitions, common tool categories, and platform integration patterns for Slack, Telegram, and web interfaces. It details various memory patterns and multi-step reasoning workflows like ReAct and planning agents, offering concrete examples of agent output for specific use cases.
Documentation
- info:Configuration & parameter referenceWhile tool parameters and memory types are documented, specific configuration options for the agent architecture and platform integrations lack explicit default values or precedence order.
Maintenance
- warning:Commit recencyNo commits have been made to the default branch in the last 12 months (pushedAt: n/a), indicating potential unmaintained status.
Practical Utility
- info:Edge casesWhile the skill covers various agent types and components, explicit documentation of failure modes and recovery paths for agent design is not present.
Instalação
npx skills add claude-office-skills/skillsExecuta a CLI skills da Vercel (skills.sh) via npx — requer Node.js localmente e pelo menos um agente compatível com skills instalado (Claude Code, Cursor, Codex, …). Pressupõe que o repositório siga o formato agentskills.io.
Extensões similares
Debate Simulator
65Extension from onewave-ai/claude-skills
Blind Spot Detective
99Systematically identify what's missing in non-fiction writing—both blind spots (inherent limitations) and blank spots (gaps that could be addressed). Use before finalizing non-fiction or when feedback feels incomplete.
AI Product Strategy
98Help users define AI product strategy. Use when someone is building an AI product, deciding where to apply AI in their product, planning an AI roadmap, evaluating build vs buy for AI capabilities, or figuring out how to integrate AI into existing products.
Academic Paper Review Skill
98Use this skill when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews covering methodology assessment, contribution evaluation, literature positioning, and constructive feedback generation. Trigger on queries involving paper URLs, uploaded PDFs, arXiv links, or requests like "review this paper", "analyze this research", "summarize this study", or "write a peer review".
Customer Journey Mapper
98Maps the full customer journey from first touch to advocacy. Generates a comprehensive customer-journey.md with all stages, touchpoints, emotions, pain points, opportunities, Mermaid diagrams, and metrics. Use when mapping customer experience, designing onboarding flows, identifying churn risks, or optimizing conversion funnels.
3D Graphics with Three.js
983D web graphics with Three.js (WebGL/WebGPU). Capabilities: scenes, cameras, geometries, materials, lights, animations, model loading (GLTF/FBX), PBR materials, shadows, post-processing (bloom, SSAO, SSR), custom shaders, instancing, LOD, physics, VR/XR. Actions: create, build, animate, render 3D scenes/models. Keywords: Three.js, WebGL, WebGPU, 3D graphics, scene, camera, geometry, material, light, animation, GLTF, FBX, OrbitControls, PBR, shadow mapping, post-processing, bloom, SSAO, shader, instancing, LOD, WebXR, VR, AR, product configurator, data visualization, architectural walkthrough, interactive 3D, canvas. Use when: creating 3D visualizations, building WebGL/WebGPU apps, loading 3D models, adding animations, implementing VR/XR, creating interactive graphics, building product configurators.