Skill of Skills
🔌 pluginActivePromisingmedium

naksha-studio

by Adityaraj0421

A virtual design team for Claude Code, Cursor, Windsurf, Gemini CLI, and Copilot — 26 roles, 60 commands, 13,800+ lines of expert design knowledge. Your agency's design brain, inside your terminal.

Stars

289

Skill Type

🏗️ Code Scaffolding & Templates

Quality Score

99/200

License

MIT

Forks

22

Last Updated

Jun 11, 2026

Discovered

Apr 4, 2026

Validation

Passed

github.com/Adityaraj0421/naksha-studio

Quality Breakdown

99/ 200

Content Signals

○Gotchas/Edge Cases+40
✓Progressive Disclosure+30
○Trigger Description+20
✓Verification/Safety+20
✓Code Examples+15
✓Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
○Real Usage (Issues)+10
○Single Responsibility+10
○Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Contains install.sh script that performs automated setup without explicit user approval gates
  • Designed to inject rules/instructions into multiple AI coding tools (Claude Code, Cursor, Windsurf, Gemini CLI, Copilot) which could influence tool behavior
  • Creates persistent configuration in multiple tool directories (.claude-plugin, .cursor, .windsurfrules, .github/copilot-instructions.md)
  • GitHub workflows present (design-check.yml, quality-check.yml, validate-structure.yml) that could execute automated processes
  • Large prompt injection surface area (13,800+ lines of design knowledge) that gets injected into AI tool contexts
  • Multi-agent orchestration design (26 specialist roles that activate automatically) indicates autonomous spawning behavior