Conciseness

The body is lean procedural instruction with no conceptual padding: 'Run `git fetch origin` first so the base is current. Stop here if the ref does not resolve or the diff is empty.' Every sentence instructs and assumes Claude's competence, matching the anchor where every token earns its place; there is no over-explanation to trim for a 4.

Actionability

Fully executable guidance throughout: exact commands ('git diff origin/main...HEAD', 'git worktree add', 'gh pr checkout <n>', 'python3 scripts/ai-context.py pull-requests', 'gh issue view <n>'), an argument-to-diff mapping table, and a copy-paste report template. Specific instructions cover the common cases (empty args, ref, PR number, path), matching the top anchor.

Workflow Clarity

Five clearly sequenced steps with explicit validation: a dedicated verification step with decision rules (CONFIRMED / PLAUSIBLE / Dropped), an early stop condition for unresolvable refs or empty diffs, and a fix feedback loop ('add a failing test first for each correctness fix, rerun the narrowest check that proves it'). This matches the anchor with explicit validation steps, feedback loops, and a checklist-style report format.

Progressive Disclosure

A single self-contained file with clear section headers, no nested references, and nothing that belongs in a separate file — the five pass briefs are one-line descriptions that correctly stay inline, and no bundle files exist to point to. Content is appropriately placed in one level with easy navigation, matching the top anchor.

Specificity

Enumerates multiple concrete actions with comprehensive coverage: 'checks correctness, the repository's documented rules, the originating issue or spec, every consumer of a changed concept, and cleanup (reuse, simplification, efficiency, depth of fix), then verifies each finding against the code before reporting it'. This matches the anchor for multiple specific concrete actions with comprehensive coverage; there are no missing capability areas to place it at 4.

Completeness

Explicitly answers both questions: what ('It checks correctness, ... every consumer of a changed concept, and cleanup ..., then verifies each finding') and when ('Use this skill whenever the user asks to: review a diff, branch, commit range or PR, ...'). Clear 'what' plus explicit concrete trigger phrases is the top anchor; not 4 because the 'when' clause is already fully explicit and specific.

Trigger Term Quality

The trigger list covers the natural phrases a user would say: 'review a diff, branch, commit range or PR, check a change before opening a PR, run a pre-Codex review, or find what a change missed'. Synonym and variation coverage is comprehensive for this domain, matching the top anchor.

Distinctiveness Conflict Risk

The opening scopes the skill to a clear niche ('Review a skillshare change before it becomes a pull request'), but the trigger phrases 'review a diff, branch, commit range or PR' are generic code-review triggers that overlap with any general code-review skill. Mostly distinct with minor overlap risk against a closely related skill — the anchor for 4, not 5, since conflict risk with generic review requests is not minimal.