Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add AlterLab-IEU/AlterLab-Academic-Skills --skill alterlab-clinical-reportsgit clone --depth 1 https://github.com/AlterLab-IEU/AlterLab-Academic-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alterlab-ieu/alterlab-academic-skills/alterlab-clinical-reports)<a href="https://agentmods.dev/skills/alterlab-ieu/alterlab-academic-skills/alterlab-clinical-reports"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab-academic-skills/alterlab-clinical-reports/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alterlab-ieu/alterlab-academic-skills/alterlab-clinical-reports"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab-academic-skills/alterlab-clinical-reports.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00133 | $0.02643 |
| Opus 5.5 | $0.00053 | $0.01057 |
| Sonnet 5.5 | $0.00027 | $0.00529 |
| Haiku 4.5 | $0.00013 | $0.00264 |
Grade A, and why
alterlab-clinical-reports scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clinical Report Writing
Overview
Document medical information with precision, accuracy, and regulatory compliance. This skill covers four report families: case reports for journal publication, diagnostic reports for clinical practice (radiology, pathology, lab), clinical trial reports for regulatory submission (SAE, CSR), and patient documentation for medical records (SOAP, H&P, discharge).
Clinical reports have to be accurate, complete, objective, and compliant with the applicable regulations (HIPAA, FDA, ICH-GCP), because they feed patient care, regulatory decisions, and the published record. Use only clinical data the user provides — never invent findings, lab values, dates, or citations to fill a template — and mark anything unknown as a placeholder for the clinician to complete. Drafts are for review and sign-off by the responsible clinician or investigator.
When to Use This Skill
Use when:
- Writing a clinical case report for journal submission (CARE guidelines)
- Creating a diagnostic report (radiology, pathology, laboratory)
- Documenting clinical trial data, SAE narratives, or a CSR (ICH-E3)
- Writing SOAP notes, H&P, discharge summaries, or consult notes
- Ensuring HIPAA compliance and proper de-identification
- Validating clinical documentation for completeness and accuracy
Does NOT Trigger
| Scenario | Use Instead |
|---|---|
| Group-level cohort analysis or GRADE-graded treatment recommendations | alterlab-clinical-decision |
| A forward-looking care plan with SMART goals for one patient | alterlab-treatment-plans |
| Designing CRFs/REDCap instruments or mapping trial data to CDISC SDTM | alterlab-redcap-cdisc |
| An IMRaD research manuscript (e.g. an RCT results paper) rather than a case report or CSR | alterlab-scientific-writing |
| IRB applications and informed-consent forms | alterlab-research-ethics |
Core Workflow
- Pick the report family and load its detailed reference (see index below).
- Draft from the template in
assets/for that report type. - Apply regulatory controls — de-identify, document consent, meet timelines.
- Validate with the matching
scripts/validator before sign-out. - Final QA against the checklist at the end of this file.
What ships with it
34 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/case_report_template.md 9.5 KB
- assets/clinical_trial_csr_template.md 9.1 KB
- assets/clinical_trial_sae_template.md 10 KB
- assets/consult_note_template.md 7.2 KB
- assets/discharge_summary_template.md 12 KB
- assets/hipaa_compliance_checklist.md 12 KB
- assets/history_physical_template.md 9.0 KB
- assets/lab_report_template.md 8.3 KB
- assets/pathology_report_template.md 6.5 KB
- assets/quality_checklist.md 9.7 KB
- assets/radiology_report_template.md 7.8 KB
- assets/soap_note_template.md 7.1 KB
- evals/evals.json 5.7 KB
- references/care_report_sections.md 5.6 KB
- references/case_report_guidelines.md 18 KB
- references/clinical_trial_report_structures.md 5.7 KB
- references/clinical_trial_reporting.md 22 KB
- references/data_presentation.md 21 KB
- references/diagnostic_report_templates.md 6.2 KB
- references/diagnostic_reports_standards.md 18 KB
- references/medical_terminology.md 15 KB
- references/patient_documentation.md 21 KB
- references/patient_record_formats.md 6.2 KB
- references/peer_review_standards.md 15 KB
- references/README.md 2.1 KB
- references/regulatory_compliance.md 17 KB
- scripts/check_deidentification.py 11 KB runs code
- scripts/compliance_checker.py 2.1 KB runs code
- scripts/extract_clinical_data.py 2.6 KB runs code
- scripts/format_adverse_events.py 3.0 KB runs code
- scripts/generate_report_template.py 4.6 KB runs code
- scripts/terminology_validator.py 4.0 KB runs code
- scripts/validate_case_report.py 11 KB runs code
- scripts/validate_trial_report.py 2.8 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +21 lines ffb180f87f2f
- 1mo ago First seen · 187 lines · 133 tokens per session scan A 7c71e38b9327
alterlab-clinical-reports is a skill published in the GitHub repository AlterLab-IEU/AlterLab-Academic-Skills (78 stars, last pushed 3d ago), licensed MIT. It adds 133 tokens to every session and 2,643 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
thesis-consistency-audit
A consistency audit for quantitative master’s and doctoral theses in management, finance, or strategy. It checks whether numbers, tables, analyses, and claims agree, and can inspect hidden author information in office documents.
aeja-tables-figures
Use when building or revising the exhibits of an American Economic Journal: Applied Economics (AEJ: Applied) manuscript so the main causal result is legible in one table or figure and respects AEA house presentation norms. Formats exhibits; it does not establish the result (aeja-identification / aeja-robustness) or…
aejpol-replication-package
Use when assembling the data and code deposit for an AEJ: Economic Policy manuscript to satisfy the AEA Data and Code Availability Policy and the AEA Data Editor's pre-publication reproducibility check. Builds the openICPSR deposit, README, and restricted-data access paths; it does not run the analysis or write the…
aejmac-tables-figures
Use when building or revising exhibits for an American Economic Journal: Macroeconomics (AEJ: Macro) manuscript — impulse-response figures, fan charts, model-fit overlays, and regression/moment tables — to AEA house standards and macro conventions. Formatting and clarity; it does not generate the underlying estimates.
aaai-artifact-evaluation
Use when packaging AAAI code, data, multimedia appendices, technical appendices, reproducibility evidence, and post-acceptance artifact releases without violating double-blind or immutable-supplement rules.
r-spss-syntax-architect
A guide for turning research hypotheses into repeatable R or SPSS code for statistical analysis. It covers panel data, where the same companies or other units are observed over time, as well as interaction effects, curves, and mediation.