Skip to content
TrustedSkillsbeta
Back to all skills

Vibe Agents

Checked
khazp·vlatest·agents·MIT

Khazp's vibe-agents analyze text/audio to detect emotional tone & subtle social cues for nuanced understanding.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add khazp/vibe-coding-prompt-template --skill vibe-agents -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

khazp

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned khazp/vibe-coding-prompt-template at db481763c2.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
db481763c2
Manifest
.agents/skills/vibe-agents/SKILL.md
Scanned
3 files, 96 lines
Copies in repo
3 — all of them scanned
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

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 .md or 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) and docs/TechDesign-*.md files 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.md including 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-*.md and docs/TechDesign-*.md documents. 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.