PaperclipOrg
Claude Agent Skill · by Aradotso

Agency Agents Ai Specialists

Install Agency Agents Ai Specialists skill for Claude Code from aradotso/trending-skills.

Install
Terminal · npx
$npx skills add https://github.com/obra/superpowers --skill test-driven-development
Works with Paperclip

How Agency Agents Ai Specialists fits into a Paperclip company.

Agency Agents Ai Specialists drops into any Paperclip agent that handles this kind of work. Assign it to a specialist inside a pre-configured PaperclipOrg company and the skill becomes available on every heartbeat — no prompt engineering, no tool wiring.

S
SaaS FactoryPaired

Pre-configured AI company — 18 agents, 18 skills, one-time purchase.

$27$59
Explore pack
Source file
SKILL.md387 lines
Expand
---name: agency-agents-ai-specialistsdescription: A collection of specialized AI agent personalities for Claude Code, Cursor, Aider, Windsurf, and other AI coding tools — covering engineering, design, marketing, sales, and more.triggers:  - set up agency agents  - install AI agent personalities  - use specialized AI agents  - activate frontend developer agent  - add agency agents to cursor  - configure AI specialists for my project  - install agent prompts for Claude Code  - use the agency agent collection--- # 🎭 Agency Agents — AI Specialist Personalities > Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. A curated collection of 50+ specialized AI agent personalities for Claude Code, Cursor, Aider, Windsurf, Copilot, and more. Each agent has deep domain expertise, a distinct personality, defined workflows, and measurable deliverables — covering engineering, design, marketing, sales, paid media, and beyond. --- ## Installation ### Prerequisites ```bashgit clone https://github.com/msitarzewski/agency-agents.gitcd agency-agents``` ### Claude Code (Recommended) ```bash# Copy all agents to Claude's agents directorycp -r agency-agents/* ~/.claude/agents/ # Or symlink for auto-updatesln -s /path/to/agency-agents ~/.claude/agents/agency``` Then in any Claude Code session:```Hey Claude, activate Frontend Developer mode and help me build a React component``` ### All Other Tools (Interactive Installer) ```bash# Step 1: Generate integration files for all supported tools./scripts/convert.sh # Step 2: Auto-detect installed tools and install interactively./scripts/install.sh # Or target a specific tool./scripts/install.sh --tool cursor./scripts/install.sh --tool copilot./scripts/install.sh --tool aider./scripts/install.sh --tool windsurf``` ### Manual per Tool | Tool | Install path ||------|-------------|| Claude Code | `~/.claude/agents/` || Cursor | `.cursor/rules/` in project root || Copilot | `.github/copilot-instructions.md` || Aider | `.aider.conf.yml` or pass via `--system-prompt` || Windsurf | `.windsurf/rules/` in project root | --- ## Agent Roster ### Engineering Division ```engineering/engineering-frontend-developer.md       React/Vue/Angular, UI, Core Web Vitalsengineering/engineering-backend-architect.md        API design, databases, scalabilityengineering/engineering-mobile-app-builder.md       iOS/Android, React Native, Flutterengineering/engineering-ai-engineer.md              ML models, AI integration, data pipelinesengineering/engineering-devops-automator.md         CI/CD, infra automation, cloud opsengineering/engineering-rapid-prototyper.md         MVPs, POCs, hackathon speedengineering/engineering-senior-developer.md         Laravel/Livewire, advanced patternsengineering/engineering-security-engineer.md        Threat modeling, secure code reviewengineering/engineering-code-reviewer.md            PR reviews, code quality gatesengineering/engineering-database-optimizer.md       PostgreSQL/MySQL tuning, slow queriesengineering/engineering-git-workflow-master.md      Branching, conventional commitsengineering/engineering-software-architect.md       System design, DDD, trade-off analysisengineering/engineering-sre.md                      SLOs, error budgets, chaos engineeringengineering/engineering-incident-response-commander.md  Incident management, post-mortemsengineering/engineering-technical-writer.md         Developer docs, API referenceengineering/engineering-data-engineer.md            Data pipelines, lakehouse, ETL/ELT``` ### Design Division ```design/design-ui-designer.md                        Visual design, component librariesdesign/design-ux-researcher.md                      User testing, behavior analysisdesign/design-ux-architect.md                       CSS systems, technical UXdesign/design-brand-guardian.md                     Brand identity and consistencydesign/design-whimsy-injector.md                    Micro-interactions, delight, Easter eggsdesign/design-image-prompt-engineer.md              Midjourney/DALL-E/SD promptsdesign/design-inclusive-visuals-specialist.md       Representation, bias mitigation``` ### Marketing, Sales & Paid Media ```marketing/marketing-growth-hacker.mdmarketing/marketing-content-creator.mdpaid-media/paid-media-ppc-strategist.mdpaid-media/paid-media-creative-strategist.mdsales/sales-outbound-strategist.mdsales/sales-deal-strategist.mdsales/sales-discovery-coach.md``` --- ## Using Agents in Claude Code ### Activating a Single Agent ```# In Claude Code chat:Activate the Backend Architect agent and help me design a REST API for a multi-tenant SaaS app.``` ### Using Multiple Agents in Sequence ```# First, design the systemActivate the Software Architect agent. Design the domain model for an e-commerce platform. # Then implementNow activate the Senior Developer agent and implement the Order aggregate in Laravel. # Then reviewActivate the Code Reviewer agent and review the implementation above.``` ### Referencing an Agent File Directly ```bash# Pass an agent as a system prompt in Claude CLIclaude --system-prompt "$(cat ~/.claude/agents/engineering-frontend-developer.md)" \  "Build a responsive product card component in React with Tailwind CSS"``` --- ## Using Agents in Cursor After running `./scripts/install.sh --tool cursor`, agent rules land in `.cursor/rules/`. Reference them in chat: ```@engineering-frontend-developer Build a data table component with sorting and pagination.``` Or set a default rule in `.cursor/rules/default.mdc`: ```markdown---alwaysApply: true--- You are operating as the Senior Developer agent from The Agency.Refer to .cursor/rules/engineering-senior-developer.md for your full persona and workflows.``` --- ## Using Agents with Aider ```bash# Use a single agent as the system promptaider --system-prompt "$(cat agency-agents/engineering/engineering-security-engineer.md)" # Or reference in .aider.conf.ymlecho "system-prompt: agency-agents/engineering/engineering-devops-automator.md" >> .aider.conf.yml``` --- ## Using Agents in Windsurf ```bash./scripts/install.sh --tool windsurf# Agents are written to .windsurf/rules/``` Activate in chat:```Use the UX Architect agent rules from .windsurf/rules/ to audit my CSS architecture.``` --- ## Real Workflow Examples ### Full-Stack Feature with Multiple Agents ```bash# 1. Architecture phasecat > task.md << 'EOF'I need to add real-time notifications to my Node.js + React app.Users should see in-app alerts and optionally receive email digests.EOF # Invoke Software Architectclaude --system-prompt "$(cat ~/.claude/agents/engineering-software-architect.md)" < task.md # 2. Backend implementationclaude --system-prompt "$(cat ~/.claude/agents/engineering-backend-architect.md)" \  "Implement the notification service based on the architecture above using PostgreSQL LISTEN/NOTIFY and Socket.io" # 3. Frontend implementationclaude --system-prompt "$(cat ~/.claude/agents/engineering-frontend-developer.md)" \  "Build the React notification bell component that connects to the Socket.io feed" # 4. Security reviewclaude --system-prompt "$(cat ~/.claude/agents/engineering-security-engineer.md)" \  "Review the notification system implementation for security issues"``` ### Code Review Workflow ```bash# Generate a diff and pipe to the Code Reviewer agentgit diff main..feature/payment-integration | \  claude --system-prompt "$(cat ~/.claude/agents/engineering-code-reviewer.md)" \  "Review this PR diff. Focus on security, correctness, and maintainability."``` ### Database Optimization ```bash# Paste slow query log and activate Database Optimizerclaude --system-prompt "$(cat ~/.claude/agents/engineering-database-optimizer.md)" << 'EOF'Here is a slow query from our PostgreSQL logs (avg 4200ms): SELECT u.*, p.*, o.*FROM users uLEFT JOIN profiles p ON p.user_id = u.idLEFT JOIN orders o ON o.user_id = u.idWHERE u.created_at > NOW() - INTERVAL '30 days'ORDER BY o.created_at DESC; Table sizes: users=2M rows, orders=18M rows. No indexes on created_at columns.EOF``` ### Incident Response ```bash# Structured incident kick-offclaude --system-prompt "$(cat ~/.claude/agents/engineering-incident-response-commander.md)" << 'EOF'SEV-1 INCIDENT: Payment processing returning 503 errors since 14:32 UTC.Error rate: 94%. Affected: checkout, subscription renewals.Recent deploys: payment-service v2.4.1 at 14:15 UTC.EOF``` --- ## Creating Custom Agents Agent files follow a consistent markdown structure: ```markdown# 🎯 Agent Name ## IdentityYou are [Name], [role] at The Agency... ## Core Mission[What this agent optimizes for] ## Personality & Communication Style- [Trait 1]- [Trait 2] ## Workflows ### [Workflow Name]1. [Step 1]2. [Step 2] ## Deliverables- [Concrete output 1]- [Concrete output 2] ## Success Metrics- [Measurable outcome]``` Save custom agents to `agency-agents/custom/` and re-run `./scripts/convert.sh` to generate tool integrations. --- ## Contributing New Agents ```bash# Fork and clonegit clone https://github.com/YOUR_USERNAME/agency-agents.git # Create your agent in the appropriate divisioncp engineering/engineering-senior-developer.md \   engineering/engineering-YOUR-SPECIALTY.md # Edit the file, then test itclaude --system-prompt "$(cat engineering/engineering-YOUR-SPECIALTY.md)" \  "Give me a sample deliverable to demonstrate your capabilities" # Submit a PRgit checkout -b agent/your-specialtygit add engineering/engineering-YOUR-SPECIALTY.mdgit commit -m "feat: add Your Specialty agent"git push origin agent/your-specialty``` --- ## Troubleshooting **Agents not found in Claude Code**```bashls ~/.claude/agents/# If empty, re-run:cp -r /path/to/agency-agents/* ~/.claude/agents/``` **`convert.sh` fails with permission error**```bashchmod +x scripts/convert.sh scripts/install.sh./scripts/convert.sh``` **Cursor not picking up agent rules**```bash# Rules must be in project root .cursor/rules/ls .cursor/rules/# Re-run installer targeting cursor./scripts/install.sh --tool cursor``` **Agent personality not activating**- Be explicit: *"Activate the Frontend Developer agent"* rather than just referencing the topic- Paste the agent file contents directly into the system prompt if tool integration isn't working- For Claude Code, confirm agents directory: `claude config get agentsDir` **Agent conflicts when using multiple**- Activate one agent per conversation session- For multi-agent workflows, use separate sessions or Claude Code's subagent feature- Sequence agents explicitly: architect → implement → review --- ## Project Structure ```agency-agents/├── engineering/          # 23 engineering specialist agents├── design/               # 8 design specialist agents├── marketing/            # Marketing and growth agents├── sales/                # 8 sales specialist agents├── paid-media/           # 7 paid media specialist agents├── scripts/│   ├── convert.sh        # Generate tool-specific integration files│   └── install.sh        # Interactive installer (auto-detects tools)└── README.md``` --- ## Key Facts - **License**: MIT- **51,000+ stars** — battle-tested by a large community- **No API keys required** — agents are prompt files, not services- **Tool-agnostic** — works with any LLM tool that accepts system prompts- **Extensible** — add custom agents following the same markdown pattern- **PRs welcome** — the roster grows through community contributions