review-abstractlisted

Review an existing scientific abstract from a writing perspective using the categorization exercise from Zucolotto's course, labelling every sentence with the part of the six-part model it implements, then reporting missing parts, a weak gap, vague results, and style defects with concrete rewrites. Use when asked to review, critique, check, improve, or give feedback on an abstract.
yuryalencar/ai-skills · ★ 0 · Code & Development · score 73

Install: claude install-skill yuryalencar/ai-skills

# /review-abstract Diagnose an abstract and hand back specific, actionable rewrites. This is a reviewer's pass over the writing, not over the science: you are not judging whether the results are good, only whether the text delivers them. ## Before anything else 1. **Load the style rules.** Invoke `paper-writing-style` and read `references/human-voice.md`. If it is not installed, work from the condensed rules in `create-abstract`. 2. **Lock the language.** Use the language of the user's first message for the whole run and do not switch. Any rewritten text you produce is in English. 3. **Get the abstract.** Read it from the path given, from the manuscript in the working directory, or from what the user pasted. If there is a full manuscript available, read it too: it is the only way to tell whether the abstract's claims match the paper. ## Step 1: categorization This is the exercise the course builds the whole method on. Go sentence by sentence and label each with the part it implements: | Label | Part | | :--- | :--- | | `CONTEXT` | Broad field and its importance | | `GAP` | What is unresolved. Usually opens with `however` | | `PURPOSE` | What this paper reports | | `METHODS` | How it was done | | `RESULTS` | The principal findings | | `CONCLUSIONS` | How the results advance the field | | `NONE` | Implements nothing. This is a finding in itself | One sentence may carry two parts; label both. Present the categorization as a table with each sentence and its