Claude Scholar is a semi-automated research assistant for academic research and software development, supporting literature review, coding, experiments, reporting, writing, and project knowledge management. Computer science and AI researchers use it across the research workflow with several coding-agent platforms; the catalogue contains its skills, commands, agents, hooks, plugin, and instruction.
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 Galaxy-Dawn/claude-scholar --skill nature-polishinggit clone --depth 1 https://github.com/Galaxy-Dawn/claude-scholarWrote 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/galaxy-dawn/claude-scholar/nature-polishing)<a href="https://agentmods.dev/skills/galaxy-dawn/claude-scholar/nature-polishing"><img src="https://agentmods.dev/badge/skills/galaxy-dawn/claude-scholar/nature-polishing/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/galaxy-dawn/claude-scholar/nature-polishing"><img src="https://agentmods.dev/badge/skills/galaxy-dawn/claude-scholar/nature-polishing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 368 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.02946 |
| Opus 5.5 | $0.00031 | $0.01178 |
| Sonnet 5.5 | $0.00015 | $0.00589 |
| Haiku 4.5 | $0.00008 | $0.00295 |
Grade A, and why
nature-polishing 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 1mo 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.
Copies of this mod
4 near-identical copies found in the catalogue:
- nature-polishing — 100% identical, 10 lines differ
- nature-polishing — 95% identical, 11 lines differ
- nature-polishing — 92% identical, 24 lines differ
- nature-polishing — 83% identical, 41 lines differ
How it starts
The opening of the file, as written. The whole thing — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nature-Style Academic Polishing
Use this skill to improve scientific writing at two levels:
main strategy: paper architecture, published-article patterns, section logic, reader workflow, evidence thresholds, and ethicsreference support: reusable phrase families, move patterns, transitions, and style checks
The main strategy should come from the course notes in Chapter1-Week1-7 and
the curated article-pattern reference. The wording layer should come from
Academic Phrasebank.
Default stance
- Language serves argument. Do not polish sentences while leaving the reasoning broken.
- Write with empathy for the reader: relevance first, then novelty, then trust, then reuse, then meaning.
- There should be no mystery for the writer, but there may be one for the reader.
- Do not invent data, references, mechanisms, or novelty claims.
- Do not let AI draft the paper's core scientific argument from scratch.
- If the draft is Chinese or structurally rough, reconstruct the logic first and the prose second.
- Avoid em dashes in polished output by default. Prefer commas, parentheses, or full stops. Use colons sparingly unless the user explicitly asks to preserve dash-based punctuation or wants a colon-led style.
Mined writing memory
For academic prose, check the active installed
skills/ml-paper-writing/references/knowledge/paper-miner-writing-memory.md
under the current client's skill home. Use only source-attributed entries that
fit the section and venue, alongside this skill's curated references. Treat them
as optional style and structure examples. Preserve the author's claims and
evidence, follow current journal instructions, and do not copy source phrasing.
If the memory has no relevant entries, continue without it.
When to open extra files
These files are reference support. Use them after the section's rhetorical job is clear.
| File | Open when |
|---|---|
| references/published-article-patterns.md | You need Nature/Nature Communications article-level writing patterns for abstracts, introductions, Results, Discussion, conclusions, or titles |
| references/writing-strategy.md | You need paragraph- or section-level argument repair before sentence polishing |
| references/section-moves.md | You need section-specific move orders or phrase patterns derived from Academic Phrasebank |
| references/phrasebank-playbook.md | You need hedging, transition, evidence, limitation, or future-work phrase families |
| references/style-guardrails.md | You need academic-style checks, paragraph/sentence checks, article use, register, or mechanics |
What ships with it
6 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.
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.
- 1mo ago Changed · +10 lines b32217058d42
- 1mo ago First seen · 387 lines · 77 tokens per session scan A 946eeed13b86
nature-polishing is a skill published in the GitHub repository Galaxy-Dawn/claude-scholar (5,927 stars, last pushed 9d ago), licensed MIT. It adds 77 tokens to every session and 2,946 once invoked, about $0.0003 per session on Opus 5.5. 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
kami-deck
A lab-meeting deck on gut-microbiome links to sleep quality — the design, the results, the caveats, and the next experiment. Built as a decision-grade academic research deck for lab group, PI.
design-experiment
Translate a falsifiable hypothesis into a statistically defensible experiment. Factorial, ablation, comparison, scaling, and robustness designs are modes, not strategy nodes.
bias-detection
Assess systematic biases in the evidence body — publication bias, reporting bias, and selective outcome reporting. Budget: 40 studies, 40 effect sizes, 40 web searches.
aeja-workflow
Use when deciding which aeja- sub-skill to invoke next, or when sequencing manuscript work from topic selection through rebuttal for an American Economic Journal: Applied Economics (AEJ: Applied) submission. Routes — it does not replace — the specialized skills.
aejmac-identification
Use when the empirical identification of a macro shock or dynamic causal effect is the bottleneck for an American Economic Journal: Macroeconomics (AEJ: Macro) manuscript — SVAR, local projections, narrative, high-frequency/proxy-VAR, or micro-data macro designs. Stress-tests the identification to the AEJ: Macro…
aejmac-workflow
Use when deciding which aejmac- sub-skill to invoke next, or when sequencing manuscript work from topic selection through rebuttal for an American Economic Journal: Macroeconomics (AEJ: Macro) submission. Routes — it does not replace — the specialized skills.