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 hamzabellouch/agent-skills --skill academic-nature-nature-datagit clone --depth 1 https://github.com/hamzabellouch/agent-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/hamzabellouch/agent-skills/academic-nature-nature-data)<a href="https://agentmods.dev/skills/hamzabellouch/agent-skills/academic-nature-nature-data"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/academic-nature-nature-data/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/hamzabellouch/agent-skills/academic-nature-nature-data"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/academic-nature-nature-data.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 | $0.00173 | $0.00967 |
| Opus 5 | $0.00086 | $0.00483 |
| Sonnet 5 | $0.00035 | $0.00193 |
| Haiku 4.5 | $0.00017 | $0.00097 |
Grade A, and why
nature-data 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.
This is a copy
89% identical to nature-data — 16 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nature Data Availability — Router
This skill is split into two layers:
- A static layer under
static/that holds versioned, reusable content fragments (the default stance and source hierarchy, the Chinese-user operating mode, and the workflow with output format). - A dynamic layer (this file plus
manifest.yaml) that loads the core every time and reaches for the deeper policy/repository/FAIR references only when a step needs them.
Do not try to apply the data-availability logic from memory or from this router. Always load fragments from disk as described below.
Routing protocol
Follow these four steps every time the skill is invoked.
1. Load the manifest and the core layer
Read manifest.yaml. Then read every file listed under always_load:
static/core/stance.md— what the data-availability package is, the default stance, and the source hierarchy.static/core/chinese-mode.md— how to operate when the user writes in Chinese (accept Chinese, draft English, convert terms precisely).static/core/workflow.md— the eight-step workflow and the output format.
2. No content axis — confirm journal and language inline
Unlike nature-writing or nature-figure, nature-data has no fragment axis. Its variation is handled at runtime, not by loading different content bodies:
- journal/article type — if journal-specific instructions conflict with this skill, follow the journal.
- access route — each dataset is classified into one route (public repository, controlled access, within paper, reused public, third-party restricted, justified request, or not applicable).
- user language — if the user writes Chinese, follow
core/chinese-mode.mdand add the 中文核对 block.
3. Run the workflow
Follow the eight-step workflow in core/workflow.md: identify the journal, inventory every supporting dataset, classify each into one access route, choose repository and identifier strategy before drafting, draft the statement with explicit dataset-to-location mapping, add formal dataset citations, run the FAIR/metadata audit, and return ready-to-paste text plus unresolved fields.
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.
- agents/openai.yaml 270 B
- manifest.yaml 1.7 KB
- README_EN.md 2.1 KB
- README.md 1.9 KB
- references/chinese-author-alignment.md 4.9 KB
- references/fair-metadata-checklist.md 4.0 KB
- references/policy-principles.md 5.2 KB
- references/repository-and-identifiers.md 4.3 KB
- references/source-basis.md 5.3 KB
- references/statement-patterns.md 7.0 KB
- static/core/chinese-mode.md 1.2 KB
- static/core/stance.md 1.9 KB
- static/core/workflow.md 1.5 KB
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 · 63 lines · 173 tokens per session scan A 06e10a29462e
nature-data is a skill published in the GitHub repository hamzabellouch/agent-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 173 tokens to every session and 967 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to nature-data, differing in 16 lines, and is treated as a copy.
Other skills, from other repositories
nsfc-budget
A tool that creates an editable LaTeX budget justification and renders it as a PDF for an NSFC research-funding application. NSFC is China’s National Natural Science Foundation, and a budget justification explains why proposed costs are needed.
nsfc-ref-alignment
A read-only checker for references in NSFC LaTeX proposals. It compares citations with the bibliography and flags missing entries, field errors, and possible mismatches between claims and papers.
nature-data
Prepare, audit, or revise Nature-ready Data Availability statements, data repository plans, dataset citations, and FAIR metadata checklists for manuscripts. Use when the user asks about Nature data availability, research data sharing, repository selection, accession numbers, restricted or sensitive data, source data…
publication-chart-skill
This skill should be used when the user asks for a publication-quality scientific figure or table, wants help choosing the right chart for results, needs a paper-ready pubfig or pubtab workflow, wants a figure + companion table for a results section, wants an Excel sheet turned into publication-ready LaTeX, or wants…
semantic-scholar-deep
Deep research over the Semantic Scholar Graph API. Covers endpoints missing from allenai's lookup skill — paper references (backward citations), recommendations, batch paper lookup (up to 500 IDs), snippet search, and multi-hop citation graph traversal (BFS forward/backward). Use when the user asks to build a citation…
thesis-control
Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and human gates.