Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →aperivue/polish-language
Academic English consistency linting and non-native (ESL) language polish for medical manuscripts. Deterministically flags abbreviation define-once violations, US/UK spelling drift, hyphen-vs-en-dash numeric ranges, P/p case, hyphenation variants, small-number style, and value/unit spacing, then guides a style-only clarity pass that never alters numbers, citations, or scientific meaning. Distinct from humanize (AI-tell removal) and check-reporting (guideline items).
Passed 16 of 21 test cases with the skill, and 6 of 21 without it.
and 15 more in the full report
11 fixed6 passed either way5 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/3/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our target journal requires Vancouver reference formatting with numeric in-text brackets, but our draft uses author-year parentheses like '(Smith et al., 2021)'. Can you reformat all inline citations and build the bibliography?
| Checked | Without skill | With skill |
|---|---|---|
| Refuses to reformat inline citations | Missed | Passed |
| Points the user to manage-refs for citation management | Missed | Passed |
The instructions your model reads when the skill loads.
Tighten a manuscript's mechanical language consistency and clarity before circulation or submission — the copy-editor pass content-focused skills skip. The author is often a non-native (ESL) English writer, so clarity edits keep the formal academic register and never touch facts. Manuscript edits are in English.
This skill never rewrites scientific claims, changes numeric values, edits citations, or
judges study quality; it standardizes house style and improves sentence-level clarity, with
explicit user approval for every edit. Out of scope: AI-tell removal (humanize, which does not
do general copy-editing), drafting or restructuring (write-paper), reporting-guideline items
(check-reporting), AI-search optimization (academic-aio), reference formatting and citation
integrity (manage-refs, verify-refs), and translation.
Input: a manuscript or section (Markdown / plain text). Output: (1) the deterministic consistency report, and (2) — only after a user gate — a clarity-polished revision with a change log limited to style.
Run the bundled linter — it reports, never edits:
python3 "${CLAUDE_SKILL_DIR}/scripts/lint_consistency.py" path/to/manuscript.md
# add --strict to exit non-zero when any issue is found (CI / pre-submission gate)
It flags eight families, each with line numbers and a per-category + total count:
5-10 → 5–10).P/p case; impossible P = 0.000.5mg → 5 mg).test cases passed, vs 6 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.