Major overhaul of onboarding system with adaptive topic selection based on user context and keywords. Addresses 8 critical gaps identified by technical- writer agent challenge. Core Changes: - Adaptive matrix: core topics (always) + adaptive topics (keyword-triggered) - Security-first: moved sandbox_native_guide to beginner_5min (before commands) - Time budget validation: all 18 profiles validated at 6-8 min/topic - Quiz integration: positioned as exit activity in Phase 4 wrap-up - New learn_security goal with 2 profiles (beginner_15min, advanced_60min) Technical Improvements: - Added onboarding_matrix_meta for version tracking and maintenance triggers - Created validation script (validate-onboarding.sh) with 6 automated checks - Created automation script (detect-new-onboarding-topics.sh) for monthly reviews - Fixed 8 missing deep_dive keys (rules, workflow, fix, architecture, etc.) - Removed duplicate deep_dive section causing validation failures Documentation: - README.md: version 3.23.0, harmonized counts (106 templates, 49 evaluations) - CHANGELOG.md: comprehensive v3.23.0 entry with all changes - Onboarding-prompt.md: updated Phase 1.5, 2, 4 with adaptive logic - Reference.yaml: 180+ lines added for adaptive architecture Validation: - All 18 profiles pass time budget constraints (30-50% buffer maintained) - All deep_dive keys verified (no missing references) - Version synchronized across 6 files via sync-version.sh Challenge: technical-writer agent identified 8 gaps in initial analysis Result: Full adaptive approach implemented, all gaps addressed Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| claude-code-releases.yaml | ||
| cowork-reference.yaml | ||
| llms.txt | ||
| README.md | ||
| reference.yaml | ||
Machine-Readable References
Files optimized for LLM/AI consumption.
Contents
| File | Description | Tokens |
|---|---|---|
| reference.yaml | Structured index with line numbers for deep dives | ~2K |
| llms.txt | Standard LLM context file for repository indexation | ~1.5K |
Usage
Give Claude Code instant expertise
# Paste into any AI assistant
curl -sL https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/machine-readable/reference.yaml
Reference in Claude Code
@machine-readable/reference.yaml
Add to system prompts
Include the YAML content in your AI assistant's system prompt for Claude Code expertise.
Back to main README