Vibes

by jonhill90

Not rated
GitHub

About

Transforms Claude Desktop into a conversational development environment using distributed MCP servers.

Details

Author
jonhill90
Categories
Developer Tools, AI, Automation

Setup

Install Vibes in your MCP client (Claude Desktop, Cursor, Windsurf, and others).

Repository: https://github.com/jonhill90/vibes

Follow the installation instructions in the repository README, then restart your MCP client.

Jon Hill's public collection of portableAgent Skills— self-contained, model- and harness-agnostic instructions an AI coding agent loads on demand. Every skill here is individually installable; nothing in this repository is specific to any one harness, and nothing here depends on private tooling or evidence.

Install one or more specific skills into the current project:

npx skills add jonhill90/skills --skill tmux --skill github-cli

npx skillspins installs by content hash inskills-lock.json, so a project's skill set stays reproducible. See theskills CLIfor the full command reference.

This repository is also anAgent Plugins 1.0.0plugin:plugin.jsonat the root, 39 skills atskills/<name>/SKILL.md(measuredls -d skills// | wc -l, verified 2026-08-21), which is the standard's own discovery convention. Any conformant client can consume the collection whole, with no bespoke tooling.

That is a portability claim, not a local one. Claude Code reads its own manifest at.claude-plugin/plugin.jsonand does not look for this file, so adding it changed nothing for Claude Code users today.npx skillsabove remains the way to install individual skills, and nothing here replaces it.

All 39, flat and alphabetical — matchingskills/'s own layout (seeWhere a skill belongsfor why this repository does not bucket by category). Measuredls -d skills//, verified 2026-08-21. This table has drifted from the tree twice: 12 skills short for five days (069e2c4, 2026-08-09) and, a second time, 13 skills short until this correction (skills#224) —scripts/validate_repository.py'svalidate_readme_tablecheck now fails CI when the table andskills/disagree, so a hand-edit that drops or misnames a row is caught before it reaches the public repository.

Each skill'sdescriptionfrontmatter is the actual trigger contract — read the skill itself for exact wording and preconditions. This repository does not yet distinguish user-invoked from model-invoked skills anywhere a reader sees before openingSKILL.md— tracked as open indocs/skills-docs-proposal-161.md.

Most skills shouldnotlive in this repository. Decide placement first:

Each skill lives atskills/<name>/SKILL.md:

skills/example-skill/ ├── SKILL.md ├── scripts/ Optional deterministic, tested helpers ├── references/ Optional detail loaded on demand └── assets/ Optional output resources

Portable frontmatter isnameanddescription(plus optionallicense,compatibility,metadata,allowed-tools). The directory name must matchname. KeepSKILL.mdunder 500 lines and move detail into directly linkedreferences/. Full conventions:AGENTS.md.

python3 scripts/validate_repository.py python3 -m unittest discover -s tests -v

CI runs both on every pull request and on pushes tomain.

- This repository holds only portable skill content and the minimal validation/tests/CI needed to keep it correct.
- Personal harness configuration — canonical instructions, hooks, agents, settings, MCP declarations, install/sync tooling — lives in a separate personal harness repository that consumes this collection; it is not vendored here.
- Behavioral evaluation methodology, scenarios, transcripts, and results are private and are not published in this repository. Where a skill references past evidence, it states what happened and when without a link to private material.
- Employer-owned or project-specific material is never copied here.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Agent-native developer Q&A API with MCP + A2A endpoints for citations, job pickup, and answer submission.

MCP bridge that lets Claude Code delegate heavy tasks to the Antigravity CLI (agy) — purpose-built tools, model routing with fallback, session continuity, and output truncation to save Claude's context and tokens.

Embeds intelligent guidance into AI workflows to organize development and ensure quality.

Open-source AI coding stack — bundled MCP servers, agent runtime, and developer tooling for shipping AI-native dev tools.

Local agent workbench bundling OpenHands, Goose, Aider, and ashlrcode against one local LLM, with ashlr-plugin MCP servers pre-wired.

Async Parallel Antigravity for Codex & Claude Code

Run parallel, resumable, human-operable Antigravity CLI sessions from Codex, Claude Code, or any MCP-capable agent harness.

knowledge network for AI coding agents. Developers connect their agents to a shared pool of verified solutions — saving tokens, reducing debugging time, and getting better results. Solution authors earn when their work helps others.

Orchestrates multiple Claude Code agents across iTerm2 sessions, providing centralized management and inter-agent communication.

Multi-LLM Design and Build Team. Confer and create with a team of LLMs.

An MCP server for initial app planning and creating a good starting point for an app.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.