By ash1794
Bart-style coaching hooks for engineering growth. Provides technical depth insights, operational maturity nudges, and self-awareness mirrors with compound reflection across sessions.
Bart-style coaching hooks for Claude Code. Provides growth-oriented feedback across three dimensions as you work, with compound reflections that accumulate across sessions.
During sessions — Three types of coaching insights appear naturally:
* Insight — Technical depth: why things work, not just how> Systems — Operational maturity: what breaks under load, what's invisible in prod# Mirror — Self-awareness: patterns in your behavior (hero-mode, skipped steps, assumptions)At session end — Prompts you to write a compound reflection comparing this session's patterns to your growth trajectory. If the session exits without one, prints a command you can run next time. Reflections persist across sessions using usage-based retention.
claude plugin install github:ash1794/bart-coaching
Two hooks, minimal context cost (~1,400 tokens total):
| Hook | When | Cost | Purpose |
|---|---|---|---|
| SessionStart | Once | ~1,200 tokens | Loads coaching context + past reflections |
| Stop | Once at exit | ~200 tokens | Prompts compound reflection before closing |
Reflections use usage-based retention:
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claim38 engineering discipline skills for Claude Code & OpenAI Codex — research, quality gates, testing patterns, deployment, learning, gap analysis, spec sync, and more. Extracted from real-world development.
npx claudepluginhub ash1794/bart-coachingAI mentor agent for vibe coders - analyzes Claude Code conversations with 6-axis skill evaluation (DECOMP/VERIFY/ORCH/FAIL/CTX/META), 7-level system (L1~L7, 0.5 increments), 4 workspace types (Builder/Explorer/Designer/Operator), and longitudinal growth tracking.
Personalized coding tutorials that use your actual codebase for examples with spaced repetition quizzes
I (Claude) act as you - Build knowledge base from your notes.
Metacognitive advisor that monitors Claude Code and provides feedback
互動式學習模式,在決策點請求有意義的程式碼貢獻(模擬未發布的學習輸出風格)
Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and sends a personalized growth report.