Architect
265Agent Claude Code
Design decisions, ADRs, technical specifications.
6,127 tagged Planning, measured the same way as everything else here.
Browse within: claude-code-plugin 139ai-coding 105spec-driven-development 87github-copilot 82agentic-workflow 62skills 58prompt-engineering 55agentic-coding 51Multi-Agent 48context-engineering 48agentic 45claude-code-skills 44workflow 44agent-orchestration 43
Agent Claude Code
Design decisions, ADRs, technical specifications.
Agent Claude Code
Plans a full course outline (chat-first) and prepares metadata and lesson scaffolding guidance. Use when the user asks to design a course.
rhofkens/business-idea-multi-agent
Agent Claude Code
Use this agent when you need to create, review, or validate architecture and planning documents for AI applications that utilize the OpenAI Agents TypeScript SDK, OpenAI TypeScript SDK, or Vercel AI SDK. This includes system design documents, technical specifications, integration plans, and architectural decision…
Agent Claude Code
Pre-implementation requirements interviewer. Use BEFORE any non-trivial feature, refactor, or new project. Reads the codebase, asks 20-40 probing questions in structured rounds, and produces a bulletproof SPEC.md with testable acceptance criteria, exact files to modify, and a wiring checklist. Never writes…
walidboulanouar/n8n-claude-code-template
Agent Claude Code
Project setup wizard. Runs automatically when CLAUDE.md contains [NOT SET] fields — triggered by any greeting (hey, hello, start, let's go, etc.). Asks 6 questions, fills CLAUDE.md and PRD.md, creates workflow stubs, then hands off to n8n-workflow-builder. Do NOT invoke manually — it triggers automatically on first…
Agent Claude Code
Use this agent when you need to create, review, or refine Product Requirements Documents (PRDs). This includes defining product features, user stories, acceptance criteria, success metrics, technical requirements, and stakeholder considerations. The agent excels at translating high-level product ideas into…
devfullcycle/mba-ia-greenfield-project
Agent Claude Code
Reads prior-phase planning documents and extracts the Conventions to Match bullets AND the Inherited TD Details (verbatim from each prior phase's context.md ## Decisions Detail section) AND the Inherited Deferred Capabilities (verbatim from each prior phase's context.md ## Non-UI / Deferred Capabilities rows with…
geekjourneyx/industry-research
Agent Claude Code
A research-planning agent that turns a business question into checkable claims and evidence plans. It can also prepare interview guidance when interviews are part of the research.
Agent Claude Code
Orchestrates the full relocation experience for clients moving into or out of a market. Handles community orientation, school research, vendor referrals, move logistics coordination, and the dozens of invisible decisions that make a relocation succeed or fail.
Agent Claude Code
Status: V1 design (2026-07-08), pre-implementation. Owner: infra. Related: issue-tracker.md, triage-labels.md, domain.md.
Agent Claude Code
Agent for researching latest specifications and making technical decisions. Activated during design, setup, module installation, and configuration file editing.
Agent Claude Code
Use sempre que o PO (Claude principal / usuário) quiser PLANEJAR, EXECUTAR ou TRIAR (bug) uma User Story / Bug do Foundation — ex.: "arquitete a US X", "planeje esta história", "implemente a US X", "triage o bug X". O Arquiteto é o ponto único de coordenação técnica: o PO fala SÓ com o Arquiteto, nunca com os…
Agent Claude Code
ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.
Agent Claude Code
Audits a feature plan PR before human review — checks spec.md and plan.md against the planning conventions in PLANNING.md and the constitution's allowlists. Reports findings; never modifies files. Invoke during Phase 2.5 (plan freeze) of the wordpress-feature skill, after scripts/open-plan-pr.sh opens the plan PR and…
AgiFlow/claude-code-prompt-analysis
Agent Claude Code
Use this agent when you need expert guidance on software architecture decisions, design patterns, system design trade-offs, technology stack selection, scalability considerations, or architectural refactoring strategies. Examples include:\n\n- User: 'I'm building a real-time chat application. Should I use WebSockets…
Agent Claude Code
Maps a codebase using team-based deep analysis with priority-driven agent assignments. Use after initial project setup, when pending-analysis memories appear, or periodically to refresh the knowledge graph.
Agent Claude Code
Use this agent to orchestrate contracted implementation planning, executable tests, and enabled infrastructure/development capabilities.
Agent Claude Code
A generic label ("code agent," "review agent") tells you the function but not the contract — how much scope it takes, what tools it has, what it never does. Naming each instrument and giving it a fixed lane (read-only vs. write-capable, which model tier, what it refuses to do) makes delegation legible: the composer…
Agent Claude Code
Turn a request into a shot-plan.json for a short (3–30s) design-led motion graphic. You run in two parts around the asset-sourcing step: Part 1 (plan) before sourcing, Part 2 (design) after. You do NOT write composition code — that's the Builder. Schema: references/shot-plan-ir.md.
Agent Claude Code
You analyse a project brief and produce a detailed generation plan. Your plan determines exactly what files, agents, skills, and infrastructure the scaffold-writer and claude-infra-writer will create.
AndreAlbuquerque/claude-config
Agent Claude Code
Visionary/strategy specialist. Rare — sits optionally above @discovery. Use only when the request is about product or company direction itself (not a scoped feature), uses explicit strategy vocabulary (vision, north star, 10x, why now, differentiation, positioning, game-changing, moonshot), or represents a genuine new…
Agent Claude CodeGemini CLI
Code analysis and design agent for reviewing existing code, debugging complex issues, and designing system architecture. Use when the user wants to understand or evaluate code without making changes. Examples: "Review the authentication module for security issues" "Why is this API endpoint returning 500 errors?"…
kasuken/github-copilot-superpowers
Agent Claude Code
Challenge assumptions and encourage critical thinking to ensure the best possible solution and outcomes.
Agent Claude Code
Agent "task-orchestrator" from kubiyabot/skill, covering core responsibilities, operational workflow, initial assessment phase, executor deployment phase and coordination phase.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: