agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
Refactor CLAUDE.md files to follow progressive disclosure principles. Use when CLAUDE.md is too long or disorganized.
$ npx -y skills add brianlovin/agent-config --skill reclaude --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/reclaudeContext preview
The summary Claude sees to decide when to auto-load this skill.
Refactor CLAUDE.md files to follow progressive disclosure principles. Use when CLAUDE.md is too long or disorganized.
name: reclaude description: Refactor CLAUDE.md files to follow progressive disclosure principles. Use when CLAUDE.md is too long or disorganized.
Refactor CLAUDE.md files to follow progressive disclosure principles.
I want you to refactor my CLAUDE.md file to follow progressive disclosure principles.
Follow these steps:
Report the current line count. Flag issues:
Read the workflow skill at `~/.claude/skills/workflow/SKILL.md` and incorporate its principles into the CLAUDE.md or a `.claude/rules/workflow.md` file. Adapt the content to fit the project — don't copy verbatim, but ensure the key behaviors are represented:
For short CLAUDE.md files, add a concise workflow section. For longer ones, create `.claude/rules/workflow.md` and link to it.
Check for a `## Verification` section with commands Claude can run after making changes. If missing:
This is critical—Claude performs dramatically better when it can verify its work.
Identify any instructions that conflict with each other. For each contradiction, ask me which version I want to keep.
Look for content that could become a **reusable global skill** in `~/.claude/skills/`:
If found, suggest creating a global skill with name and description.
Extract only what belongs in the root CLAUDE.md:
Organize remaining instructions into `.claude/rules/` files by category (e.g., TypeScript conventions, testing patterns, API design, Git workflow).
Identify content that should be removed entirely:
# Project Name One-line description. ## Commands - `command` - what it does (only non-obvious ones) ## Rules - [Topic](/.claude/rules/topic.md) — brief description ## Verification After making changes: - `npm test` - Run tests - `npm run lint` - Check linting
**Keep in CLAUDE.md:**
**Move to `.claude/rules/`:**
**Remove entirely:**
My agent configuration for Claude Code and Codex.
Repo: brianlovin/agent-config
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
Use Bun instead of Node.js, npm, pnpm, or vite. Provides command mappings, Bun-specific APIs, and development patterns.
Guide a user end-to-end through setting up Chrome Web Store API release automation in any repository. Use when asked to walk someone through OAuth/CWS…
Remove AI-generated code slop from the current branch. Use after writing code to clean up unnecessary comments, defensive checks, and inconsistent style.
Generate a complete set of favicons from a source image and update HTML. Use when setting up favicons for a web project.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…