More screenshots
Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
DeepSeek
Muse+22 moreClaude CodeCursorCodex CLIDeepSeekMuse
Dots
Manus
Grok
Grok Bot+18 agentsResearch Data Sharing Evidence Packet
Organize supplied research data-sharing records into a traceable evidence packet with Claude.
$1
Research Data Sharing Evidence Packet
Example session with this skill installed
Organize a packet for my study. I have a journal policy requiring a DOI, a consent form that only allows sharing with researchers, an MRI inventory, and a draft statement saying all data is public.
- Read your context and instructions
- Compiled the research data sharing
1. Packet decision
Decision: PARTIAL DATA-SHARING EVIDENCE PACKET AVAILABLE
The records support a controlled-access handoff, but the claim that data is public is unsupported by the consent restriction.
6. Availability-statement claim check
Status: UNSUPPORTED. Claim conflicts with R2.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Manuscript submissions often stall when researchers cannot reconcile conflicting data-sharing requirements from journals, funders, and ethics boards. Scattered records like consent forms, repository drafts, and code scripts make it difficult to prove what can be shared and what must be restricted.
What it does
- Builds a traceable source register from consent forms, ethics approvals, and data inventories.
- Classifies research assets into public, controlled-access, or restricted categories.
- Flags discrepancies between draft availability statements and actual evidence.
- Generates a data and code deposit ledger to track identifiers, licenses, and versions.
- Surfaces gaps in code documentation, such as missing environment lockfiles or local file paths.
Why this beats prompting it yourself
This skill enforces a rigid structure that prevents the LLM from hallucinating compliance or making dangerous legal interpretations. It maintains a strict boundary between data organization and data transformation, ensuring you never accidentally publish sensitive participant information.
Use cases
- Preparing a Data Availability Statement for a high-impact journal submission.
- Organizing evidence for a funder's end-of-grant data-sharing report.
- Drafting a controlled-access procedure for sensitive clinical or ecological data.
- Auditing a research code package for portability and environment documentation.
Known limitations
Does not perform data anonymization, validate live DOIs, or interpret legal contracts. Requires all records to be provided as text or file inputs.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Cannot access live databases or repositories. Does not perform anonymization or legal interpretation. Requires all evidence to be provided as input.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 months ago
Permissions
Permissions are limited to the active local workspace and are used to inspect user-supplied or local workspace files. The skill package does not require bundled credentials, unrestricted external network access, or automatic production changes.