- Claude Reflect System: Automatic skill improvement via feedback analysis - 8-step workflow: Monitor → Parse → Classify → Propose → Review → Backup → Apply → Commit - Safety features: User review gate, Git backups, syntax validation, locking - Security warnings: Feedback poisoning, memory poisoning, prompt injection mitigations - YAML index: 10 new skill lifecycle entries (lines 113-123) - Resource evaluation: Self-improve skill pattern (redirected to proven alternative) - Landing sync history: v3.11.5 → v3.11.6 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