Vibe Agents
Khazp's vibe-agents analyze text/audio to detect emotional tone & subtle social cues for nuanced understanding.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add vibe-agents npx -- -y @trustedskills/vibe-agents
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"vibe-agents": {
"command": "npx",
"args": [
"-y",
"@trustedskills/vibe-agents"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill generates configuration files and a master plan (AGENTS.md) to guide AI coding assistants in building an MVP (Minimum Viable Product). It's specifically designed as Step 4 within the "vibe-coding" workflow, focusing on progressive disclosure – a high-level overview in AGENTS.md with detailed configurations in separate files. The skill ensures continuity by referencing prior product requirements and technical design documents to maintain context throughout the development process.
When to use it
- When you're ready to configure AI coding assistants for your project after defining the product vision (PRD) and technical design.
- After completing Step 1 (loading context from PRD and Tech Design documents) and Step 2 (answering configuration questions).
- To create a structured set of files (
AGENTS.md,agent_docs/, tool-specific.mdor directory files) that will direct the AI coding assistants' actions. - When you need to ensure your AI assistant understands the project’s goals, technical stack, and desired code style.
Key capabilities
- Context Extraction: Extracts key information from
docs/PRD-*.md(Product Requirements Document) anddocs/TechDesign-*.mdfiles including product name, user stories, features, tech stack, database schema, and AI tool recommendations. - Configuration Questioning: Asks the user about preferred AI tools (Claude Code, Gemini CLI, Google Antigravity, Cursor, VS Code + GitHub Copilot, Lovable / v0) and technical expertise level (Vibe-coder, Developer, In-between).
- File Generation: Creates a structured project directory with
AGENTS.md(master plan),agent_docs/(detailed tech information), and tool-specific configuration files (CLAUDE.md,GEMINI.md,.cursor/rules/,.github/copilot-instructions.md). - Instruction Templates: Generates templates for
AGENTS.mdincluding sections on project overview, how the AI should think (understand intent, ask questions, plan before coding), and a Plan -> Execute -> Verify workflow.
Example prompts
- "Generate AGENTS.md and configuration files based on my PRD and Tech Design documents."
- "I'm using Gemini CLI and Cursor for this project; create the necessary configuration files."
- “My technical level is Developer, please generate the configuration files accordingly.”
Tips & gotchas
- Prerequisites: The skill requires existing
docs/PRD-*.mdanddocs/TechDesign-*.mddocuments. If these are missing, it will suggest running the appropriate skills first. - Session Continuity: Pay attention to any "continuity hints" added in generated instructions to avoid issues during subsequent steps of the vibe-coding workflow.
- Model Versions: The skill generally uses model family names (e.g., Claude) rather than specific versions unless requested by the user.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.