TacoSkill LAB
TacoSkill LAB
HomeSkillHubCreatePlaygroundSkillKit
© 2026 TacoSkill LAB
AboutPrivacyTerms
  1. Home
  2. /
  3. SkillHub
  4. /
  5. claude-reflect
Improve

claude-reflect

7.0

by jeremylongshore

74Favorites
182Upvotes
0Downvotes

Execute self-learning system that captures corrections during sessions and syncs them to CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something. Trigger with phrases like "remember this", "don't forget", "use X not Y", or "actually...".

self-learning

7.0

Rating

0

Installs

AI & LLM

Category

Quick Review

Excellent skill with clear description and well-organized documentation. The SKILL.md provides comprehensive coverage of when and how to invoke the self-learning system, with explicit trigger patterns and command references. Task knowledge is strong with clear two-stage workflow explanation and multiple command options. Structure is clean with a concise overview and logical sections. The skill addresses a genuinely novel problem—capturing and persisting corrections across sessions—that would be token-intensive for a CLI agent to handle manually. Minor room for improvement in explicitly documenting the technical implementation details of hook triggering, though referenced scripts likely contain this information.

LLM Signals

Description coverage9
Task knowledge8
Structure9
Novelty8

GitHub Signals

1,046
135
8
0
Last commit 0 days ago

Publisher

jeremylongshore

jeremylongshore

Skill Author

Related Skills

rag-architectprompt-engineerfine-tuning-expert

Loading SKILL.md…

Try onlineView on GitHub

Publisher

jeremylongshore avatar
jeremylongshore

Skill Author

Related Skills

rag-architect

Jeffallan

7.0

prompt-engineer

Jeffallan

7.0

fine-tuning-expert

Jeffallan

6.4

mcp-developer

Jeffallan

6.4
Try online