Coaching — AI skill for Claude Code
Generate AI coaching feedback for recent Melee games using the configured LLM.
How to install Coaching
Installs to ~/.claude/skills/bloodshed-rain-themagi-coaching/SKILL.md
mkdir -p ~/.claude/skills/bloodshed-rain-themagi-coaching && curl -fsSL https://raw.githubusercontent.com/Bloodshed-Rain/TheMAGI/HEAD/.claude/skills/coaching.md -o ~/.claude/skills/bloodshed-rain-themagi-coaching/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Coaching does
name: coaching description: Generate AI coaching feedback for recent Melee games using the configured LLM user_invocable: true
Generate AI-powered coaching feedback for the user's Melee games.
Usage
/coaching- Coach on the most recent game/coaching- Coach on the last N games as a set/coaching- Coach on a specific replay file
Steps
- Parse arguments to determine what to coach on
- For recent games: `npx tsx src/pipeline-cli.ts --dir <replay-fold
Alternatives in AI
- Sentrux — Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improveme 2.9k ★
- PRD: Gentleman AI Installer — One command. Any agent 1.9k ★
- AI Investigator — An automated AI system (Python framework) designed to analyze any type of website content and generate structu 733 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Concept Update
Sweep recent changes and update the LLM-Wiki repo's concept docs, architecture diagram, AGENTS.md, and memory.
Homefield
Benchmarks are away games. Rank coding agents on YOUR repo's git history, with honest statistics, a flake filt
Wiki Synthesize
Synthesize wiki/sources/ .md pages from raw session transcripts using the configured LLM backend.
Peer Review
Multi-LLM peer review skill for Claude Code — send plans to Codex and Gemini for structured feedback with cros
Systems Thinking
A cognitive base that shifts AI agent reasoning from linear cause-effect chains to feedback-driven structural
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
Related Agents
Melee Coach Analyst
Use this agent when working on MAGI project code that involves Melee game knowledge, replay analysis logic, co
Brag Spotter
Proactively scans for achievements and wins that aren't in the brag doc yet. Checks recent work notes, inciden
Wins Capture
Proactively scans for achievements and wins that aren't in the wins doc yet. Checks recent work notes, inciden