bycatlog22· 36 skills
Iterative skill tuning via execute-evaluate-improve feedback loop. Uses maestro delegate Claude to execute skill, Agy to evaluate quality, and Agent to apply improvements. Iterates until quality threshold or max iterations. Triggers on "skill iter tune", "iterative skill tuning", "tune skill".
$npx -y skills add catlog22/maestro-flow --skill skill-iter-tuneInstalls into the current project.
Run `npx skills use "https://github.com/catlog22/maestro-flow" --skill "catlog22/maestro-flow/skill-iter-tune"` 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/catlog22/maestro-flow" that are relevant to the current task. Run `npx skills add "https://github.com/catlog22/maestro-flow"` and select the relevant skills, then follow their instructions.