self-improvement

Convert user feedback into CLAUDE.md edits and new skills.

3|1|Updated Apr 4, 2026
One-click install
npx skills add https://github.com/epologee/leclause-skills --skill self-improvement-epologee
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: self-improvement
Source: https://github.com/epologee/leclause-skills/tree/main/packages/self-improvement/skills/self-improvement
Command: npx skills add https://github.com/epologee/leclause-skills --skill self-improvement-epologee

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Converts informal user feedback, remembered preferences, or requests to create or improve skills into actionable edits and new skill artifacts so Claude's behavior improves persistently and consistently across contexts.

Core Features & Use Cases

  • Duplicate detection & consolidation: Finds repeated instructions across CLAUDE.md and skills and recommends or performs consolidation to the optimal location (user-level, project-level, or plugin-level).
  • Hook-first policy for marketplaces: Detects plugin marketplace projects and prioritizes hook reason or plugin-level changes instead of user-level edits.
  • Skill extraction & TDD workflow: Extracts large CLAUDE.md sections into new skills using a RED-GREEN-REFACTOR approach and updates allowlists and allowed-tools as needed.
  • Safe edits & commits: Applies language-aware edits, verifies staleness via git, summarizes changes, and offers to commit user-level configuration updates.
  • Use case: When a user says "remember this" or "do not add emojis to commits", run the scan, determine best location, apply the edit, and report what changed.

Quick Start

Tell Claude: /self-improvement please incorporate this feedback into CLAUDE.md and create or update the corresponding skill.

Frequently Asked Questions about self-improvement

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn user feedback into persistent CLAUDE.md edits?

To turn user feedback into persistent CLAUDE.md edits, the skill converts informal user preferences and behavioral notes into targeted edits, applying them to the optimal location and optionally committing the configuration updates via git.

What is the best way to consolidate duplicate instructions across Claude skills?

Consolidating duplicate instructions across Claude skills involves scanning project and user plugin repositories to detect repeated rules, extracting large CLAUDE.md sections into new skills, and relocating them to the optimal level.

Can I extract large CLAUDE.md sections into a new skill?

Yes, you can extract large CLAUDE.md sections into a new skill using a RED-GREEN-REFACTOR workflow, which automatically updates allowlists and allowed-tools during the skill extraction process.

Does this skill apply hook-first rules for plugin marketplaces?

Yes, it applies hook-first rules for plugin marketplaces by detecting marketplace projects and prioritizing hook reason or plugin-level configuration changes instead of standard user-level edits.

How do I verify staleness before applying edits to CLAUDE.md?

To verify staleness before applying edits to CLAUDE.md, the skill uses git to check repository state, applies language-aware edits safely, and produces a concise change summary for tracking modifications.