improve-claude-config
npx machina-cli add skill yu-iskw/coding-agent-fabric/improve-claude-config --openclawImprove Claude Configuration
Purpose
This skill enables Claude Code to evolve and improve its own configuration based on observed patterns, user feedback, and development needs.
When to Use
Invoke this skill when:
- You've explained the same concept to Claude multiple times
- Claude repeatedly makes the same type of mistake
- A new workflow pattern has emerged that should be automated
- Hooks could prevent recurring issues
- New skills would benefit the project
Self-Improvement Workflow
1. Analyze Current State
Read and understand the current configuration:
# View CLAUDE.md
read_file CLAUDE.md
# List all skills
list_dir .claude/skills/
# List all agents
list_dir .claude/agents/
# View current hooks
read_file .claude/settings.json
2. Identify Improvement Opportunity
| Pattern | Action |
|---|---|
| Repeated explanation | Add to CLAUDE.md or create a skill |
| Recurring mistake | Add rule to CLAUDE.md |
| Manual repetitive task | Create a hook |
| Complex workflow | Create a skill |
| Specialized task delegation | Create an agent |
3. Implement Improvement
Adding Rules to CLAUDE.md
For project conventions or gotchas Claude keeps forgetting:
## Recent Learnings (append to CLAUDE.md)
- [Date]: Description of rule and why it matters
Creating a New Skill
- Create directory:
.claude/skills/<skill-name>/ - Create
SKILL.mdwith standard structure.
Creating a New Hook
Add to .claude/settings.json and create the corresponding script in .claude/hooks/.
4. Validate Changes
- Verify JSON syntax in
settings.json. - Test hooks if added.
- Verify skill loads correctly.
Best Practices
- Be minimal: Only add what's necessary
- Be specific: Vague rules are ignored
- Test changes: Validate hooks and skills work
- Version control: Commit configuration changes with clear messages
Source
git clone https://github.com/yu-iskw/coding-agent-fabric/blob/main/.claude/skills/improve-claude-config/SKILL.mdView on GitHub Overview
This skill lets Claude Code evolve its own configuration by learning from observed patterns, user feedback, and development needs. It updates CLAUDE.md, creates new skills or hooks, and automates improvements to reduce repeated issues. The outcome is a more resilient, workflow-ready setup that stays aligned with current practices.
How This Skill Works
First, it reads the current setup (CLAUDE.md, skills, agents, and settings.json). Next, it identifies improvement opportunities using the pattern guide (e.g., repeated explanations, recurring mistakes, or new workflows). Finally, it implements the change by updating CLAUDE.md, creating a new skill or a hook, and validating JSON syntax and skill loading.
When to Use It
- You've explained the same concept to Claude multiple times.
- Claude repeatedly makes the same type of mistake.
- A new workflow pattern has emerged that should be automated.
- Hooks could prevent recurring issues.
- New skills would benefit the project.
Quick Start
- Step 1: Analyze current state by reading CLAUDE.md, listing skills and agents, and viewing .claude/settings.json
- Step 2: Identify Improvement Opportunity by selecting a pattern from the guide (repeated explanations, recurring mistakes, new workflows, hooks, or new skills)
- Step 3: Implement and validate changes by updating CLAUDE.md, creating a new skill/hook/agent as needed, and verifying JSON syntax and load integrity
Best Practices
- Be minimal: Only add what's necessary
- Be specific: Vague rules are ignored
- Test changes: Validate hooks and skills work
- Version control: Commit configuration changes with clear messages
- Maintain compatibility: Ensure changes fit with existing setup
Example Use Cases
- Example 1: Add a rule to CLAUDE.md to avoid repeating a concept.
- Example 2: Create a new skill under .claude/skills/ to automate a recurring workflow.
- Example 3: Add a hook in .claude/hooks/ to prevent a manual repetitive task.
- Example 4: Create an agent to handle a specialized task delegation.
- Example 5: Update CLAUDE.md with a new Recent Learnings entry and automate related rules.
