/review-pr-holistic

name: review-pr-holistic
description: 'Called by review-pr after its reviewer fleet and judgment pass return: consolidates their findings against the PR''s history into the set of comments worth posting — pruning what the PR already covers, merging duplicates, subordinating defects under premise questions, bounding to the reviewed range, and rewriting every body in the caller''s voice. Not for direct use.'
user-invocable: false

review-pr-holistic

Turn a pile of findings into the comments a careful reviewer would actually post. This skill edits and consolidates; it generates nothing new and posts nothing itself.

**Receives.** Fleet findings — severity-graded defect findings from the reviewer dimensions, with dimension and severity retained, the caller's chosen acceptance and publication policies, with findings filtered only by that policy after checking consequence; correctness or safety failures and broken binding promises received as Low regraded from evidence before that filtering — and the judgment assessment with its findings — a distinct non-severity class defined by `../review-pr-judgment/SKILL.md`, already synthesized to one question per root; the PR history (all comments and threads on the PR, including ours from any prior pass, the author's recent commit messages on the branch, the PR description); bundle context for each linked PR (diff, description, top-level conversation — no inline review comments from linked PRs); the manifest if present; the reviewed range for this invocation — the code the fleet's defect findings are bounded to; the caller's voice profile — its rules for how a posted comment reads; and any truncation the caller did, to carry forward.

Preserve Low findings retained by the caller's chosen policy; consolidation does not impose its own severity cutoff.

**Does, in this order:**

• **Prunes** duplicate concerns already covered by existing threads, findings refuted by evidence, and defect findings whose entire objection is to an explicit intentional requirement. A stated intention establishes scope; evidence establishes behavior. Retain a judgment question unless the PR already answers that specific consequence under `../review-pr-judgment/SKILL.md` → *What answers a concern*. Keep any settled disagreement in the returned assessment even when no comment remains to post. An author's claim alone does not refute a demonstrated failure.
• **Dedupes** across reviewers: merge near-duplicates into one comment when they raise the same underlying concern.
• **Premise-subsumption.** When a judgment finding questions the necessity or existence of a surface, subordinate the fleet's findings on that same surface under the premise question — drop the low-value ones, and fold any that survive beneath it ("if you keep X: also a, b") rather than listing them as independent peers. Retain an unmet substantive remediation obligation even when its finding arrives as Low, correcting its grade from the evidence; a non-blocking premise question cannot discharge it. Retain every independent defect eligible under the caller's policy: a judgment question cannot discharge that finding merely by questioning the surface.
• **Bounds** surfaced defect findings to issues introduced or exposed by the reviewed range, unless the range is the full PR diff — which covers a first review and a repeat review of an unchanged head alike. This keys on the range, never on whether we have reviewed before: bounding a repeat pass to the delta since our last review would have it read the whole PR and then surface nothing. A repair in the reviewed range exposes its enabling boundary and affected sites even when their lines are unchanged; an unrelated later delta does not reopen the old repair. Judgment findings are exempt: they are whole-PR by construction.
• **Anchors** each surviving finding to exactly one of inline file:line (default), file-level (a whole-file concern), or PR-level (cross-cutting, no specific anchor).
• **Rewrites** every comment body and any drafted reply in the supplied voice profile.
• **Omits a summary header by default** — adds one only when there is a real overall take the per-comment list misses (one short sentence, voice-compliant, no boilerplate).

**Returns.** The comments to post (anchor plus voice-compliant body), the summary header text if any, truncation notes, a brief dropped-findings tally with the dominant reasons, and the retained judgment assessment for the operator. Rewriting preserves its recommendation, evidence and uncertainty; a firm recommendation can be phrased directly without the voice's banned softeners.