About this skill
Mindful AI coding discipline framework. Activate ONLY when user invokes /kasi- command, explicitly requests code review / security audit / migration plan / legacy refactor, complains the AI is hallucinating or looping on ghost bugs, or asks for disciplined / checklist-driven work. Do NOT auto-trigger on routine coding edits, trivial bug fixes, or single-file changes — those should run without the framework loaded. Also routes UI mockup / prototype / pitch deck / visual design requests through Claude Design instead of hand-coding markup. Mode-gated: respects /kasi off|router|lite|full|ultra session state and project .kasidit/config.json.
Quick start
- Copy the install prompt. Use the green button above this README.
- Send it to your agent. Paste it into your coding agent’s chat and send.
- Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Review, license & listing details
This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.
Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.
0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1
Content SHA-256: 325563cff316e15c27f56fb3704fa95158841445c55ccbb811b557a391b91ed6
About this listing
- Category
- Security
- Reported license
- MIT
- Listing language (estimated)
- English
- Review status
- Not individually reviewed
- Agent compatibility
- Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.