Autonomous orchestration framework for Claude Code with MemPalace-inspired memory (4-layer stack, 818-token wake-up), parallel-first Agent Teams (6 teammates), Aristotle First Principles methodology, and 4-stage quality gates. 925+ tests, 22 active hooks, automatic learning pipeline.
This repository also configures its own agents. See what multi-agent-ralph-loop tells them →
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
Version history and reference tables for Multi-Agent Ralph (batch execution v2.88, skills/commands unification v2.87, LSP integration v2.88.1, security fixes v2.89.2, test layout, docs map). Load when you need the detailed feature reference, changelog, or file-layout tables that used to live in CLAUDE.md.
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
When the user wants to create or update a README.md file for a project. Also use when the user says "write readme," "create readme," "document this project," "project documentation," or asks for help with README.md. This skill creates absurdly thorough documentation covering local setup, architecture, and deployment.
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
Comprehensive research skill using the native WebSearch and WebFetch tools plus Context7 for library documentation.
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
Analyze completed tasks to improve the Ralph system. Saves learnings to living knowledge vault and coordinates insights across 6 ralph- teammates.
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
Comprehensive AI code security review using 27 sec-context anti-patterns. Use for code review when security vulnerabilities are suspected, especially for AI-generated code.
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
Claude-driven security audit with an independent second opinion. Integrates the ralph-security agent (6 quality pillars, OWASP A01-A10). Uses LSP for code navigation during analysis. Use when: (1) /security is invoked, (2) task relates to security functionality.
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
Global skill enforcing senior software engineering best practices.
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
Pre-launch shipping checklist orchestrating /gates, /security, /browser-test, /perf. Ensures nothing ships without passing all quality checks. Use when: (1) before deploying, (2) before merging to main, (3) before release. Triggers: /ship, 'ship it', 'ready to deploy', 'pre-launch check'.
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
Smart Forking - Find and fork from relevant historical sessions using parallel memory search across vault, handoffs, and ledgers.
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
A skill for removing AI-generated writing patterns ('slop') from prose. Eliminates telltale signs of AI writing like filler phrases, excessive hedging, overly formal language, and mechanical sentence structures. Use when: writing content that should sound human and natural, editing AI-generated drafts, cleaning up…
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
Tree of Attacks with Pruning for systematic code analysis.
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
Autonomous batch task execution with PRD parsing, task decomposition, and continuous execution until all tasks complete. Uses /orchestrator internally. Stops only for major failures (no internet, token limit, system crash). Use when: (1) processing task lists autonomously, (2) PRD-driven development, (3) batch feature…
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
Classifies task complexity (1-10) for model and agent routing.
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
Visualize task dependencies and progress (Gastown-style).
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
Custom skill for testing-anti-patterns.
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
Living knowledge base management. Actions: search (query vault), save (store learning), index (update indices), compile (raw->wiki->rules graduation), init (create vault structure). Follows Karpathy pipeline: ingest->compile->query. Use when: (1) searching accumulated knowledge, (2) saving learnings, (3) compiling raw…
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
React and Next.js performance optimization guidelines from Vercel Engineering. Use when writing, reviewing, or refactoring React/Next.js code. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
Manage git worktrees with PR workflow and multi-agent review. Use when developing features in isolation with easy rollback.
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
Lead protocol for the session running in the main checkout that delegates write tasks to its team's worker sessions (qteam runs zc-1, zc-2, mmx; qteam-zc runs zc-3, zc-4, mmx-2, mmx-3 — each in its own worktree and worktree- branch) and integrates their branches into main. Use this skill whenever delegating work to…
alfredolopez80/multi-agent-ralph-loop
Skill Claude Code
Worker protocol for the worker sessions of a Q-team (qteam runs zc-1, zc-2, mmx; qteam-zc runs zc-3, zc-4, mmx-2, mmx-3), which run inside a Claude Code worktree (.claude/worktrees/ ) and take tasks from the lead session. Use this skill whenever a message from lead arrives, when starting or finishing any task, before…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: