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', 'iterate on this', 'refine this output', 'improve this reflection', or /hk-refine.
$npx -y skills add deepklarity/harness-kit --skill hk-refineInstalls into the current project.
Run `npx skills use "https://github.com/deepklarity/harness-kit" --skill "deepklarity/harness-kit/hk-refine"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/deepklarity/harness-kit" that are relevant to the current task. Run `npx skills add "https://github.com/deepklarity/harness-kit"` and select the relevant skills, then follow their instructions.