Microfrontend

Use when the user asks to split the web app into independently deployed micro frontends, Module Federation, remoteEntry/mf-manifest, import maps, single-spa, Native Federation, shared singletons or cross-app communication. Produces the composition choice, host/remote config and deployment rules. Not for a single-team monorepo (use monorepo).

45 stars 6 forksDevOps & Cloud

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add j4flmao/agent-skills --skill microfrontend
Manual install
git clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/frontend/universal/microfrontend ~/.claude/skills/microfrontend

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Microfrontend Architecture

## Purpose
Design microfrontend architectures with integration strategy, shared dependency management, and cross-app communication protocols.

## Agent Protocol

### Trigger
User request includes: `microfrontend`, `micro-frontend`, `module federation`, `mf`, `mfe`, `frontend composition`, `federated module`, `webpack federation`, `rspack federation`.

### Input Context
- Number of frontend teams
- Current frontend architecture (monolith SPA, multi-page)
- Framework preferences (React, Vue, Angular, Solid)
- Build tool (Webpack 5, Rspack, Vite)
- Deployment platform (Kubernetes, S3/CDN, Netlify, Vercel)
- Integration requirements (auth, navigation, cross-app communication)

### Output Artifact
A markdown document containing:
- Microfrontend composition approach (Module Federation, iframe, Web Components) with rationale
- Shared dependency strategy (singleton vs shared vs standalone)
- Cross-app communication protocol
- Shell/Host application design
- Deployment pipeline per microfrontend
- Migration plan from monolith SPA

### Response Format
Produce the artifact directly. No preamble. No postamble. No explanations. No filler/hedging/transitions. Compress output — why use many token when few do trick. If monolith SPA is appropriate, output `Monolith SPA recommended. Reason: [reason].` and stop.

——

### Completion Criteria
- Integration method selected with comparison to alternatives
Read the full skill on GitHub

Details

Skill name
microfrontend
Path
skills/frontend/universal/microfrontend/SKILL.md
License
MIT
Repo updated
17 November 2026

FAQ

What does the Microfrontend skill do?

Use when the user asks to split the web app into independently deployed micro frontends, Module Federation, remoteEntry/mf-manifest, import maps, single-spa, Native Federation, shared singletons or cross-app communication. Produces the composition choice, host/remote config and deployment rules. Not for a single-team monorepo (use monorepo).

How do I install the Microfrontend skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill microfrontend. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Microfrontend popular?

It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.

Related skills

Agent Observability

45

j4flmao/agent-skills

Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).

DevOps & Cloud

AI Agent Architectures

45

j4flmao/agent-skills

Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).

AI, LLMs & Agents

AI Agent Core Loop

45

j4flmao/agent-skills

Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).

AI, LLMs & Agents

Microservices

45

j4flmao/agent-skills

Use when the user asks about microservices, splitting a monolith, service boundaries, database per service, sagas, service discovery or strangler fig migration. Produces a decomposition and communication plan (or a monolith verdict). Not for DDD modeling (use architecture-domain-driven-design) or Kubernetes setup (use kubernetes).

DevOps & Cloud

Longhorn

45

j4flmao/agent-skills

Use when the user asks about Longhorn on Kubernetes, Longhorn volumes and replicas, backup targets (S3 or NFS), recurring snapshots, disaster recovery volumes, the V2 data engine, Longhorn performance, or degraded volumes. Produces Longhorn install, StorageClass and backup configs. Not for Ceph or SAN design (use storage-infrastructure).

DevOps & Cloud

Monitoring

45

j4flmao/agent-skills

Use when the user asks about infrastructure monitoring with Prometheus, Grafana, Loki or ELK, scrape configs and relabeling, Alertmanager routing by severity, Loki label strategy, or node and host metrics. Produces monitoring stack configs and alert routes. Not for Kubernetes ServiceMonitor setup (use prometheus-grafana) or TSDB scaling (use sre-observability-scaling).

DevOps & Cloud

Browse the most popular Claude skills, all devops & cloud skills, or write your own with the skills generator.