ML Impl — AI skill for Claude Code
Full implementation loop - plan, write, and review code (Meta-Loop Steps 3.1-3.4).
How to install ML Impl
Installs to ~/.claude/skills/jpavley-meta-loop-ios-ml-impl/SKILL.md
mkdir -p ~/.claude/skills/jpavley-meta-loop-ios-ml-impl && curl -fsSL https://raw.githubusercontent.com/jpavley/meta-loop-ios/HEAD/commands/ml-impl.md -o ~/.claude/skills/jpavley-meta-loop-ios-ml-impl/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What ML Impl does
description: Full implementation loop - plan, write, and review code (Meta-Loop Steps 3.1-3.4) argument-hint: spec_path
Meta-Loop: Implementation Loop
Complete the implementation loop: plan the implementation, write code, and review for correctness.
**Modes:** Plan Mode → Agent Mode → Ask Mode
Arguments
$ARGUMENTS: Path to the specification to implement- Examples:
specs/views/my-feature/spec.md
- Examples:
Prerequisites
This skill implements **Steps 3.1-3.4** of the Meta-Loop
Alternatives in AI
Full documentation available on GitHub
View Source RepositoryRelated Skills
Code Use Case
Instructs AI Agent to read the use case, the implementation plan and write the code
Full Stack Chat Application With Multi Platform Clients AI Agent Integration
A Claude Code-style AI agent harness in Python. Uses Ollama + native LLM tool-calling to read/write files and
Aar Loop
Run an After Action Review after any AI session and write concrete lessons so your agent stops repeating mista
RAG Sys
Deep Research Agent demo (React + Python FastAPI + ArangoDB) built with Claude Code under a defined plan → imp
Hero Bg
Inspects a project's hero and generates a guided two-image, one-video AI background workflow with loop-safe pr
Agent Skills Deep Dive
A Python implementation of the Claude Agent Skills system — a sophisticated prompt-based meta-tool architectur
Related Agents
Eval Implementer
Implementer role of the D365FO agent eval loop. Runs ON THE VM (mcp-server in full mode + C# bridge) against t
Go Tester
Use this agent to write tests, debug test failures, check coverage, or run the full QA workflow for the aiagen
Arquiteto
Meta-persona of the workbench. Invoke to plan complex tasks (>3 steps, multi-domain, irreversible action), cre