AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Science Data Code

skill-shikaijieskj-science-skills-science-data-code · by shikaijieskj

Prepare, audit, or revise Science/AAAS-family data availability, code availability, materials availability, repository plans, accession numbers, source-data mapping, FAIR metadata, and reproducibility statements. Use when the user asks about Science data/code policies, Data and materials availability, code repository wording, Zenodo/GitHub/OSF/Dryad/figshare/GEO/SRA/PRIDE accession plans, or Chin…

No reviews yet
0 installs
14 views
0.0% view→install

Install

$ agentstack add skill-shikaijieskj-science-skills-science-data-code

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-shikaijieskj-science-skills-science-data-code)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Science Data Code? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Science Data and Code

Use this skill to connect the manuscript's claims to inspectable data, code, materials, and metadata. Treat availability as part of the evidence chain.

Default stance

  • Do not invent DOIs, accession numbers, repository records, licenses, embargoes, ethics

approvals, access committees, or code status.

  • Prefer public, stable, discipline-appropriate repositories.
  • Separate data, code, materials, protocols, models, and third-party resources.
  • Flag available upon reasonable request as weak unless there is a clear legal, ethical,

commercial, privacy, or third-party restriction.

  • Verify current target-journal policy before final submission wording.

Open extra files

| File | Open when | |---|---| | [references/availability-patterns.md](references/availability-patterns.md) | Need ready-to-adapt data/code/materials statement patterns | | [references/repository-checklist.md](references/repository-checklist.md) | Need repository, identifier, license, metadata, or FAIR checks | | [references/source-basis.md](references/source-basis.md) | Need source hierarchy or policy-vs-advice boundaries |

Workflow

  1. Identify target journal and article type.
  2. Inventory every asset needed to support the main and supplementary claims:

raw data, processed data, figure source data, code, scripts, models, protocols, materials, third-party datasets, and restricted data.

  1. Map each asset to one access route:

public repository, controlled access, within paper/supplement, reused public source, third-party restricted, available on justified request, or not yet provided.

  1. Choose a repository and identifier strategy before drafting.
  2. Draft data/code/materials availability text with asset-to-location mapping.
  3. Add missing-information flags.
  4. Run the FAIR/reproducibility checklist.

Output format

Data and code availability
[ready-to-paste statement]

Asset map
| Asset | Supports claim/figure | Location | Identifier | Access conditions | Missing info |

Repository actions
- [specific actions]

Risk flags
- [specific flags or "None"]

For Chinese author notes, provide the submission-ready English statement first, then a short Chinese checklist of author actions.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.