data-management-plan-creator
Automatically generate NIH 2023-compliant Data Management and Sharing Plan (DMSP) drafts following FAIR principles
50
38%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/data-management-plan-creator/SKILL.mdQuality
Discovery
54%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description targets a very specific niche (NIH DMSP generation) with strong domain-specific trigger terms, making it highly distinctive. However, it lacks a 'Use when...' clause and lists only a single action (generate drafts) rather than enumerating specific sub-tasks, which weakens both completeness and specificity.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user needs to create or review a Data Management and Sharing Plan for an NIH grant application or mentions DMSP, data sharing, or FAIR compliance.'
List more specific concrete actions, e.g., 'Generates repository recommendations, outlines data types and standards, addresses access and preservation timelines, and produces NIH 2023-compliant DMSP drafts following FAIR principles.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (NIH DMSP) and one action (generate drafts), and mentions compliance standards (NIH 2023, FAIR principles), but does not list multiple concrete actions like filling specific sections, handling repository selection, or formatting citations. | 2 / 3 |
Completeness | It answers 'what' (generate NIH DMSP drafts) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'when' is entirely absent, warranting a 1. | 1 / 3 |
Trigger Term Quality | Contains strong natural trigger terms a researcher would use: 'NIH', 'Data Management and Sharing Plan', 'DMSP', 'FAIR principles', '2023-compliant'. These are highly specific domain terms users in this space would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | This is a very specific niche — NIH 2023-compliant DMSP generation following FAIR principles. It is highly unlikely to conflict with other skills given the narrow domain focus and specific regulatory context. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a README for a software project than an actionable skill for Claude. It is bloated with boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status) that consume tokens without adding instructional value. The core task—generating NIH-compliant DMSPs—lacks a concrete workflow, example output, or template that Claude could actually use to produce a plan.
Suggestions
Remove boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status) that don't help Claude perform the task—these waste significant token budget.
Add a concrete example of a generated DMSP output (even a partial one) so Claude knows exactly what format and language to produce, rather than just listing bullet points of what it should contain.
Define a clear step-by-step workflow: gather project details → generate draft using template → validate against NIH 6 required elements checklist → iterate on gaps → output final document.
Move the detailed FAIR principles explanation and NIH elements descriptions to a reference file, keeping only a brief checklist in the main skill file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely verbose with many sections that add no value for Claude: Risk Assessment tables, Security Checklists, Evaluation Criteria, Lifecycle Status, and extensive FAIR principles explanations that Claude already knows. The Overview section restates the title. Much of this is boilerplate padding rather than actionable instruction. | 1 / 3 |
Actionability | The CLI commands and Python module usage are concrete and copy-paste ready, which is good. However, the skill never shows what the actual generated output looks like (the 'Example Output' section just lists bullet points describing what it contains rather than showing a concrete example). There's no actual template or generation logic shown—it assumes scripts/main.py exists but doesn't show how to create it. | 2 / 3 |
Workflow Clarity | There is no clear multi-step workflow for generating a DMSP. The skill presents CLI usage and module usage but doesn't sequence the actual process: gathering inputs, generating the draft, reviewing/validating the output, iterating on sections. There are no validation checkpoints for ensuring NIH compliance of the generated document. | 1 / 3 |
Progressive Disclosure | There are references to external files (references/nih_dmp_template.md, requirements.txt) which is good, but the main file itself is a monolithic wall containing sections that should be separated (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status are all inline). The FAIR principles and NIH elements sections could be referenced rather than fully enumerated. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
858c2e5
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.