aif

Configures AI agent context by analyzing tech stacks, installing skills, and setting up MCP servers.

31|2|Updated Mar 21, 2026
One-click install
npx skills add https://github.com/letuhao/lore-weave --skill aif-letuhao
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: aif
Source: https://github.com/letuhao/lore-weave/tree/main/.cursor/skills/aif
Command: npx skills add https://github.com/letuhao/lore-weave --skill aif-letuhao

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Setting up AI agent context for a new or existing project requires manually analyzing the tech stack, finding relevant skills, writing project documentation, and configuring MCP servers. This Skill automates that entire bootstrap process while scanning every external skill for prompt injection before it is trusted. ## Core Features & Use Cases - Project Analysis & Stack Detection: Reads package.json, composer.json, requirements.txt, go.mod, and other config files to detect languages, frameworks, and databases, then generates .ai-factory/DESCRIPTION.md and AGENTS.md. - Skill Acquisition with Security Scanning: Searches skills.sh for matching skills, installs them, and runs a two-level prompt-injection check (automated security-scan.py plus manual semantic review) before use. - MCP Server Configuration: Writes .cursor/mcp.json with runtime-specific formats for Cursor, Claude Code, OpenCode, GitHub Copilot, and Codex, covering GitHub, Postgres, Filesystem, and Playwright servers. - Use Case: You clone an existing repository and run the setup command. The Skill detects a Node.js/Prisma/PostgreSQL stack, installs relevant skills after security scanning, generates AGENTS.md and base coding rules, and configures the Postgres and GitHub MCP servers. ## Quick Start Ask the agent to set up AI context for this project by analyzing the tech stack, installing relevant skills, and configuring MCP servers.

Frequently Asked Questions about aif

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up AI agent context for an existing project?

Run the setup command with no arguments in a project containing config files like package.json or composer.json. The Skill detects your stack, recommends skills and MCP servers, and generates DESCRIPTION.md, AGENTS.md, and base rules after your confirmation.

How does the skill scan external skills for prompt injection?

Every skill installed from skills.sh is scanned with security-scan.py, which exits 0 for clean, 1 for blocked, and 2 for warnings. Blocked skills are removed via cleanup-blocked-skill.py, and a manual semantic review of the SKILL.md content is also performed.

What happens if Python is not installed for the security scanner?

The Skill probes python3, python, py -3, and py in order to find a Python 3 interpreter. If none is found, it asks you to provide a Python path, skip scanning with a warning, or install Python first and re-run.

Which MCP servers can be configured and for which runtimes?

Supported server templates include GitHub, Postgres, Filesystem, and Playwright. The configuration is written in runtime-specific formats for Cursor and Claude Code (mcpServers), OpenCode (mcp), GitHub Copilot (servers), and Codex (TOML config).

Can generated documentation be written in a language other than English?

Yes. The Skill resolves language.ui for communication and language.artifacts for generated files from config.yaml, AGENTS.md, or by asking you. All artifacts like DESCRIPTION.md and AGENTS.md are then written in the resolved artifact language.

When should I use skill generation instead of installing from skills.sh?

Generation via the skill-generator is used when no matching skill exists on skills.sh or when you have reference documentation URLs. Learn Mode studies the provided URLs to produce a skill grounded in real documentation rather than generic patterns.