agentrigs
+ submit rig
~ / rigs / yair-zehavi / claude-code-skills

yair-zehavi/claude-code-skills

Claude Code skills that turn repeatable editorial and design-review work into a written method: a Hebrew AI-writing humanizer, an adversarial UI QA loop and an art direction method for graphics that do not look AI-generated.

↗ GitHub ★ 0 MIT updated today collection Claude Code
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~34 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit yair-zehavi/claude-code-skills/skills ./rig-claude-code-skills/skills

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit yair-zehavi/claude-code-skills/skills/art-directed-graphic .claude/skills/art-directed-graphic
$ npx degit yair-zehavi/claude-code-skills/skills/design-qa .claude/skills/design-qa
$ npx degit yair-zehavi/claude-code-skills/skills/humanizer-he .claude/skills/humanizer-he

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (3)

art-directed-graphicdesign-qahumanizer-he

Similar rigs

plugin87/ux-ui-agent-skills
Turn Claude into a senior design architect: DTCG tokens, 50 components, WCAG 2.2 AA-AAA, 138 design systems, any-framework code, and 48 objective gates that fail the build instead of faking success.
★ 1,531 project Claude CodeCodex 2 mcp 25 skills 1 agents 3 hooks 4d ago
Skill Collector 18.4k tok ·
alvaroofernaandez/dotfiles
Personal macOS terminal and AI agent environment — tmux, yazi, and Ghostty configs plus full Claude Code and OpenCode setup (skills, subagents, commands, hooks).
★ 2 setup Claude CodeCodex 72 skills 20d ago
Skill Collector 6.7k tok ·
calven-ai/marketing-as-code
The starter repo for a marketing team that runs on code: strategy, content, decisions and 99 agent skills as plain text a coding agent reads and writes, with a human review gate.
★ 8 project Claude CodeCodexCursor 3 mcp 111 skills 36 agents 1 hooks today
Orchestrator 15.5k tok ·
tstapler/dotfiles
Tyler Stapler's dotfiles
★ 8 setup Claude CodeCodex 147 skills 31 agents 9d ago
Orchestrator 10.0k tok ·
copied ✓