mk-loop

SKILLWorkflowcommunity
v0.0.0ngocsangyemMITUpdated 2mo agoSource →

Use when autonomously improving a measurable scalar metric through bounded, git-tracked iterations: modify one scoped change, verify, keep or revert. Triggers on /mk:loop, ''optimize coverage/bundle size/lint count'', ''iterate until the metric improves''. NOT for subjective cleanup (see mk:cook), k

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
14Repo stars
1Clients
1Formats
2mo agoLast update
Skill
Authorngocsangyem
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor—
Copilot—
ChatGPT—
Gemini—
About

Use when autonomously improving a measurable scalar metric through bounded, git-tracked iterations: modify one scoped change, verify, keep or revert. Triggers on /mk:loop, ''optimize coverage/bundle size/lint count'', ''iterate until the metric improves''. NOT for subjective cleanup (see mk:cook), known-root-cause bugs (see mk:fix), behavioral grading (see mk:evaluate), or shipping (see mk:ship).

Keywords
skillclaude

No dependency coverage

This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.