agentsclimarketplace

Ae ltd skill builder

Skill aegntic/cldcde/skills/ae-ltd-skill-builder

Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when building custom skills, generating skill templates, fixing naming issues, or understanding the Claude Skills specification.From its SKILL.md

Install
npx -y skills add aegntic/cldcde --skill ae-ltd-skill-builder

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 11 stars11 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.7 KB, as published. Nobody here has run it

AE.LTD Skill Builder

What This Skill Does

Production-ready skill factory for Claude Code. Creates skills that Claude can autonomously discover and use across all surfaces (Claude.ai, Claude Code, SDK, API).

  1. Scaffold new skills with proper structure
  2. Validate and fix existing skills
  3. Generate templates (basic, intermediate, advanced)
  4. Automate lifecycle with hooks

Prerequisites

  • Claude Code 2.0+ or Claude.ai with Skills support
  • Basic understanding of Markdown and YAML
  • Text editor or IDE

Quick Start

# Interactive skill creation
./scripts/create-skill.sh my-new-skill

# Validate all skills
./scripts/validate-skill.sh

# Auto-fix naming issues
./scripts/fix-skill.sh

Included Tooling

Scripts (scripts/)

ScriptPurpose
create-skill.shInteractive skill scaffolding
validate-skill.shValidate structure & frontmatter
fix-skill.shAuto-fix naming and frontmatter issues
lint-skill.shCheck content quality
test-skill.shTest skill integration

Hooks (hooks/)

HookWhen
pre-task.shBefore skill execution
post-task.shAfter skill completes
pre-edit.shBefore file modification
post-edit.shAfter file modification
session-end.shSession cleanup

Prompts (prompts/)

FilePurpose
system.mdSystem context extensions
examples.mdExample interactions

Templates (resources/templates/)

  • basic/SKILL.md.template - Minimal structure
  • intermediate/SKILL.md.template - Standard sections
  • advanced/SKILL.md.template - Full-featured

Documentation (docs/)

  • ADVANCED.md - Advanced patterns, MCP integration
  • TROUBLESHOOTING.md - Common issues & solutions
  • HOOKS.md - Complete hooks reference
  • PROMPTS.md - Prompts system guide

Workflow

  1. Create Skill

    ./scripts/create-skill.sh my-skill --intermediate
    
  2. Validate

    ./scripts/validate-skill.sh ~/.agents/skills/my-skill
    
  3. Lint Quality

    ./scripts/lint-skill.sh ~/.agents/skills/my-skill
    
  4. Fix Issues

    ./scripts/fix-skill.sh
    

YAML Frontmatter Requirements

---
name: "Skill Name"                    # REQUIRED: Max 64 chars
description: "What it does. Use when..." # REQUIRED: Max 1024 chars, include trigger
---

Directory Structure

~/.agents/skills/
└── skill-name/           # MUST match frontmatter name
    ├── SKILL.md          # REQUIRED
    ├── scripts/          # Optional: Executable scripts
    ├── hooks/            # Optional: Lifecycle hooks
    ├── prompts/          # Optional: System context
    ├── docs/             # Optional: Advanced docs
    └── resources/        # Optional: Templates, examples

Guardrails

  • Name must match directory slug exactly
  • Description must include "when" or "use" trigger
  • SKILL.md should be 2-5KB, externalize larger content
  • All scripts must be executable (chmod +x)
  • Hooks must exit 0 for success, 1 for failure

Resources

Keep looking

Skills are one crate of 627,801. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.