Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
vibestack
SkillsSixty commands for AI coding assistants — /office-hours to shape an idea, /review before you merge, /ship to open the PR — plus the standing rules they assume. One install covers Claude Code, Cursor, Kiro and Codex CLI. Plain bash, MIT, no telemetry.
git clone https://github.com/timurgaleev/vibestack.git -
aidimag
MCP serversPersistent, verified memory for AI coding agents: recall, capture, guardrails, review queue.
aidimag@1.0.22 -
Boltwork
MCP serversAI services via Bitcoin Lightning — PDF summarisation, code review, translation and more.
boltwork-mcp@0.1.12 -
diffpilot
MCP serversMCP server for PR code review, commit messages, changelogs, and secret detection.
DiffPilot@1.0.7 -
brainstorm-mcp
MCP serversMulti-model AI brainstorming debates with code review and quick perspectives
brainstorm-mcp@1.8.0 -
Erkle team memory
MCP serversShared, scoped, reviewable team memory for AI coding agents.
-
AGI-Super-Team
SkillsAn installable, cross-framework AI organization: C-suite agents, expert subagents, curated skills, independent review, and one-command setup across 18 AI client/runtime adapters.
git clone https://github.com/aAAaqwq/AGI-Super-Team.git -
community-job-search-plugin
SkillsA Claude plugin for running a job search: triage listings, tailor resumes and cover letters, handle recruiter outreach, prep for and debrief interviews, track your network, keep a pipeline that doesn't rot, and run a weekly review.
git clone https://github.com/backwardstruck/community-job-search-plugin.git -
Pull Request Review Assistant
PromptsAct as a Pull Request Review Assistant. You are an expert in software development with a focus on security and quality assurance. Your task is to review pull requests to ensure code quality and identify potential…
-
valcraft
SkillsAgent skills for spec-driven development. An automated agentic delivery loop coordinates planning, implementation, and cross-agent code reviews. Requirements, plans, and decisions live in ordinary project files with project-wide IDs linked from commits and PRs, reducing manual handoffs and repeated explanations while keeping session context small.
git clone https://github.com/valzav/valcraft.git -
karpathy-guidelines
Prompts--- name: karpathy-guidelines description: Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface…
-
Diff Security Auditor Agent Role
Prompts# Security Diff Auditor You are a senior security researcher and specialist in application security auditing, offensive security analysis, vulnerability assessment, secure coding patterns, and git diff security review…
-
aidimag
MCP serversPersistent, verified memory for AI coding agents: recall, capture, guardrails, review queue.
aidimag@1.0.20 -
gossipcat
MCP serversMulti-agent orchestration for Claude Code — consensus review, adaptive dispatch, skill learning
gossipcat@0.2.1 -
git-enhanced
MCP serversEnhanced Git MCP Server - Code review, commit analysis, and branch management
@davidweb3-ctrl/mcp-git-enhanced@1.0.1 -
clawhub
MCP serversGit hosting for AI agents: repos, changes, focused diffs, reviews, issues, code search.
useclawhub-mcp@0.1.0 -
diffctx
MCP serversSelects the minimum code an LLM needs to review a git diff
diffctx@1.20.0 -
SpringRoll
MCP serversRegister, deploy, review, and govern internal applications built with coding agents.
-
cynicalsally
MCP serversBrutally honest code reviews: scores, real issues, and usable fixes. CLI + MCP server.
@cynicalsally/cli@0.7.0 -
Plainsight MCP
MCP serversSearch the Plainsight playbook and review code against proven best practices.
-
DontPanic
MCP serversLocal MCP server to plan, dispatch, review, and gate AI coding work.
dontpanic-orchestrate@0.2.0 -
Telegram bot development skill for Claude Code, Codex, OpenCode and Cursor: build, review and debug Telegram bots and Mini Apps against the live Bot API, checking the official docs and your installed library (aiogram, grammY, python-telegram-bot, Telegraf) before any call.
git clone https://github.com/nyxandro/telegram-bot-development-skill.git -
livewire-alpine-skills
SkillsAgent Skills for Laravel Livewire v4 + Alpine.js v3. Recipes EXECUTED against a real install (14 tests), a 21-rule reviewer that gates on exit code, project-convention detection, and an objective eval. 12k lines from the official docs.
git clone https://github.com/olgunozoktas/livewire-alpine-skills.git -
aiteamkit
SkillsMulti-harness AI plugin for Claude Code, Cursor and Codex CLI: skills that run the delivery lifecycle of a project team - intake, estimate, design, spec, breakdown, plan, implement, fix, review, QA, verify, release, incident, retro, onboard, handover. Author and approver stay separate roles.
git clone https://github.com/lamngockhuong/aiteamkit.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.