Menu
Install and configure aflare, including the MCP server connection for Claude Code.
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace --skill setupThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Deploy a LangChain 1.0 / LangGraph 1.0 app to Cloud Run, Vercel, or LangServe correctly — with timeouts sized for chain length, cold-start mitigation, SSE anti-buffering headers, and Secret Manager over .env. Use when prepping a first production deploy, debugging a stream that hangs behind a proxy, or diagnosing p99 latency spikes. Trigger with "langchain deploy", "langchain cloud run", "langchain vercel python", "langchain langserve", or "langchain docker".
Build a correct LangGraph 1.0 ReAct agent with create_react_agent — typed tools, error propagation, recursion caps, and stop conditions that actually stop. Use when writing a first tool-calling agent, migrating from AgentExecutor or initialize_agent, or diagnosing an agent that loops on vague prompts. Trigger with "langgraph agent", "create_react_agent", "langgraph tool calling", "AgentExecutor migration", or "agent loop cost".
Build LangGraph 1.0 human-in-the-loop approval flows with interrupt_before / interrupt_after and Command(resume=...) — JSON-serializable state, clean resume semantics, and UI wiring for approval decisions. Use when adding an approval gate before an expensive tool call, wiring a Slack/web UI for agent approvals, or debugging a graph that crashes on interrupt. Trigger with "langgraph human in loop", "langgraph interrupt_before", "langgraph approval flow", "Command resume", "langgraph HITL".
Showing SKILL.md
| name | setup |
| description | Install and configure aflare, including the MCP server connection for Claude Code. |
| invocation | user |
| allowed-tools | Read, Edit, Write, Bash |
| version | 0.6.0 |
| author | aflare |
| license | AGPL-3.0 |
| compatibility | claude-code >= 0.7.0 |
| tags | ["setup","installation","configuration","mcp"] |
This skill installs and configures aflare, an AI-powered terminal workflow engine, and sets up the MCP server connection for Claude Code integration. It handles binary installation, PATH configuration, and MCP server setup.
Choose one of the following installation methods:
Option 1: Install Script (Linux/macOS)
curl -sL https://raw.githubusercontent.com/alib8b8/aflare/main/install.sh -o install.sh
bash install.sh
Option 2: Go Install
go install github.com/alib8b8/aflare/cmd/aflare@latest
Option 3: Download from Releases Download the binary for your platform: https://github.com/alib8b8/aflare/releases
aflare --version
aflare list
The MCP server is pre-configured in .mcp.json:
{
"mcpServers": {
"aflare": {
"type": "stdio",
"command": "aflare",
"args": ["--mcp-server"]
}
}
}
Claude Code will automatically start the MCP server when the plugin is activated.
Create ~/.aflare/config.yaml:
safe_mode: false
default_model: "ollama://llama3"
api_keys:
openai: "your-api-key"
deepseek: "your-api-key"
After successful setup:
~/.aflare/config.yamlaflare --versionExample 1: Fresh Install on Linux
curl -sL https://raw.githubusercontent.com/alib8b8/aflare/main/install.sh -o install.sh
bash install.sh
aflare --version
Example 2: Update via Go
go install github.com/alib8b8/aflare/cmd/aflare@latest
aflare --version
Example 3: Configure API Keys
mkdir -p ~/.aflare
cat > ~/.aflare/config.yaml <<EOF
safe_mode: false
default_model: "deepseek-chat"
api_keys:
deepseek: "sk-your-key"
openai: "sk-your-key"
EOF
which aflareaflare --versionaflare --mcp-server