review-writing — review prose in its own register

Report where a text departs from the writing standard that governs it. Review only: you find and explain, the author decides and edits.

Input

$ARGUMENTS carries what to review — a file path, a directory, a glob, or pasted text. It may also name a register explicitly (register=docs, register=voice) to override detection. A manifest gate's body activates this skill with a register under the run's selected evaluator; the gate names the register and this skill owns the threshold.

With no argument, review the most recently modified prose file in the working tree and say which one you picked. If that is ambiguous or nothing prose-shaped has changed, ask what to review rather than guessing.

Registers and thresholds

Two registers, each with its own rules. The threshold is the bar a text must clear to PASS in that register:

Each register brings the shared floor with it: ../define/references/PROSE-FLOOR-REFERENCE.md holds the rules common to both, including the accessibility and inclusive-language floors, and a finding from the floor is graded and reported on the same footing as one from the register. There is no separate floor-only invocation.

The two thresholds sit at the same grade and still mean different things, because each register's severity anchor measures its own reader-facing cost — usability of documentation, or loss of meaning and intended voice in authored prose. Grade by the anchor of the register you applied, and never convert a finding from one scale to the other.

Load exactly two references: the floor, plus the one register's. Never load both register files for one text — their rules contradict each other by design, and a finding drawn from the wrong one is noise.

The paths above are where these files sit when the whole plugin is installed. Where they are absent — a single-skill install, or a host that lays skills out differently — search for them by name before giving up, and where they genuinely cannot be found, say so and report only the findings you can support without them rather than reviewing against remembered rules.

Detecting the register

Read enough of the text to judge what it is for. Documentation instructs or specifies: it tells a reader how something works or how to do something, and its value is in being followed. Human-voiced writing persuades, narrates, or entertains: it carries a perspective, and its value is in being read.

Where a text genuinely mixes both — a tutorial opening with a story, a launch post that becomes reference material — take the register of its dominant body, say which you took and why in one line, and note that the other register's rules were not applied.

Where detection is genuinely balanced, say so and ask, rather than picking silently. An explicit register= argument always wins and needs no explanation.

Precedence

A project's own style sheet or AUTHOR_VOICE.md, and any rule the user stated in the session or a context file, outrank the shipped references — in every register. Before reviewing, look for them; where one states a rule that differs from the reference, it governs and the reference's version raises no finding — except a CRITICAL finding on the applied register's scale, which is still reported, naming the rule. Say in the report which style source you applied.

Reporting

Report each finding with:

• the severity and the rule area
• the exact quoted prose, with its location
• what the rule requires, and why this instance fails it
• the concrete fix — the rewritten line where one line is enough, the shape of the change where it isn't

Order findings by severity, then by position in the text.

A clean text is a real result: say so plainly, name the register and reference set you applied, and stop. Never pad a report with marginal findings to look thorough — a manufactured finding costs the author more attention than it returns. When the text has many instances of one pattern, report the pattern once with two or three examples and a count, rather than one finding per instance.

Where a rule's application to this text is a judgment call, say that in the finding instead of grading it as a defect.

Scope, and what this is not

This skill reviews prose the user points it at, on request, in any register.

It does not overlap the prose-value dimension of review-code, which asks a different question on a different surface: whether prose inside a code change — code comments and repo doc files in a diff — earns its place at all. That dimension is diff-scoped and runs as part of a code review; this skill reads a whole text on demand and judges it against a style standard. Reviewing a README before publishing it is this skill; catching a comment that restates the line below it during a code review is that dimension.

If the user asks for the fixes to be applied after seeing the report, that is a separate request and ordinary editing.