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 LuuOW/meridian-mcp --skill scientific-writing-voicegit clone --depth 1 https://github.com/LuuOW/meridian-mcpWrote 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/luuow/meridian-mcp/scientific-writing-voice)<a href="https://agentmods.dev/skills/luuow/meridian-mcp/scientific-writing-voice"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/scientific-writing-voice/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/luuow/meridian-mcp/scientific-writing-voice"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/scientific-writing-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00077 | $0.01595 |
| Opus 5 | $0.00039 | $0.00797 |
| Sonnet 5 | $0.00015 | $0.00319 |
| Haiku 4.5 | $0.00008 | $0.00160 |
Grade A, and why
scientific-writing-voice 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 9d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scientific-writing-voice
When to invoke
- Writing a 200–800 word brief of a technical paper
- Drafting newsletter prose about research
- Calibrating an LLM system prompt that asks for science-journalism tone
- Editing a colleague's overly-hedged academic text toward a broader readership
The target register (what "Quanta-meets-Nature" actually means)
- Precise without being technical. Keep every quantitative claim (masses in MeV/c², statistical significance in σ, redshifts, temperatures). Strip the derivation apparatus (equations, Feynman diagrams, group-theoretic notation) — you're conveying what was found, not how to reproduce it.
- Confident, not hedging. Avoid "the authors claim / suggest / argue". State the finding. If you want to qualify, say "Under the assumption that dark matter couples only through the Higgs portal, the mass window narrows to…". Write conditions as conditions, not as linguistic hedges.
- Active voice, concrete subjects. Not "it was observed that" — "The Parkes Pulsar Timing Array observed…".
- Lead with the discovery, not the context. Readers of a brief have ~30 seconds to decide if they care.
- Short paragraphs (2–4 sentences). White space is a navigation aid.
Canonical structure (200–600 words)
TL;DR — one sentence, ≤40 words
Opens with a boldface **TL;DR:**. Names the phenomenon, the chief numerical result, and the setting.
TL;DR: Scalar-tensor mixing during a brief early matter-dominated epoch generates a stochastic gravitational-wave background in the nanohertz band compatible with the NANOGrav 15-year excess.
¶1 — What was studied
Name the system, the measurement or simulation, the scale. Do not explain what a pulsar timing array is unless the paper's novelty depends on it.
¶2 — How
Methodology in 2–4 sentences. Instruments, sample sizes, statistical frameworks. Mention what separates this attempt from prior work ("the first analysis that jointly fits the spectral index and amplitude").
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.
- 9d ago First seen · 109 lines · 77 tokens per session scan A b1aa51685ea4
scientific-writing-voice is a skill published in the GitHub repository LuuOW/meridian-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 1,595 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
nature-figure
Create, revise, audit, and export submission-grade scientific figures for Nature-family and other high-impact venues in Python (matplotlib/seaborn) or R (ggplot2/patchwork/ComplexHeatmap), including multi-panel plots, figures4papers-style work, and journal-ready SVG/PDF/TIFF outputs. Use for paper or scientific plots…
nature-reviewer
A tool for simulating peer review of a research paper from the reviewer’s point of view. Peer review is the process in which experts assess a paper before publication.
nature-paper-card
Build a source-grounded deep-reading Paper Card for one scientific paper, preprint, PDF, DOI, arXiv page, publisher article, or pasted paper text. Use when the user asks for a Paper Card, deep-reading literature card, single-paper deep analysis, module-by-module analysis, experiment-to-claim evidence chain…
nature-ref-verifier
A reference-checking workflow that compares bibliographic details across multiple sources. Bibliographic details include authors, title, year, volume, issue, pages, and DOI, the persistent identifier for a research publication.
nature-statistics
Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction, model…
nature-experiment-log
A workflow for turning experiment notes, images, audio, or text into structured Markdown laboratory logs with YAML metadata. It can also organize raw attachments and optionally connect the logs to Feishu or Obsidian.