Skip to main content
skill CX Codex

normalize-agent-for-claude — Claude Code skill: setup guide

normalize-agent-for-claude audits AGENT.md files and optimizes them for Claude Code runtime by separating role identity from procedures.

no license 117 installs ★ 5 updated 2026-08-31

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add ulpi-io/skills --skill normalize-agent-for-claude -a claude-code
Open on GitHub

What normalize-agent-for-claude does

This skill audits an existing AGENT.md against real Claude Code runtime mechanics. Because Claude treats the markdown body as the system prompt, keeping step-by-step instructions inside the main prompt wastes context budget. The workflow preserves core identity and decision rules in the body while directing procedural commands into external skills.

Execution starts in plan mode by default. The tool inspects frontmatter fields, line count, and tool surface, then writes a DAG migration plan to .ulpi/plans/agents/ in both markdown and JSON formats. Changes are applied directly only when invoked with --mode rewrite.

The routine demands references/claude-agent-runtime.md before generating recommendations. It rejects skill headers like allowed-tools on agent files and will not process SKILL.md targets.

What it helps with

  • audit oversized AGENT.md files against Claude runtime rules
  • extract procedural steps into skills without losing role identity
  • generate a structured DAG migration plan in markdown and JSON
  • strip invalid skill-only frontmatter attributes from agent configs

Example prompts for the agent

  • Create a migration plan for an agent: normalize-agent-for-claude ./agents/reviewer
  • Rewrite prompt and frontmatter directly: normalize-agent-for-claude ./agents/tester/AGENT.md --mode rewrite

How to install normalize-agent-for-claude

1Skills CLI (Vercel)

npx skills add ulpi-io/skills --skill normalize-agent-for-claude -a claude-code

2Manually: put the files in place

~/.claude/skills/normalize-agent-for-claude/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/normalize-agent-for-claude/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about normalize-agent-for-claude

How to install normalize-agent-for-claude in Claude Code?

Run npx skills add ulpi-io/skills --skill normalize-agent-for-claude -a claude-code. The file will be placed into ~/.claude/skills/normalize-agent-for-claude/SKILL.md.

What does normalize-agent-for-claude do?

It checks AGENT.md against Claude Code architecture constraints, trims unnecessary context, and isolates procedural steps from role descriptions.

Does it modify files immediately?

No. The default mode is plan, which only produces reports in .ulpi/plans/agents/. It alters agent files only when --mode rewrite is explicitly passed.

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set49

The whole set →
nestjs Guides AI agents through NestJS module design using project-specific dependency injection, thin controllers, and class-validator DTOs. CX Codex +1 129installs browse-stealth The browse-stealth skill runs Camoufox through the browse CLI to inspect and use sites that block ordinary browser automation. Reach for it when a page shows a CAPTCHA, a 403, or a browser challenge. CX Codex +1 126installs docker Guides your agent to write container setups with multi-stage builds, non-root users, pinned image tags, and strict .dockerignore hygiene. CX Codex +1 122installs normalize-skill-for-claude normalize-skill-for-claude is a Claude Code skill that audits an existing skill, plans changes, and rewrites its metadata, body, and references for routing. CX Codex +1 118installs bugfix-crate The bugfix-crate skill works through an existing Rust crate issue file one finding at a time, testing each change and recording its outcome. CX Codex +1 117installs review-crate review-crate reads every file in a Rust crate, runs tests, and reports bugs with exact line numbers. Use it to catch logic errors, panics, race conditions, and validation gaps that unit tests miss. CX Codex +1 115installs create-tests-extract create-tests-extract extracts heavy inline test blocks into adjacent files while preserving access to private module items. CX Codex +1 113installs browse-aeo browse-aeo audits how ready a page is for citation in AI answers, then checks its visibility across Google AI Overviews and Perplexity. CX Codex +1 111installs

Project sponsors

Companies that keep this analytics open