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
  • 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.

Back to skills

Design In Repo

ASecurity

Version design files inside the repo as source of truth. Use when saving .pen JSON to design/, avoiding cloud-only design, binary merge conflicts, splitting tokens lib vs pages. TRIGGER when: design in repo, .pen JSON, gitattributes binary, design tokens lib, design conflict. Gatilhos PT: design versionado no repo, salvar .pen, conflito de design, biblioteca de tokens, nunca editar JSON na mão.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgogit

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill design-in-repo --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Design In Repo?

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

Security grade badge for Design In Repo
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-design-in-repo/badge)](https://www.skillsdirectory.com/skills/majinmagros-design-in-repo)

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

Download Zip
Files
SKILL.md
---
name: design-in-repo
description: Version design files inside the repo as source of truth. Use when saving .pen JSON to design/, avoiding cloud-only design, binary merge conflicts, splitting tokens lib vs pages. TRIGGER when: design in repo, .pen JSON, gitattributes binary, design tokens lib, design conflict. Gatilhos PT: design versionado no repo, salvar .pen, conflito de design, biblioteca de tokens, nunca editar JSON na mão.
---

# Design in Repo

## Quando usar

- Design precisa ser versionado junto do código, não só na nuvem.
- Arquivos `.pen` (JSON) vivem em `design/`.
- Time sofre com merge de design ou design desatualizado vs. código.
- Precisa ler design localmente sem depender de app/nuvem.

## Passos

1. **Salve o `.pen` JSON em `design/`.** Estrutura sugerida: `design/lib/` (tokens, componentes) + `design/pages/<area-ou-time>/`. Commit junto da PR que implementa.
2. **Leia local, não na nuvem.** Use `cat` / `JQ` / `grep` local para inspecionar tokens, telas e diffs. Nuvem é espelho, repo é oráculo.
3. **Trave o merge como binário.** Em `.gitattributes`: `*.pen merge=binary diff off`. Nunca faça merge textual de `.pen`.
4. **Separe lib de pages.** `lib` = tokens e componentes compartilhados (dono: design system). `pages` = uma pasta por área/time. Isso reduz conflito e deixa ownership claro.
5. **Resolva conflito regenerando, nunca editando.** Conflito em `.pen`? Descarte um lado e regenere pelo app a partir da versão canônica. Nunca edite JSON na mão para mudança semântica (cor, layout, hierarquia).
6. **Edição manual só para metadado trivial.** Renomear arquivo, mover pasta, bump de versão: ok via texto. Mudança visual/semântica: sempre pelo app, depois exporte para `design/`.

## Regras

- `*.pen` é binário para o git. Sem exceção.
- JSON editado na mão nunca representa decisão de design.
- `lib` compartilhada tem dono único. Time não edita token global sem review.
- Design fora de `design/` não existe para CI nem para review.
- Nuvem divergiu do repo? O repo vence até reconciliação explícita.

## Related skills

- `design-system` — pilares e contrato do design system.
- `cloud-design-prototyping` — prototipação na nuvem antes de versionar.

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
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. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 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', ...

686011 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.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 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 →