Claude Scientific Writer is an AI-assisted research and writing tool that searches literature and produces documents such as scientific papers, reports, posters, grant proposals, and reviews with citations. Researchers and technical writers can use it as a Claude Code plugin, Python package, or command-line tool, with the catalogue entries defining agent workflows for it.
Borrowing it
Nothing to install: this file belongs to K-Dense-AI/claude-scientific-writer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/K-Dense-AI/claude-scientific-writer/main/.claude/skills/clinical-reports/SKILL.mdgit clone --depth 1 https://github.com/K-Dense-AI/claude-scientific-writerWrote 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/k-dense-ai/claude-scientific-writer/clinical-reports)<a href="https://agentmods.dev/skills/k-dense-ai/claude-scientific-writer/clinical-reports"><img src="https://agentmods.dev/badge/skills/k-dense-ai/claude-scientific-writer/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/k-dense-ai/claude-scientific-writer/clinical-reports"><img src="https://agentmods.dev/badge/skills/k-dense-ai/claude-scientific-writer/clinical-reports.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00055 | $0.02915 |
| Opus 5 | $0.00028 | $0.01458 |
| Sonnet 5 | $0.00011 | $0.00583 |
| Haiku 4.5 | $0.00006 | $0.00292 |
Grade A, and why
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 12d 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.
This is a copy
100% identical to clinical-reports — 19 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clinical Reports
Purpose
Prepare draft reporting structures, aggregate tables, and review manifests from verified authorized facts. Route each artifact to the correct reporting guidance, preserve provenance, and stop when source support or qualified review is missing.
This skill does not establish legal, regulatory, ethical, journal, accreditation, or institutional compliance. Its scripts check structure and internal consistency only.
Non-Negotiable Boundary
Never:
- diagnose, recommend treatment, choose or change dosing, triage, or provide return precautions;
- interpret images, specimens, raw laboratory results, symptoms, or other clinical observations;
- invent, infer, normalize, “complete,” or silently reconcile observations, results, dates, units, denominators, causality, expectedness, seriousness, outcomes, or conclusions;
- create an individual case safety report from patient-level narrative or decide reportability;
- sign, attest, approve, file, transmit, submit, amend a source record, or act as a licensed clinician, pathologist, radiologist, laboratorian, safety physician, statistician, privacy officer, attorney, or regulatory professional;
- use real PHI in examples, assets, tests, prompts, logs, or external services;
- call an external LLM, image service, API, or another skill.
All generated artifacts must remain visibly marked:
DRAFT — NOT FOR CLINICAL USE, SIGNATURE, FILING, OR SUBMISSION. Populate only from verified authorized source records. Qualified review and sign-off are required.
If the request crosses a boundary, stop the unsafe portion. Offer a blank structured template, a source-fact manifest, or a deterministic structural check. Direct clinical or regulatory decisions to the responsible qualified professional.
Input Gate
Proceed only when all conditions are true:
- Purpose is explicit: publication draft, diagnostic-report scaffold, trial-results manuscript, protocol reporting review, CSR draft, aggregate safety table, or aggregate research summary.
- Data class is allowed:
synthetic,deidentified, oraggregate. - Authority is documented: the requester is authorized to use the records for the stated purpose.
- Local-only handling is feasible: no upload, remote API, telemetry, or credential is needed.
- Minimum necessary is defined: exclude fields not needed for the artifact.
- Provenance exists: every populated field or claim maps to one or more verified source-fact IDs.
- Review owner is identified: qualified clinical, statistical, safety, privacy, legal, journal, and/or regulatory review as applicable.
What ships with it
35 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/adverse_event_aggregate_input_template.csv 120 B
- assets/case_report_template.json 2.1 KB
- assets/clinical_trial_csr_template.json 2.6 KB
- assets/clinical_trial_results_template.json 3.8 KB
- assets/clinical_trial_safety_aggregate_template.json 1.4 KB
- assets/consistency_manifest_template.json 531 B
- assets/deidentification_process_checklist.json 2.1 KB
- assets/lab_report_template.json 1.7 KB
- assets/pathology_report_template.json 1.7 KB
- assets/provenance_manifest_template.json 560 B
- assets/quality_review_checklist.json 1.7 KB
- assets/radiology_report_template.json 1.5 KB
- assets/research_summary_template.json 1.6 KB
- assets/terminology_manifest_template.json 426 B
- assets/trial_protocol_reporting_checklist.json 4.2 KB
- references/case_report_guidelines.md 3.3 KB
- references/clinical_trial_reporting.md 5.0 KB
- references/data_presentation.md 3.6 KB
- references/diagnostic_reports_standards.md 4.0 KB
- references/medical_terminology.md 3.5 KB
- references/privacy_and_deidentification.md 4.5 KB
- references/professional_review.md 3.9 KB
- references/README.md 2.1 KB
- references/report_type_routing.md 4.2 KB
- references/safety_reporting.md 5.9 KB
- references/sources.md 8.4 KB
- scripts/_common.py 9.2 KB runs code
- scripts/check_deidentification.py 11 KB runs code
- scripts/consistency_checker.py 13 KB runs code
- scripts/format_adverse_events.py 16 KB runs code
- scripts/generate_report_template.py 3.9 KB runs code
- scripts/provenance_validator.py 9.1 KB runs code
- scripts/terminology_validator.py 10 KB runs code
- scripts/validate_case_report.py 9.4 KB runs code
- scripts/validate_trial_report.py 20 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.
- 12d ago First seen · 249 lines · 55 tokens per session scan A f1da8ce1a00f
clinical-reports is a skill published in the GitHub repository K-Dense-AI/claude-scientific-writer (2,327 stars, last pushed 23d ago), licensed MIT. It adds 55 tokens to every session and 2,915 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to clinical-reports, differing in 19 lines, and is treated as a copy.
Other skills, from other repositories
health-nutrition-expert
Apply cutting-edge 2025 nutrition science on longevity, metabolic health, gut microbiome, and evidence-based dietary patterns for optimal vitality and disease prevention. Use when planning a diet, evaluating a nutrition claim, or applying evidence-based guidance on longevity, metabolic, and gut health.
tabpfn-regress
Run a TabPFN regression baseline, generate the first submission, then optimize with GBT ensembles and regression-specific post-processing (clipping, target transforms, rank blending). Use after tabpfn-explore has prepared the data and CV folds.
tabpfn-explore
EDA, data profiling, adversarial validation, preprocessing checks, CV scheme setup, and API budget verification for tabular Kaggle competitions. Run at the start of every new competition before any modeling.
drug-discovery
Drug discovery: ChEMBL search, drug-likeness, interactions.
aaai-experiments
Use when designing or auditing AAAI experiments for the broad-AI program committee, including baselines, ablations, statistical significance, robustness, human evaluation, AI-for-Social-Impact and alignment/safety evidence, compute and cost reporting, and reproducibility-checklist alignment for Phase-1 survival.
acl-experiments
Use when designing or auditing experiments for an ACL paper, covering tuned LLM baselines, multi-dataset and multilingual evaluation, statistical significance and variance, human evaluation with agreement reporting, contamination and prompt-sensitivity controls, ablations, and error-analysis expectations in NLP…