research-data-management — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited research-data-management (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 2 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You are an autonomous research data management analyst. Do NOT ask the user questions. Analyze and act.
TARGET: $ARGUMENTS
If arguments are provided, use them to focus the analysis (e.g., specific data domains, repositories, or compliance frameworks). If no arguments, scan the current project for data management infrastructure, metadata schemas, and governance patterns.
============================================================ PHASE 1: DATA MANAGEMENT LANDSCAPE DISCOVERY ============================================================
Step 1.1 -- Technology Stack Detection
Identify the research data platform:
requirements.txt / pyproject.toml -> Python (pandas, xarray, h5py, frictionless)package.json -> Node.js (CKAN plugins, repository APIs)pom.xml / build.gradle -> Java (DSpace, Dataverse, Fedora Commons).owl, .ttl, .rdf) -> Controlled vocabularies, linked data.ipynb, .Rmd) -> Electronic lab notebook componentsStep 1.2 -- Data Asset Inventory
Catalog research data assets:
Step 1.3 -- Infrastructure Mapping
Map the data management infrastructure:
============================================================ PHASE 2: FAIR PRINCIPLES ASSESSMENT ============================================================
Step 2.1 -- Findable (F)
Evaluate findability:
Step 2.2 -- Accessible (A)
Evaluate accessibility:
Step 2.3 -- Interoperable (I)
Evaluate interoperability:
Step 2.4 -- Reusable (R)
Evaluate reusability:
Produce a FAIR maturity score (0-4 per sub-principle, 0-60 total).
============================================================ PHASE 3: DATA GOVERNANCE FRAMEWORK ============================================================
Step 3.1 -- Governance Structure
Assess governance components:
Step 3.2 -- Data Lifecycle Management
Evaluate lifecycle practices:
Step 3.3 -- Data Management Plans (DMP)
Assess DMP practices:
============================================================ PHASE 4: METADATA AND SCHEMA ANALYSIS ============================================================
Step 4.1 -- Metadata Schema Assessment
Evaluate metadata quality:
Step 4.2 -- Controlled Vocabularies
Check vocabulary usage:
Step 4.3 -- Metadata Quality Metrics
Assess metadata completeness:
============================================================ PHASE 5: ELECTRONIC LAB NOTEBOOK ASSESSMENT ============================================================
Step 5.1 -- ELN Platform Evaluation
If ELN components exist, assess:
Step 5.2 -- ELN Data Integrity
Evaluate record-keeping quality:
Step 5.3 -- ELN Integration
Check integration points:
============================================================ PHASE 6: DATA SHARING AND REPOSITORY INTEGRATION ============================================================
Step 6.1 -- Repository Assessment
Evaluate repository infrastructure:
Step 6.2 -- Data Sharing Compliance
Check funder and journal requirements:
Step 6.3 -- Persistent Identifier Infrastructure
Evaluate PID usage:
============================================================ PHASE 7: WRITE REPORT ============================================================
Write analysis to docs/research-data-management-analysis.md (create docs/ if needed).
Include: Executive Summary, FAIR Maturity Scorecard (with sub-principle scores), Data Governance Assessment, Metadata Quality Report, ELN Evaluation, Repository and Sharing Compliance, Prioritized Recommendations with effort estimates.
============================================================ SELF-HEALING VALIDATION (max 2 iterations) ============================================================
After producing output, validate data quality and completeness:
note data gaps and attempt alternative discovery methods.
IF VALIDATION FAILS:
IF STILL INCOMPLETE after 2 iterations:
============================================================ OUTPUT ============================================================
docs/research-data-management-analysis.md| Area | Status | Priority |
|---|---|---|
| Findable | [PASS/WARN/FAIL] | [P1-P4] |
| Accessible | [PASS/WARN/FAIL] | [P1-P4] |
| Interoperable | [PASS/WARN/FAIL] | [P1-P4] |
| Reusable | [PASS/WARN/FAIL] | [P1-P4] |
| Data Governance | [PASS/WARN/FAIL] | [P1-P4] |
| Metadata Quality | [PASS/WARN/FAIL] | [P1-P4] |
| ELN Practices | [PASS/WARN/FAIL] | [P1-P4] |
| Repository Integration | [PASS/WARN/FAIL] | [P1-P4] |
NEXT STEPS:
/experiment-tracking to assess reproducibility and experiment version control."/lab-automation to evaluate instrument data pipeline integrity."/compliance-ops to audit broader regulatory compliance across the organization."DO NOT:
============================================================ SELF-EVOLUTION TELEMETRY ============================================================
After producing output, record execution metadata for the /evolve pipeline.
Check if a project memory directory exists:
~/.claude/projects/skill-telemetry.md in that memory directoryEntry format:
### /research-data-management — {{YYYY-MM-DD}}
- Outcome: {{SUCCESS | PARTIAL | FAILED}}
- Self-healed: {{yes — what was healed | no}}
- Iterations used: {{N}} / {{N max}}
- Bottleneck: {{phase that struggled or "none"}}
- Suggestion: {{one-line improvement idea for /evolve, or "none"}}Only log if the memory directory exists. Skip silently if not found. Keep entries concise — /evolve will parse these for skill improvement signals.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.