morganmuli/metaskill
No description.
field: Developer tools workflow: CI/CD & deployData / ETLFrontend & designTesting & TDDPlanning & specs
stack: Shell
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
up to ~19.5k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Context hog · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add context7 -- npx -y @upstash/context7-mcp@latest $ claude mcp add sequential-thinking -- npx -y @modelcontextprotocol/server-sequential-thinking $ claude mcp add memory -- npx -y @modelcontextprotocol/server-memory $ claude mcp add postgres -- npx -y @modelcontextprotocol/server-postgres postgresql://localhost:5432/myapp $ claude mcp add playwright -- npx -y @playwright/mcp@latest $ npx degit morganmuli/metaskill/examples/data-science/.claude ./rig-metaskill # inspect, then merge into .claude/
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add context7 -- npx -y @upstash/context7-mcp@latest $ claude mcp add sequential-thinking -- npx -y @modelcontextprotocol/server-sequential-thinking $ claude mcp add memory -- npx -y @modelcontextprotocol/server-memory $ claude mcp add postgres -- npx -y @modelcontextprotocol/server-postgres postgresql://localhost:5432/myapp $ claude mcp add playwright -- npx -y @playwright/mcp@latest
$ npx degit morganmuli/metaskill/examples/data-science/.claude/skills/evaluate-model .claude/skills/evaluate-model $ npx degit morganmuli/metaskill/examples/data-science/.claude/skills/generate-report .claude/skills/generate-report $ npx degit morganmuli/metaskill/examples/data-science/.claude/skills/run-pipeline .claude/skills/run-pipeline $ npx degit morganmuli/metaskill/examples/fullstack-web/.claude/skills/api-test .claude/skills/api-test $ npx degit morganmuli/metaskill/examples/fullstack-web/.claude/skills/build-and-test .claude/skills/build-and-test $ npx degit morganmuli/metaskill/examples/fullstack-web/.claude/skills/deploy-preview .claude/skills/deploy-preview $ npx degit morganmuli/metaskill/examples/ios-app/.claude/skills/run-simulator .claude/skills/run-simulator
$ curl -fsSL --create-dirs -o .claude/agents/analyst.md https://raw.githubusercontent.com/morganmuli/metaskill/main/examples/data-science/.claude/agents/analyst.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/morganmuli/metaskill/main/examples/data-science/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/data-engineer.md https://raw.githubusercontent.com/morganmuli/metaskill/main/examples/data-science/.claude/agents/data-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/ml-engineer.md https://raw.githubusercontent.com/morganmuli/metaskill/main/examples/data-science/.claude/agents/ml-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/tech-lead.md https://raw.githubusercontent.com/morganmuli/metaskill/main/examples/data-science/.claude/agents/tech-lead.md $ curl -fsSL --create-dirs -o .claude/agents/backend-engineer.md https://raw.githubusercontent.<redacted>-web/.claude/agents/backend-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.<redacted>-web/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/devops-engineer.md https://raw.githubusercontent.<redacted>-web/.claude/agents/devops-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-engineer.md https://raw.githubusercontent.<redacted>-web/.claude/agents/frontend-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/tech-lead.md https://raw.githubusercontent.<redacted>-web/.claude/agents/tech-lead.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/morganmuli/metaskill/main/examples/ios-app/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/ios-engineer.md https://raw.githubusercontent.com/morganmuli/metaskill/main/examples/ios-app/.claude/agents/ios-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/tech-lead.md https://raw.githubusercontent.com/morganmuli/metaskill/main/examples/ios-app/.claude/agents/tech-lead.md $ curl -fsSL --create-dirs -o .claude/agents/test-engineer.md https://raw.githubusercontent.com/morganmuli/metaskill/main/examples/ios-app/.claude/agents/test-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/ui-designer.md https://raw.githubusercontent.com/morganmuli/metaskill/main/examples/ios-app/.claude/agents/ui-designer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (5)
| server | source | est. tokens |
|---|---|---|
| Context7 | npm | 1.2k |
| Sequential Thinking · "sequential-thinking" | npm | 900 |
| Memory (knowledge graph) · "memory" | npm | 2.6k |
| Postgres | npm | 600 |
| Playwright MCP · "playwright" | npm | 7.5k |
Skills (7)
Subagents (15)
| analyst model: sonnet | Use this agent when performing exploratory data analysis, creating visualizations, running statistical tests, analyzing experiment results, or generating reports. For example: profiling a new dataset, |
| code-reviewer model: sonnet | Use this agent when code changes need review before completion. For example: after implementing a data pipeline, after building a model training loop, after writing feature engineering code, before me |
| data-engineer model: sonnet | Use this agent when working with data ingestion, ETL pipelines, data validation, preprocessing, schema design, or data storage. For example: building a data loading pipeline from CSV/Parquet, adding p |
| ml-engineer model: sonnet | Use this agent when working with model architecture, training loops, loss functions, optimizers, hyperparameter tuning, experiment tracking, or model evaluation. For example: building a PyTorch model, |
| tech-lead model: opus | Use this agent when a complex task needs to be broken down, when multiple agents need coordination, or when the best approach for an ML/data science task is unclear. For example: implementing a new mo |
| backend-engineer model: sonnet | Use this agent when the task involves API endpoints, database schema design, Prisma migrations, authentication, authorization, server-side validation, middleware, or business logic. For example: creat |
| code-reviewer model: sonnet | Use this agent when code changes need to be reviewed before completion. For example: after implementing a feature, before merging a PR, when refactoring existing code, when a security-sensitive change |
| devops-engineer model: sonnet | Use this agent when the task involves Docker, docker-compose, CI/CD pipelines, GitHub Actions, environment variable management, deployment scripts, monitoring, logging infrastructure, or production re |
| frontend-engineer model: sonnet | Use this agent when the task involves React components, pages, hooks, client-side routing, styling with Tailwind CSS, form handling, client-side state management, or accessibility. For example: buildi |
| tech-lead model: opus | Use this agent when a complex task needs to be broken down into frontend, backend, and devops subtasks. For example: implementing a new feature end-to-end, planning a database schema change that affec |
| code-reviewer model: sonnet | Use this agent when code changes need review before completion. For example: after implementing a new feature, before merging a PR, when refactoring existing code, when evaluating an architecture deci |
| ios-engineer model: sonnet | Use this agent when SwiftUI views, data models, view models, networking, persistence, or business logic need to be implemented. For example: creating a new screen, adding a network API call, setting u |
| tech-lead model: opus | Use this agent when a complex task needs to be broken down, when multiple agents need coordination, or when the best approach is unclear. For example: implementing a new feature end-to-end, planning a |
| test-engineer model: sonnet | Use this agent when tests need to be written, debugged, or improved. For example: writing XCTest unit tests for a view model, creating XCUITest UI tests for a user flow, setting up mock services for t |
| ui-designer model: sonnet | Use this agent when UI/UX work is needed: creating custom SwiftUI components, implementing animations, fixing layout issues, polishing visual design, building a design system, or improving accessibili |
Similar rigs
ifitsmanu/claude-template
The best Claude Code setup template. 14 commands, 5 agents, 6 MCP servers, auto-formatting hooks. Based on Boris Cherny's workflow.
Fort Knox 17.2k tok · · Q32
affaan-m/agentshield
AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️
MCP Hoarder 60.2k tok · · Q15
imMamdouhaboammar/agent-kernel
Local governance, memory, failure lessons, and architecture guardrails for Claude Code, Codex, Cursor, Gemini CLI, and other AI coding agents.
MCP Hoarder 34.4k tok · · Q20
nandhasuhendra/dotfiles
My configuration files that I use on several applications and Linux desktops.
MCP Hoarder 19.1k tok · · Q0