almax000almax000/claude-skills/init-modular/SKILL.md

init-modular

Skill1 starsChanged 7 months agoMITView on GitHub

Initialize a modular .claude/ directory structure with battle-tested agents, hooks, and rules. After initialization, customize for your project:

In this repository14 other files it gives its agents.
- brew-maintainSkill
- cc-updatesSkill
- commit-helperSkill
- dev-consoleSkill
- explain-codeSkill
- learnSkill
- plan-debateSkill
- port-managerSkill
- product-contextSkill
- projectSkill
- refactorSkill
- techdebtSkill
- ui-specSkill
- web-researcherSkill

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
After initialization, customize for your project:
line 76

≈ “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

init-modular

Initialize a modular .claude/ directory structure with battle-tested agents, hooks, and rules.

What Gets Created

.claude/
├── agents/
│   ├── code-reviewer.md      # Code review before commits
│   ├── debugger.md           # Root cause analysis
│   ├── deep-researcher.md    # Deep research (Opus)
│   ├── general-researcher.md # Daily research (Sonnet)
│   └── lite-researcher.md    # Quick lookup (Haiku)
├── hooks/
│   ├── error-lesson-reminder.sh  # Session end reminder
│   └── session-start-read-lessons.sh  # Session start reminder
├── rules/
│   ├── code-quality.md       # Code quality standards
│   ├── git-workflow.md       # Git commit conventions
│   └── _error-lessons.md     # Error lessons log
└── settings.json             # Hook configurations

Component Details

Agents

code-reviewer

Purpose: Code review before commits
Model: Sonnet
Focus: Quality, security, maintainability

debugger

Purpose: Root cause analysis and minimal fixes
Model: Sonnet
Focus: Find root cause, not symptoms

Research Agents (3-tier)

Agent	Model	Use Case
deep-researcher	Opus	Architecture, source analysis
general-researcher	Sonnet	Daily research, comparisons
lite-researcher	Haiku	Quick lookups, batch queries

Hooks

error-lesson-reminder.sh

Trigger: Session end
Action: Remind to record error lessons

session-start-read-lessons.sh

Trigger: Session start
Action: Show high-priority error lessons

Rules

code-quality.md

Function length limit (50 lines)
File length limit (700 lines)
Cyclomatic complexity limit (10)
TypeScript: no any
Comment guidelines

git-workflow.md

Commit message format
Type conventions (feat, fix, docs, etc.)

_error-lessons.md

Template for recording errors
Prevents repeating mistakes

Customization

After initialization, customize for your project:

Adjust limits in rules/code-quality.md
Add project-specific rules in rules/
Create custom agents in agents/
Modify hooks for your workflow

Why Modular?

Benefit	Explanation
Organized	Each concern has its own file
Version controlled	Track changes to individual configs
Shareable	Copy specific files to other projects
Extensible	Add new agents/rules without touching others

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