Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Pnas Data

ASecurity

Use to build PNAS's Data Availability Statement and deposition plan — mandatory deposition of data in an approved repository at submission, accession numbers/DOIs, public + archived code, and materials sharing. "Available on request" is not sufficient for primary data.

1,052 stars
0 votes
0 copies
0 views
Added 6/6/2026
ai-agentsgoexpressgit

Works with

cli

Security Analysis

A100/100

Scanned 6/6/2026

Install to Claude Code

$npx -y skills add brycewang-stanford/Awesome-Journal-Skills --skill pnas-data --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pnas Data?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Pnas Data
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-pnas-data/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-pnas-data)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: pnas-data
description: Use to build PNAS's Data Availability Statement and deposition plan — mandatory deposition of data in an approved repository at submission, accession numbers/DOIs, public + archived code, and materials sharing. "Available on request" is not sufficient for primary data.
---

# Data & Code Availability (pnas-data)

## When to trigger

- There is no **Data Availability Statement**, or it says "available on request".
- Sequences/structures/datasets are not deposited or have no accession numbers.
- Custom analysis code is not in a public, archived repository.
- Unique reagents/strains/cell lines have no sharing plan.

## PNAS's standard (the bar)

PNAS requires a **Data Availability Statement** in every research article, and that the **data and materials needed to support the conclusions be deposited and available at the time of submission/publication**. For data types with an established public repository, **deposition is required**, and the **accession numbers/DOIs go in the Data Availability Statement**. **"Available upon request" is not sufficient for the primary data** underlying the figures and conclusions.

## Deposit in approved repositories (with accessions)

| Data type                          | Deposit in (examples)                      |
|------------------------------------|--------------------------------------------|
| Nucleotide / genome sequences      | GenBank / ENA / DDBJ                        |
| High-throughput sequencing         | GEO / SRA / ArrayExpress                    |
| Protein/macromolecular structures  | PDB; maps → EMDB                            |
| Proteomics                         | PRIDE / ProteomeXchange                     |
| Crystallographic data              | CCDC / CSD                                  |
| Generic datasets                   | Dryad / Zenodo / Figshare / OSF            |
| Code                               | GitHub/GitLab **+ archived** to Zenodo (DOI) |

- Obtain **accession numbers / DOIs before/at submission**; cite them in the Data Availability Statement and Materials and Methods.
- Code that produces the results must be **public and archived** (a versioned release with a citable DOI; a bare GitHub link is not durable).

## Data Availability Statement (template)

> *All study data are included in the article and/or SI Appendix. [Sequencing data have been deposited in GEO (accession GSEXXXXXX).] [Structures have been deposited in the PDB (XXXX).] [Analysis code has been deposited in Zenodo (DOI: 10.5281/zenodo.XXXXXXX).] [Previously published data used in this work are available at …] [Restricted data (e.g., human-subjects data) are available under … from … subject to …]*

Avoid bare "data available on request" for primary data; restricted human/clinical data must state the access procedure and the controlling body.

## Where the statement and the data live

- The **Data Availability Statement** is a required element of the article (near the end, before/with the references — confirm placement in current guidelines).
- Datasets too large for a figure but central to the conclusions can go in **SI Appendix** or, if very large, in an external repository cited by accession/DOI — not "available on request."
- Reference the deposited data in **both** the Data Availability Statement **and** the Materials and Methods, so a reader following the methods can reach the data.

## Materials & reagents

- Unique materials (plasmids, cell lines, strains, antibodies) should be available, e.g., via Addgene/repositories or under an MTA; state how.
- Identify key reagents with RRIDs where available.

## Ethics & compliance (as applicable)

- Human-subjects: IRB/ethics approval + informed consent statement.
- Animal work: IACUC/animal-ethics approval and guideline compliance.
- Field/biodiversity: permits and the Nagoya Protocol where relevant.
- Dual-use / biosafety: flag if applicable.

## Output format

```
【Data deposited】 type → repository → accession/DOI (list each) | gaps
【Code public + archived DOI】 yes/no (link + DOI)
【Data Availability Statement】 drafted? compliant (no "on request" for primary data)?
【Materials sharing】 plan for unique reagents (Addgene/MTA)
【Ethics approvals】 IRB / IACUC / permits present where needed?
【Next】 pnas-significance
```

## Anti-patterns

- **Do not** write "data available on request" for the primary data behind the figures.
- **Do not** link only to a personal/lab website (not durable) — use an archival repository with a DOI.
- **Do not** forget to make code public and versioned; reviewers may try to run it.
- **Do not** submit without accession numbers in hand for deposited data.

Attribution

brycewang-stanfordbrycewang-stanford
View sourceMore from brycewang-stanford →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693161 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →