drugclaw/scientific-workflow-tools
skills/science/scientific-workflow-tools/SKILL.md
Research-method workflow guide for hypothesis framing, peer-review style critique, reproducibility planning, study-design checks, and scientific-writing structure. Use when the user asks for manuscript critique, research-gap framing, hypothesis generation, reproducibility checklists, or study-planning support that should stay on the research side rather than patient-care decisions.
$ install --global
skillsauthnpx skillsauth add drugclaw/drugclaw scientific-workflow-toolsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 4, 2026, 6:26 PM8.7s2 files scanned
SKILL.md
- name:
- scientific-workflow-tools
- description:
- Research-method workflow guide for hypothesis framing, peer-review style critique, reproducibility planning, study-design checks, and scientific-writing structure. Use when the user asks for manuscript critique, research-gap framing, hypothesis generation, reproducibility checklists, or study-planning support that should stay on the research side rather than patient-care decisions.
- source:
- drugclaw
- updated_at:
- 2026-03-11
Scientific Workflow Tools
Use this skill when the user needs higher-level research method support rather than raw database lookup or computation.
Typical triggers:
- generate or compare mechanistic hypotheses from observations
- review a manuscript draft for rigor, missing controls, or overstated claims
- build a reproducibility checklist before submission or release
- structure a scientific report, review, or response-to-reviewers plan
- identify missing controls, statistical gaps, or reporting-standard issues
Bundled Asset
templates/reproducibility_checklist.py
Preferred Workflow
- Restate the research question, claim, or draft under review.
- Separate what is observed from what is inferred.
- Enumerate methodological risks before proposing fixes.
- Use the checklist template to create a durable artifact for reporting or project tracking.
- Keep outputs explicitly on the research side. Do not cross into patient-level diagnosis or treatment planning.
Reproducibility Checklist
python3 templates/reproducibility_checklist.py \
--profile omics \
--output research/omics_checklist.md \
--summary research/omics_checklist.json
Supported baseline profiles:
generalomicsmlclinical-research
Use the generated checklist as a starting artifact, then tailor it to the exact study.
Working Rules
- Hypotheses should be testable and distinguish observation from mechanism.
- Peer-review style critique should prioritize reproducibility, controls, statistics, and claim scope.
- Scientific writing support should strengthen structure and rigor, not fabricate citations or results.
- Reporting-guideline and checklist outputs are planning artifacts, not proof that the study is compliant.
Related Skills
For literature search outputs and evidence tables, activate literature-review-tools.
For clinical-study design and reporting-guideline selection, activate clinical-research-tools.
For numerical statistical execution, activate stat-modeling-tools or survival-analysis-tools.
For experiment suggestion or bounded closed-loop optimization, activate bayesian-optimization-tools.
For figure generation, activate scientific-visualization-tools.
For bioinformatics, chemistry, or docking execution, activate the corresponding domain skill instead of keeping the task abstract.
Related Skills
drugclaw/survival-analysis-tools
tools
VerifiedTrustedCommunity
Survival and time-to-event workflow guide for Kaplan-Meier summaries, log-rank tests, and Cox proportional hazards models with reproducible outputs. Use when the user asks for time-to-event analysis, censored data summaries, hazard ratios, or survival-group comparison for research datasets.
52SKILL.mdUpdated Apr 4, 2026
drugclaw/stat-modeling-tools
tools
VerifiedTrustedCommunity
Statistical modeling workflow guide for hypothesis tests, effect-size reporting, statsmodels regression, diagnostics, and structured result export. Use when the user asks for statistical test selection, OLS or logistic regression, coefficient tables, inference, or reproducible statistical summaries for scientific datasets.
52SKILL.mdUpdated Apr 4, 2026
drugclaw/scientific-visualization-tools
tools
VerifiedTrustedCommunity
Scientific visualization workflow guide for publication-ready static figures with seaborn or matplotlib and interactive figures with Plotly. Use when the user asks for scientific plots, cohort or assay figures, publication graphics, dashboards, or reusable plotting scripts for research datasets.
52SKILL.mdUpdated Apr 4, 2026
drugclaw/patent-landscape-tools
tools
VerifiedTrustedCommunity
Drug-patent landscape workflow guide for searching US patents via the PatentsView API, classifying pharmaceutical claim types (NCE, formulation, method-of-use, polymorph, combination, biologic, process), grouping by patent family and assignee, estimating expiry timelines, and cross-referencing the FDA Orange Book for marketed-drug exclusivity windows. Use when the user asks about patent coverage, IP white-space, patent cliffs, or competitive filing activity around a drug, target, or compound class without asking for legal counsel.
52SKILL.mdUpdated Apr 4, 2026