iterative-improvementlisted

Run a criteria-driven adversarial improvement loop: interview the user into a weighted, numerically scoreable criteria document, then repeatedly (1) have a hostile independent reviewer audit the work, (2) triage its findings into actionable changes, (3) execute them, and (4) have an independent scorer measure real progress against the criteria. Use this whenever the user wants something made *better* rather than made. The test is not the wording — it is whether two competent people could disagree about whether the work is finished; if yes, use this even when the request is short, scoped to a single file, or phrased without any of the words below. Typical phrasings: "improve this", "polish this", "take it to the next level", "make this world class", "audit and fix it", "iterate on this", "this is good but…", "keep going until it's great", "run N rounds on this" — across designs, landing pages, UI, codebases, architecture, docs, copy, or any artifact where quality is open-ended and there is no single correct an
fireheartjerry/jerry-skills · ★ 0 · Web & Frontend · score 73

Install: claude install-skill fireheartjerry/jerry-skills

# Iterative Improvement A loop for making something genuinely better when "better" has no test suite. The core problem with open-ended improvement is that both the target and the progress are invisible. An agent asked to "improve this design" will make *changes*, feel productive, and have no idea whether it moved toward or away from what the user wanted. Ten rounds of that produces churn, not quality. This skill fixes both halves. First it makes the target explicit and numerical, in collaboration with the user, so there is something to aim at. Then it runs a cycle where an independent hostile reviewer finds what's wrong, that criticism gets triaged into real changes, the changes get executed, and a *separate* independent scorer measures the result. The score is the feedback signal that tells you whether the loop is working. ``` INTERVIEW ──► CRITERIA DOC (weighted, scoreable, user-approved) │ ▼ ┌──────► HOSTILE REVIEW (independent, brutal, specific) │ │ │ ▼ │ TRIAGE (reason about it — accept, reject, defer) │ │ │ ▼ │ EXECUTE (make the changes, verify each) │ │ │ ▼ │ SCORE (independent scorer, fresh context) │ │ └────────────┴──► target hit / rounds spent / plateau ──► REPORT ``` ## When this fits Use it when t