skill-registry

Generate a compact skill catalog from SKILL.md files into .atl/skill-registry.md.

2|Updated Jul 29, 2025

Search Tags:#agent delegation #deduplication #project conventions #YAML frontmatter #skill registry #prompt injection defense #configuration automation

Ready to run

npx skills add https://github.com/kurojs/EnderDots --skill skill-registry-kurojs

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-registry
Source: https://github.com/kurojs/EnderDots/tree/main/.config/opencode/skills/skill-registry
Command: npx skills add https://github.com/kurojs/EnderDots --skill skill-registry-kurojs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Skill registry creation prevents sub-agents from needing to read many individual SKILL.md files by converting them into compact, pre-resolved rules that can be injected into prompts.

Core Features & Use Cases

Catalogs available skills: Scans all known user-level and project-level skill directories for SKILL.md files and deduplicates by keeping the most specific version.
Produces compact rules: Generates 5-15 line, actionable rule blocks per skill derived from Critical Patterns / Rules, suitable for direct copy into sub-agent prompts.
Persists an automated artifact: Writes the registry to .atl/skill-registry.md and optionally saves it to engram for cross-session reuse.
Collects project conventions: Detects convention index files (e.g., agents.md/AGENTS.md) and includes both the index file and all referenced paths so sub-agents avoid extra hops.

Quick Start

Ask the AI to update the skills registry after you add or remove skills so it regenerates .atl/skill-registry.md with current compact rules.

Frequently Asked Questions about skill-registry

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

FAQPage Schema

How do I generate a compact catalog of project skills for AI sub-agents?▼

To generate a compact catalog of project skills, you can use a skill registry to scan SKILL.md files and pre-digest them into 5-15 line actionable rule blocks. This prevents sub-agents from needing to read many individual files by injecting resolved rules directly into prompts.

What is the best way to prevent prompt injection when delegating tasks to AI agents?▼

Preventing prompt injection during agent delegation involves using pre-resolved constraint mappings extracted from project conventions. Generating a skill registry isolates actionable rules from raw SKILL.md files, providing a secure, compact rule set for injection.

How do I deduplicate project conventions and skill instructions across multiple directories?▼

You can deduplicate project conventions and skill instructions by scanning known user-level and project-level skill directories, keeping only the most specific version of each skill. This automated process ensures your sub-agents use the correct, resolved rules.

Does the skill registry process workflow-only skills and YAML frontmatter configurations?▼

The skill registry explicitly skips workflow-only skills and processes YAML frontmatter from discovered SKILL.md files. It focuses on extracting delegation-ready trigger mappings and constraints to persist in the .atl/skill-registry.md file.

How do I collect and index project conventions for automated agent configuration?▼

You collect project conventions for agent configuration by detecting convention index files like agents.md or AGENTS.md. The registry automatically includes both the index file and all referenced paths so sub-agents avoid extra file reading hops.

When should I update the skill registry artifact for cross-session reuse?▼

You should update the skill registry artifact whenever you add or remove skills, prompting the AI to regenerate the .atl/skill-registry.md file. This ensures current compact rules are persisted and optionally saved to engram for cross-session reuse.