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 agentmods add skills/learningmatter-mit/atomisticskills/general-fair-data-reviewnpx skills add learningmatter-mit/AtomisticSkills --skill general-fair-data-reviewgit clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkillsWrote 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/learningmatter-mit/atomisticskills/general-fair-data-review)<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/general-fair-data-review"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/general-fair-data-review.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.02176 |
| Opus 5 | $0.00022 | $0.01088 |
| Sonnet 5 | $0.00009 | $0.00435 |
| Haiku 4.5 | $0.00004 | $0.00218 |
Grade A, and why
general-fair-data-review 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
General FAIR Data Review
Goal
Assess whether a manuscript submission or standalone code/data repository satisfies the FAIR Guiding Principles (Wilkinson et al., Sci. Data 2016). The output is a structured reviewer report — analogous to a peer-review report — that scores each FAIR sub-principle, identifies gaps, and provides concrete remediation steps the authors can act on before publication.
This skill is complementary to general-peer-review, which focuses on scientific methodology. Run both in sequence for a complete review.
Prerequisites
- A manuscript (PDF or markdown) and/or a link to a code/data repository (GitHub, Zenodo, Figshare, etc.)
- Read access to any supplementary files, Data Availability Statements (DAS), or README files provided by the authors
Instructions
1. Identify Review Scope
Determine what artifacts are under review. Three modes exist:
| Mode | Input | Focus |
|---|---|---|
| Manuscript + data/code | PDF + repo URL | Full FAIR review |
| Manuscript only | DAS quality, metadata richness, identifier presence | |
| Code/data repo only | Repo URL / directory | Repository-level FAIR compliance |
State the mode explicitly at the start of the review report.
2. Read the Manuscript and Data Availability Statement
Load the manuscript. Locate and extract:
- The Data Availability Statement (DAS) — usually a dedicated section near the end.
- Any Code Availability Statement.
- All data/code repository URLs or DOIs mentioned.
If no DAS exists, flag immediately as a Critical Finding (fails F4, A1, R1.1).
3. Inspect the Data/Code Repository
For each repository URL found, check the following. If no repository exists, mark all sub-principles below as Fail.
Repository inspection checklist:
- Does a persistent identifier (DOI, Handle) exist? → F1
- Is metadata present and rich (title, authors, description, keywords, license)? → F2, R1
- Does the metadata explicitly reference the dataset/code identifier? → F3
- Is the repository indexed in a searchable resource (Zenodo, Figshare, OSF, etc.)? → F4
- Can the data/code be accessed via a standard protocol (HTTP/HTTPS, FTP)? → A1
- Is the protocol open and free (no proprietary portal login required)? → A1.1
- If restricted, is there a documented access procedure? → A1.2
- Does metadata remain accessible even if data is removed? → A2
- Are standard, community-recognized formats used (CIF, JSON, CSV, HDF5, not .xlsx or proprietary)? → I1
- Are domain ontologies or controlled vocabularies used for metadata fields? → I2
- Are cross-references to related datasets or publications included? → I3
- Is a clear, machine-readable license present (CC-BY, MIT, Apache 2.0, etc.)? → R1.1
- Is provenance documented (how data was generated, software versions, parameters)? → R1.2
- Do files conform to domain community standards (e.g., CIF for crystal structures, SMILES for molecules, HDF5 for trajectories)? → R1.3
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 First seen · 239 lines · 44 tokens per session scan A 015cd9f3620d
general-fair-data-review is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (158 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 2,176 once invoked, about $0.0002 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
domain-setup
Configure your industry domain, country, and regulatory context — agents automatically adapt to your business.
tooluniverse-drug-research
Comprehensive drug profiling — mechanism, primary/secondary targets, drug interactions, clinical-trial status, adverse events (FAERS), pharmacogenomics, and approval history. Use for full drug investigation reports, 'tell me about drug X' queries, and assembling drug profiles for clinicians, researchers, or regulatory…
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
catalyst-center-readonly
Query Cisco Catalyst Center read-only — device inventory, site hierarchy, wireless, assurance health, compliance, software images, events. All 514 read-only API operations reachable through 8 grouped dispatchers. Use when asked what Catalyst Center manages, where a device sits, what its health or compliance state is…
build-audit-logs
Build or review audit trails in TypeScript/JavaScript apps using evlog (pipelines, typed actions, denials, retention, compliance-style reviews). For application code, not for extending the evlog package.