alfredolopez80/multi-agent-ralph-loop

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Ethereum/EVM JSON-RPC call builder and validator - use when interacting with blockchain nodes via RPC.

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Senior Blockchain Architect research agent for comprehensive analysis of EVM chains, perpetual DEX architectures, CEX integrations, and DeFi-TradFi bridges. Use for: blockchain research, protocol comparisons, technical feasibility studies, security audits, compliance analysis, architecture blueprints. Triggers…

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

5-phase first-principles deconstruction for genuinely ambiguous or high-impact decisions. On-demand only - it never selects or changes provider/model/effort (#45 invariant).

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Use the ast-grep MCP tools for structural code search based on Abstract Syntax Tree (AST) pattern matching.

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Browser automation security policy: trust zones (localhost GREEN / staging YELLOW / production RED), the agent-browser tool workflow, allowed vs prohibited actions, and config/secret file handling. Use when the task involves browser automation, agent-browser, Playwright or Chrome DevTools MCP, taking screenshots of…

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Learn patterns from a specific GitHub repository. Clones, analyzes code structure, extracts patterns, populates procedural memory AND syncs to Obsidian vault for Graph View visualization. Use for: targeted learning from known quality repos, quick knowledge acquisition, specific pattern extraction. Triggers…

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Full curator pipeline for autonomous learning from quality repositories. Executes: discovery → scoring → ranking → ingest → learn → vault sync. Writes to procedural memory AND Obsidian vault for Graph View visualization and graduation pipeline. Use for: populating procedural memory with domain patterns, first-time…

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Intensive task clarification using AskUserQuestion - use when starting any non-trivial task.

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Codebase defense analysis system for security profiling.

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Design system management for frontend agents. Actions: init (create DESIGN.md from template), load (inject into agent context), validate (check component compliance). Use when: (1) starting a frontend project, (2) generating UI components, (3) reviewing frontend code for design consistency. Triggers: /design-system…

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Code quality analyzer that identifies "slop" - code violating established coding principles - and suggests concrete improvements. Analyzes code against principles like KISS, YAGNI, SOLID, DRY, and provides before/after fix examples.

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Eval-Driven Development (EDD) Framework - Define-before-implement pattern with structured evals. Provides workflow: Define specifications → Implement features → Verify against evals. Components: TEMPLATE.md for eval definitions, edd.sh CLI script, /edd skill invocation. Check types: CC- (Capability), BC- (Behavior)…

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

End-of-session learning classification. Reviews accumulated learnings and classifies each as GREEN (generic, goes to global wiki), YELLOW (project-specific, goes to project wiki), or RED (sensitive, discarded). Triggered at session end via Stop hook. Use when: (1) session ending, (2) manual review of learnings.…

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

9-language quality gate validation: linting, formatting, type checking, and test execution. Validates code changes meet quality standards before completion. Use when: (1) after code implementation, (2) before PR creation, (3) as part of /orchestrator Step 6, (4) manual quality check. Triggers: /gates, 'quality gates'…

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Explicit opt-in tool: drives the Google Gemini CLI. Use ONLY when the user asks for Gemini by name. Never a default, a fallback, or an automatic second opinion. Triggers: 'use gemini', 'gemini cli', 'run with gemini', 'ask gemini'.

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Ralph Loop pattern with swarm mode: iterative execution until VERIFIEDDONE with multi-agent coordination. Use when: (1) iterative refinement needed, (2) quality gates must pass, (3) automated validation required. Triggers: /iterate, 'iterate until done', 'keep trying', 'fix until passing', 'loop until done'.

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Skill "kaizen" from alfredolopez80/multi-agent-ralph-loop, covering kaizen and v2.88 key changes (model-agnostic).

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Explicit opt-in tool: looks up OpenAI developer documentation via Context7 MCP. Use ONLY when the user is actually working with OpenAI APIs/SDKs or the Codex CLI, or asks for these docs by name. Never a default documentation route. Triggers: 'openai docs', 'codex documentation', 'openai api reference', 'codex mcp'…

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Full orchestration workflow with swarm mode: evaluate -> clarify -> classify -> persist -> plan mode -> spawn teammates -> execute -> validate -> retrospective. Use when: (1) implementing features, (2) complex refactoring, (3) multi-file changes, (4) tasks requiring coordination. Triggers: /orchestrator, /orch…

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Run multiple Ralph loops concurrently for independent tasks. Supports all 6 ralph- teammates (coder, reviewer, tester, researcher, frontend, security). Manages parallel agent execution with proper isolation and result aggregation. Use when: (1) multiple independent fixes needed, (2) parallel reviews required, (3)…

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Performance optimization skill. Core Web Vitals via Lighthouse, bundle size analysis, metrics tracking over time. Use when: (1) optimizing frontend performance, (2) analyzing bundle size, (3) tracking metrics regression. Triggers: /perf, 'performance audit', 'core web vitals', 'bundle size'.

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Plan-State Management for Ralph. Create, track, and manage implementation plans with LSA verification. Coordinates with 6 ralph- teammates including ralph-frontend and ralph-security.

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Product Requirements Document generation and management with INVEST-compliant user stories.

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Launch quality subagents in parallel using the native Task tool. Includes ralph-security for OWASP validation and ralph-frontend for WCAG checks. Reads results post-analysis for orchestrator decision-making.