yu-iskwyu-iskw/coding-agent-fabric/.claude/skills/improve-claude-config/SKILL.md

improve-claude-config

Skill1 starsChanged 9 months agoApache-2.0View on GitHub

Self-improvement skill for evolving Claude Code configuration. Use when you notice repeated mistakes, want to add new workflows, or optimize the development experience.

In this repository16 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .cursor/rules/tech-stack.mdcCursor rule
- build-and-fixSkill
- bumpup-versionsSkill
- clean-projectSkill
- fix-issueSkill
- initialize-projectSkill
- lint-and-fixSkill
- manage-adrSkill
- manage-changelogSkill
- node-upgradeSkill
- security-vulnerability-auditSkill
- setup-dev-envSkill
- sync-readmeSkill
- test-and-fixSkill
- test-integration-dockerSkill

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Read and understand the current configuration:
line 26
Very specific:
Create SKILL.md with standard structure.
line 67
Very specific:
Add to .claude/settings.json and create the corresponding script in .claude/hooks/.
line 71
Very specific:
Verify JSON syntax in settings.json.
line 75
Distinctive:
Test hooks if added.
line 76
Distinctive:
Verify skill loads correctly.
line 77
Distinctive:
Be minimal: Only add what's necessary
line 81
Distinctive:
Version control: Commit configuration changes with clear messages
line 84

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Improve 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.md with 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

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free