📄 skillActivePromisingmedium

ai-devkit

Make AI coding agents follow a repeatable engineering workflow with planning, memory, verification, skills, and review. One config. All agents. Same workflow.

Supported Platforms

🤖 Claude Code🖱️ Cursor🧠 Codex

Stars

1.3k

Skill Type

🏗️ Code Scaffolding & Templates

Quality Score

87/200

License

Unknown

Forks

210

Last Updated

Jun 11, 2026

Discovered

Apr 17, 2026

Validation

Passed

github.com/codeaholicguy/ai-devkit

Quality Breakdown

87/ 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

Repository contains multiple AI agent configuration files (.claude, .cursor, .codex, .gemini, .agent) that define workflows and commands for autonomous agent operation
Persistent configuration modification through dot-directories (.claude/, .cursor/, .codex/, .agent/) that could alter agent behavior across sessions
Multi-agent orchestration support indicated by workflows for 'execute-plan', 'debug', 'code-review', and other autonomous operations without explicit human approval gates documented
GitHub Actions workflows present (.github/workflows/) that could enable CI/CD automation and deployment without clear human approval controls
NPM package distribution (ai-devkit) that installs automated agent infrastructure via 'npx ai-devkit@latest init' with interactive setup