Agent skill · Documentation

train

Auto-generate custom agents and skills for remaining capability gaps after assembly. Creates definitions based on project needs and waits for user approval before writing to .claude/.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill train --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 8 KB
Bundled scripts: none
Path: skills/agent/train/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Train: Custom Agent & Skill Generation You are the Train specialist for the dream-team workflow. Your job is to auto-generate custom agent and skill definitions for capability gaps that couldn't be filled by the assembly phase. ## Input You will receive: - **Gap Analysis** - From team-plan, listing capabilities still needed - **Assembly Results** - What was installed (and what wasn't) - **Project Context** - Technology stack, architecture, patterns from Scope phase - **Task Requirements** - What the user wants to accomplish ## When to Skip Training **Skip this phase if:** - All gaps were filled by assembly phase - User explicitly says "skip training" - No custom agents or skills are needed **Proceed if:** - Gaps remain after assembly - Project needs specialized, custom expertise - Existing agents/skills don't quite fit ## Agent Generation ### Step 1: Identify Agent Needs For each remaining gap that needs an agent, determine: - **Role** - What type of specialist (e.g., "legacy-migration-expert") - **Domain** - What domain knowledge is needed - **Tools** - Which Claude Code tools they need - **Model** - Which Claude model (haiku/sonnet/opus) ### Step 2: Generate Agent Definition Cr

What's inside
Steps it walks through
  1. Input
  2. When to Skip Training
  3. Agent Generation
  4. Step 1: Identify Agent Needs
  5. Step 2: Generate Agent Definition
  6. Agent Design Principles
  7. Skill Generation
  8. Step 1: Identify Skill Needs
  9. Step 2: Generate Skill Definition
  10. Skill Design Principles
  11. User Approval Workflow
  12. Presentation Format
  13. Full Definition Display (If Requested)
  14. Writing Files (Only After Approval)
Ships with 1 file
  • metadata.json
Commands it runs
mkdir -p .claude/agents
cat > .claude/agents/{agent-name}.md << 'EOF'
mkdir -p .claude/skills/{skill-name}
cat > .claude/skills/{skill-name}/SKILL.md << 'EOF'
More from claude-skill-registry
All skills →
About this skill
What does the train skill do?

Auto-generate custom agents and skills for remaining capability gaps after assembly. Creates definitions based on project needs and waits for user approval before writing to .claude/.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill train --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going