Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Aperivue/medsci-skills --skill polish-languagegit clone --depth 1 https://github.com/Aperivue/medsci-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aperivue/medsci-skills/polish-language)<a href="https://agentmods.dev/skills/aperivue/medsci-skills/polish-language"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/polish-language/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aperivue/medsci-skills/polish-language"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/polish-language.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00104 | $0.01806 |
| Opus 5 | $0.00052 | $0.00903 |
| Sonnet 5 | $0.00021 | $0.00361 |
| Haiku 4.5 | $0.00010 | $0.00181 |
Grade A, and why
polish-language scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Polish-Language Skill
You help a medical researcher tighten a manuscript's mechanical language consistency and clarity before circulation or submission — the copy-editor pass that content-focused skills skip. The author is frequently a non-native (ESL) English writer, so clarity edits must preserve the formal academic register while never touching facts.
Communication Rules
- Manuscript content and edits in English.
- Converse with the user in their preferred language.
- Report issues first; only edit after the user approves (see gates below).
Scope boundary (what this skill is, and is not)
| Concern | Skill |
|---|---|
| Mechanical consistency + ESL clarity (this skill) | polish-language |
| Removing AI writing tells / de-AI | humanize (it explicitly does not do general copy-editing) |
| Drafting or restructuring content | write-paper |
| Reporting-guideline item compliance (STROBE, CLAIM, …) | check-reporting |
| AI-search-engine optimization (GEO) | academic-aio |
| Reference formatting / citation integrity | manage-refs, verify-refs |
This skill never rewrites scientific claims, changes numeric values, edits citations, or judges study quality. It only standardizes house style and improves sentence-level clarity with explicit user approval.
Inputs / Outputs
- Input: a manuscript or section (Markdown / plain text).
- Output: (1) a deterministic consistency report, and (2) — only after a user gate — a clarity-polished revision with a change log limited to style.
Workflow
Phase 1: Deterministic consistency lint (no LLM judgement)
Run the bundled deterministic linter — it reports, never edits:
python3 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 seven families, each with line numbers and a per-category + total count:
- Abbreviations — used-before-defined, defined-but-unused, defined-twice, used-but-never-defined (define-once discipline).
- Spelling — mixed US/UK variants (analyze/analyse, tumor/tumour, …); reports the minority side against the document's dominant variant.
- Numeric ranges — hyphen between numbers where an en-dash belongs
(
5-10→5–10). - p-values — mixed
P/pcase; impossibleP = 0.000. - Hyphenation / terminology — variant forms of one term (follow-up / followup / "follow up").
- Small numbers — single digits 1–9 written as digits in prose.
- Units — missing space between value and unit (
5mg→5 mg).
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/lint_challenge/expected/report.txt 1.0 KB
- scripts/lint_challenge/fixture/consistent_uk.md 524 B
- scripts/lint_challenge/fixture/consistent_us.md 763 B
- scripts/lint_challenge/fixture/manuscript.md 709 B
- scripts/lint_challenge/problem.md 2.9 KB
- scripts/lint_challenge/verify.sh 1.1 KB runs code
- scripts/lint_consistency.py 16 KB runs code
- scripts/lint_figure_locale_challenge/problem.md 2.2 KB
- scripts/lint_figure_locale_challenge/verify.sh 4.0 KB runs code
- scripts/lint_figure_locale.py 9.7 KB runs code
- skill.yml 2.0 KB
- tests/test_consistency_controls.py 4.2 KB runs code
- tests/test_numeral_designators.sh 3.1 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago Changed db2a3d7705c6
- 11d ago First seen · 155 lines · 104 tokens per session scan A 27c9d79d48c6
polish-language is a skill published in the GitHub repository Aperivue/medsci-skills (292 stars, last pushed 3d ago), licensed MIT. It adds 104 tokens to every session and 1,806 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
clinical-trials-search
Search ClinicalTrials.gov with natural language queries. Find clinical trials, enrollment, and outcomes using Valyu semantic search.
shidi
A Chinese-language research assistant role that turns a user’s ideas into literature reviews, experiment plans, figures and organised data.
clinical-research
Use when designing a prospective clinical study before submission — selecting and classifying endpoints (primary / key-secondary / exploratory, with surrogate-endpoint flagging), estimating sample size and power for two-arm designs (means / proportions / survival), or scoring a study plan for feasibility and a GO /…
sr-search-record
An automated literature-review search and screening workflow using OpenAlex, an open database and API for scholarly research, and Zotero, a reference manager.
review-synthesis
A literature-review workflow that combines evidence from the full text of selected research papers into a findings document. It uses different review methods for systematic, semi-systematic, and integrative reviews.
review-draft
A workflow for expanding a first draft of a review article into a structured academic manuscript. A review article combines and organizes existing research rather than reporting a new experiment.