hk-refine

SKILLWorkflowcommunity
v0.0.0deepklarityMITUpdated 1mo agoSource →

Iteratively improve any output by running a structured observe-hypothesize-change-rerun loop. Uses an organized scratch directory to prevent context blowup — the conversation stays thin while iterations accumulate on disk. Use when an output (reflection, plan, prompt, pipeline result) isn't good eno

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
89Repo stars
1Clients
1Formats
1mo agoLast update
Skill
Authordeepklarity
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor
Copilot
ChatGPT
Gemini
About

Iteratively improve any output by running a structured observe-hypothesize-change-rerun loop. Uses an organized scratch directory to prevent context blowup — the conversation stays thin while iterations accumulate on disk. Use when an output (reflection, plan, prompt, pipeline result) isn't good enough and needs systematic refinement. Triggers on: 'close the loop', 'this output isn't good enough',

Keywords
skillclaude