Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Layout Init

ASecurity

Map an existing codebase into LAYOUT.md, covering the folder tree with the purpose of each part, the components and how they connect, the database schema, and a list of the business logic with where each piece lives. Use when the user asks to map, document or describe the layout or architecture of an existing project.

2 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsrustnodedatabasedocumentation

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add TonyLikeDev/TrustMeBro --skill layout-init --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Layout Init?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Layout Init
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tonylikedev-layout-init-25054534/badge)](https://www.skillsdirectory.com/skills/tonylikedev-layout-init-25054534)

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: layout-init
description: Map an existing codebase into LAYOUT.md, covering the folder tree with the purpose of each part, the components and how they connect, the database schema, and a list of the business logic with where each piece lives. Use when the user asks to map, document or describe the layout or architecture of an existing project.
---

# Layout init

Write `LAYOUT.md` in the project root: a map that lets anyone, including Bob in a later session, find where things are and where a new addition fits without rereading the code. Every entry comes from the code and names its file.

Template: `.bob/trustmebro/templates/LAYOUT.md`.

If `LAYOUT.md` already exists, update it in place instead of starting over, and report what changed.

## 1. Read

1. README, `AGENTS.md`, package manifests (`package.json`, `pyproject.toml`, ...) and the directory tree. Skip generated and vendored folders (`node_modules`, `venv`, `dist`, `build`, caches, data dumps).
2. Entry points, then each top-level module: what it provides and what it uses from the others.
3. The database: schema files, migrations, ORM models. When they disagree, the migrations win.
4. The logic: routes and handlers, services, jobs, validators, anything that encodes a business rule or a workflow.

## 2. Write `LAYOUT.md` from the template

- **Folder tree**: every folder and every file that matters, each with a one-line purpose. Group trivial files ("assets/: images").
- **Components**: one row each with path, responsibility and dependencies, then the main flows as `A → B → C`.
- **Database**: every table or collection with its key fields and relations, plus the file that defines it. Write "No database." if there is none.
- **Logic**: one line per piece of business logic: what it does, and `file:function` where it lives.

It is a map, not documentation: one line per entry, no code. Session start loads it only while everything fits in about 8,000 characters (roughly 3,500 left for the layout when the project also has a roadmap); a longer layout is only pointed to. So keep it tight, and for a large project stay at module level. Check that every path you write exists.

## 3. Report

Summarize in a few lines: components, tables, and anything surprising (dead code, a README claim the code doesn't back). Tell the user that from now on, asking to add something plans it against this layout and records it in `ROADMAP.md`.

Attribution

TonyLikeDevTonyLikeDev
View sourceMore from TonyLikeDev →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

695601 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →