Claude Octopus Agent Catalog
> *32 specialized personas, infinite possibilities. But which one grabs YOUR problem?* π
MCP get_skill({ skillId: "claude-octopus-agent-catalog-2c210acc" })Use this skill with your agent
Create a free account and connect via MCP
# Claude Octopus Agent Catalog
> *32 specialized personas, infinite possibilities. But which one grabs YOUR problem?* π
**Note on Permissions:** Current releases prompt before background provider execution so you can approve Codex or Gemini usage explicitly.
---
## TL;DR - Which Tentacle Do I Need?
| When You Want To... | Reach For This Tentacle | Why This One? |
|---------------------|-------------------------|---------------|
| Design a REST/GraphQL API | `backend-architect` | Microservices maestro |
| Find security vulnerabilities | `security-auditor` | OWASP whisperer |
| Debug failing tests | `debugger` | Stack trace detective |
| Implement with TDD | `tdd-orchestrator` | Red-green-refactor guru |
| Review code quality | `code-reviewer` | Best practices enforcer |
| Write Python code | `python-pro` | Pythonic perfection |
| Write TypeScript | `typescript-pro` | Type safety fanatic |
| Design database schema | `database-architect` | Data modeling master |
| Research AI/LLM patterns | `ai-engineer` | Prompt engineering pro |
| Optimize performance | `performance-engineer` | Latency hunter |
| Synthesize user research | `ux-researcher` | Empathy tentacle π |
| Develop business strategy | `strategy-analyst` | Framework master π |
| Write literature review | `research-synthesizer` | Knowledge weaver π |
| Draft research papers | `academic-writer` | Citation ninja π |
| Create exec summaries | `exec-communicator` | Boardroom whisperer π |
| Write PRDs/user stories | `product-writer` | Requirements master π |
| Plan marketing campaigns | `marketing-strategist` | Growth funnel guru π |
| Build financial models | `finance-analyst` | Spreadsheet surgeon π |
| Review compliance/GDPR | `legal-compliance-advisor` | Regulatory navigator π |
| Design UI/UX systems | `ui-ux-designer` | Design intelligence π |
**Still unsure?** Just describe what you need - Claude Octopus auto-routes to the right tentacle! π¦
Knowledge-worker personas for researchers, consultants, and product managers are also included. [See Knowledge Workers Guide β](KNOWLEDGE-WORKERS.md)
---
## Table of Contents
1. [By Development Phase](#by-development-phase) - Double Diamond workflow
2. [By Domain](#by-domain) - Backend, Frontend, Quality, Ops
3. [Knowledge Work](#knowledge-work) - Research, consulting, writing
4. [Top 10 Tentacles](#top-10-tentacles) - The heavy hitters
5. [Cost Tiers](#cost-tiers) - Token budget awareness
6. [Common Workflows](#common-workflows) - Multi-tentacle patterns
7. [The Principles (Don't Invoke Directly)](#the-principles-internal-use-only) - Quality checklists
8. [Decision Tree](#decision-tree) - When all else fails
---
## By Development Phase
Claude Octopus follows the **Double Diamond** methodology:
```
DISCOVER DEFINE DEVELOP DELIVER
(probe) (grasp) (tangle) (ink)
\ / \ / \ / \ /
\ π / \ π― / \ π§ / \ β
/
\ π¦ / \ / \ π¦ / \ /
\ / \ / \ / \ /
\/ \/ \/ \/
Diverge then Converge to Diverge with Converge to
converge problem solutions delivery
```
### π Probe Phase: Research & Discovery
**Use when:** Starting a project, exploring options, gathering requirements
| Tentacle | Superpower | Example Prompt |
|----------|------------|----------------|
| `ai-engineer` | LLM/RAG patterns, prompt engineering | "Research OAuth 2.0 patterns for multi-tenant SaaS" |
| `business-analyst` | Requirements, metrics, stakeholder analysis | "Analyze user authentication requirements" |
| `context-manager` | Multi-agent coordination | "Coordinate research across multiple domains" |
**Pro tip:** Probe tentacles are cheap (sonnet/inherit) - fire liberally!
---
### π― Grasp Phase: Architecture & Design
**Use when:** Planning architecture, defining system design, creating blueprints
| Tentacle | Superpower | Example Prompt |
|----------|------------|----------------|
| `backend-architect` β | API design, microservices, distributed systems | "Design a REST API for user authentication" |
| `frontend-developer` | React 19, Next.js 15, UI/UX patterns | "Design component architecture for dashboard" |
| `database-architect` | Schema design, migrations, normalization | "Design user and session tables" |
| `cloud-architect` | AWS/GCP/Azure, IaC, cost optimization | "Plan multi-region deployment" |
| `graphql-architect` | Federation, resolvers, schema design | "Design GraphQL schema for e-commerce" |
**Pro tip:** These tentacles are premium (opus/inherit) - they're worth it for architecture decisions.
---
### π§ Tangle Phase: Development & Implementation
**Use when:** Writing code, implementing features, building solutions
| Tentacle | Superpower | Example Prompt |
|----------|------------|----------------|
| `tdd-orchestrator` β | Test-driven development, red-green-refactor | "Implement user registration with TDD" |
| `debugger` β | Error analysis, stack traces, root cause | "Debug JWT validation failures" |
| `devops-troubleshooter` | K8s debugging, log analysis, infra | "Fix deployment issues in staging" |
| `python-pro` | Python 3.12+, FastAPI, async | "Implement FastAPI authentication" |
| `typescript-pro` | Advanced types, generics, strict mode | "Implement TypeScript SDK" |
**Pro tip:** Tangle has a **75% quality gate** - multiple tentacles validate before delivery.
---
### β
Ink Phase: Review & Delivery
**Use when:** Code review, security audit, performance optimization, shipping
| Tentacle | Superpower | Example Prompt |
|----------|------------|----------------|
| `code-reviewer` β | Best practices, architecture review | "Review authentication module" |
| `security-auditor` β | OWASP, DevSecOps, threat modeling | "Audit for SQL injection vulnerabilities" |
| `test-automator` | Unit/integration/E2E test generation | "Generate test coverage for auth" |
| `performance-engineer` | Profiling, benchmarking, Core Web Vitals | "Find N+1 query issues" |
| `deployment-engineer` | GitHub Actions, ArgoCD, GitOps | "Set up CI/CD pipeline" |
**Pro tip:** Ink tentacles work with the `squeeze` command for adversarial review!
---
## By Domain
### Backend Development π
```
General Backend β backend-architect (inherit - adapts to complexity)
Database Focus β database-architect (opus - critical decisions)
GraphQL API β graphql-architect (opus - schema design)
Python Backend β python-pro (opus - advanced patterns)
Node.js Backend β typescript-pro (opus - type safety)
```
### Frontend Development π¨
```
React/Next.js β frontend-developer (inherit - adapts)
TypeScript β typescript-pro (opus - complex types)
Performance β performance-engineer (inherit - profiling)
```
### Quality & Security π‘οΈ
```
Code Quality β code-reviewer (opus - comprehensive)
Security β security-auditor (opus - critical)
Testing β test-automator (sonnet - generation)
Performance β performance-engineer (inherit - profiling)
```
### Operations & Infrastructure βοΈ
```
Cloud/AWS/GCP β cloud-architect (opus - critical decisions)
Kubernetes/Docker β deployment-engineer (haiku - fast)
Troubleshooting β devops-troubleshooter (sonnet - specialized)
Incidents β incident-responder (sonnet - SRE)
```
### Documentation & Diagrams π
```
Technical Docs β docs-architect (sonnet - writing)
Flowcharts β mermaid-expert (haiku - simple)
```
---
## Knowledge Work
> *When your deliverable isn't code, but crystallized knowledge.* π
Claude Octopus also includes specialized agents for researchers, consultants, designers, marketers, and product managers.
### π― UX Research
```
User interviews β ux-researcher (opus - synthesis)
Journey mapping β ux-researcher (opus - empathy)
Pain points β ux-researcher (opus - definition)
```
### π Strategy & Consulting
```
Market analysis β strategy-analyst (opus - frameworks)
Business cases β strategy-analyst (opus - quantification)
Exec summaries β exec-communicator (sonnet - clarity)
```
### π Academic & Research
```
Literature review β research-synthesizer (opus - synthesis)
Gap analysis β research-synthesizer (opus - identification)
Academic writing β academic-writer (sonnet - formatting)
```
### π Product Management
```
PRDs & specs β product-writer (sonnet - clarity)
User stories β product-writer (sonnet - structure)
Acceptance criteriaβ product-writer (sonnet - precision)
```
### π£ Marketing & Growth
```
Campaign planning β marketing-strategist (sonnet - channels)
Growth funnels β marketing-strategist (sonnet - optimization)
SEO & content β marketing-strategist (sonnet - strategy)
```
### π° Finance & Pricing
```
Financial models β finance-analyst (sonnet - projections)
Unit economics β finance-analyst (sonnet - metrics)
Pricing strategy β finance-analyst (sonnet - optimization)
```
### π¨ UI/UX Design
```
Design systems β ui-ux-designer (sonnet - BM25 intelligence)
Color & typography β ui-ux-designer (sonnet - data-driven)
Component specs β ui-ux-designer (sonnet - handoff)
```
### βοΈ Legal & Compliance
```
GDPR/CCPA review β legal-compliance-advisor (sonnet - regulations)
SOC 2 readiness β legal-compliance-advisor (sonnet - controls)
Contract review β legal-compliance-advisor (sonnet - risk)
```
**Deep dive:** See the full [Knowledge Workers Guide β](KNOWLEDGE-WORKERS.md)
---
## Top 10 Tentacles
The heavy hitters, based on real-world usage:
### 1. ποΈ backend-architect
**Model:** inherit (adapts to complexity)
**Superpower:** API design, microservices architecture, distributed systems
**When to use:**
- Designing REST/GraphQL/gRPC APIs
- Architecting microservices systems
- Defining service boundaries and communication patterns
- Planning event-driven architectures
**Avoid if:**
- Simple CRUD operations (just implement directly)
- Frontend-only work (use `frontend-developer`)
- Database schema design (use `database-architect` first)
---
### 2. π code-reviewer
**Model:** opus (complex reasoning)
**Superpower:** Code quality, best practices, architecture review
**When to use:**
- PR reviews (pairs with `/octo:review` skill)
- Architecture validation
- Best practices enforcement
**Avoid if:**
- Security-focused review (use `security-auditor`)
- Performance-focused review (use `performance-engineer`)
---
### 3. π debugger
**Model:** sonnet (specialized analysis)
**Superpower:** Error analysis, stack traces, root cause identification
**When to use:**
- Failing tests or production errors
- Understanding cryptic stack traces
- Root cause analysis
**Avoid if:**
- Infrastructure issues (use `devops-troubleshooter`)
---
### 4. π‘οΈ security-auditor
**Model:** opus (critical analysis)
**Superpower:** OWASP Top 10, vulnerability scanning, threat modeling
**When to use:**
- Security audits (pairs with `squeeze` command)
- Finding vulnerabilities in auth/payment code
- OWASP compliance checks
---
### 5. π§ͺ tdd-orchestrator
**Model:** opus (multi-step reasoning)
**Superpower:** Test-driven development, red-green-refactor
**When to use:**
- Building new features test-first
- Comprehensive test coverage
- Refactoring with confidence
---
### 6. π¨ frontend-developer
**Model:** inherit (adapts to complexity)
**Superpower:** React 19, Next.js 15, modern UI patterns
**When to use:**
- React component architecture
- Server Components and Client Components
- State management decisions
---
### 7. ποΈ database-architect
**Model:** opus (critical decisions)
**Superpower:** Schema design, migrations, query optimization
**When to use:**
- New database schema design
- Migration planning
- Query performance issues
---
### 8. β‘ performance-engineer
**Model:** inherit (adapts to profiling depth)
**Superpower:** Profiling, benchmarking, Core Web Vitals
**When to use:**
- N+1 query hunting
- API response time optimization
- Memory leak detection
---
### 9. π python-pro
**Model:** opus (advanced patterns)
**Superpower:** Python 3.12+, FastAPI, async programming
**When to use:**
- Python backend development
- FastAPI/Django/Flask services
- Async/await patterns
---
### 10. π typescript-pro
**Model:** opus (complex type systems)
**Superpower:** Advanced types, generics, strict TypeScript
**When to use:**
- Advanced TypeScript type definitions
- Generic types and utility type creation
- Strict TypeScript configuration
---
## Cost Tiers
### π Premium (Opus)
Most expensive, use for critical decisions.
`code-reviewer`, `tdd-orchestrator`, `database-architect`, `security-auditor`, `cloud-architect`, `python-pro`, `typescript-pro`, `graphql-architect`
### π° Standard (Sonnet)
Mid-range, good for focused tasks.
`debugger`, `test-automator`, `docs-architect`, `business-analyst`, `devops-troubleshooter`, `incident-responder`, `ui-ux-designer`, `marketing-strategist`, `finance-analyst`, `legal-compliance-advisor`
### π΅ Trivial (Haiku)
Cheapest, use for simple tasks.
`mermaid-expert`, `deployment-engineer`
### π Adaptive (Inherit)
Auto-selects based on task complexity.
`backend-architect`, `frontend-developer`, `ai-engineer`, `performance-engineer`, `context-manager`
---
## Common Workflows
### π New Feature Development
```
1. Research β ai-engineer
2. Design β backend-architect + database-architect
3. Implement β tdd-orchestrator
4. Review β code-reviewer + security-auditor
```
### π₯ Production Bug Fix
```
1. Respond β incident-responder
2. Debug β debugger
3. Fix β backend-architect
4. Validate β test-automator
```
### β‘ Performance Optimization
```
1. Profile β performance-engineer
2. Database β database-architect
3. Validate β performance-engineer
```
### π‘οΈ Security Audit
```
1. Scan β security-auditor
2. Fix β backend-architect
3. Validate β security-auditor
```
---
## The Principles (Internal Use Only)
β οΈ **Don't invoke these directly!** They're quality checklists used BY other tentacles.
| Principle | Used By | Purpose |
|-----------|---------|---------|
| `general` | code-reviewer | Correctness, reliability |
| `security` | security-auditor | OWASP, auth patterns |
| `performance` | performance-engineer | Profiling, caching |
| `maintainability` | code-reviewer | Readability, testing |
---
## Decision Tree
See [agent-decision-tree.md](agent-decision-tree.md) for visual flowcharts.
**Quick version:**
```
What phase are you in?
ββ Research/Explore β PROBE tentacles
ββ Design/Plan β GRASP tentacles
ββ Build/Code β TANGLE tentacles
ββ Review/Ship β INK tentacles
```
---
## Quick Links
- **README:** [../README.md](../README.md)
- **Decision Tree:** [agent-decision-tree.md](agent-decision-tree.md)
- **Monthly Review:** [monthly-agent-review.md](monthly-agent-review.md)
- **Personas:** [../agents/personas/](../agents/personas/)
---
<p align="center">
π <em>"39 tentacles, one purpose: your code, done right."</em> π
</p>Related Skills
More skills in Agent Orchestration
1. Product type search β what design patterns fit this product?
Design UI/UX systems with style guides, palettes, typography, and component specs for new interfaces
Acp Router
Route plain-language requests for Claude Code, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or explicit ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). For coding-agent thread requests, read this skill first, then use only `sessions_spawn` for thread creation. Codex chat binding defaults to the native Codex app-server plugin unless ACP is explicit or background spawn needs ACP.
Add New Safe Output Type
Adding a New Safe Output Type to GitHub Agentic Workflows
Agent Governance
Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tools (APIs, databases, file systems) - Implementing policy-based access controls for agent tool usage - Adding semantic intent classification to detect dangerous prompts - Creating trust scoring systems for multi-agent workflows - Building audit trails for agent actions and decisions - Enforcing rate limits, content filters, or tool restrictions on agents - Working with any agent framework (PydanticAI, CrewAI, OpenAI Agents, LangChain, AutoGen)
Agentic Development
Build AI agents with Pydantic AI (Python) and Claude SDK (Node.js)
Agentic Workflows
Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.
Explore Other Categories
Skills from other categories with shared topics
Anthropic Brand Styling
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
API Design Principles
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.
Azure Aks Agent Skill
Azure Aks Agent Skill linked from Juliano Barbosa Claude Code Skills, with the upstream skill instructions available on GitHub.