clinical-reports
Generates fail-closed draft JSON templates and runs local deterministic structure and consistency checks for clinical reports: CARE case reports, radiology, pathology and lab scaffolds, CONSORT 2025, SPIRIT 2025, ICH E3 CSRs, aggregate adverse-event tables, provenance manifests, terminology schemas, and de-identification process checklists. Use when drafting a case report for publication from a verified source-fact manifest. Use when checking a trial results manuscript, protocol, or CSR draft against its reporting structure. Use when building an aggregate safety table from synthetic or de-identified data. Use when routing an artifact to the right guideline. Not for diagnosis, treatment advice, individual case safety report creation, or filing and submission.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 132
- Forks
- 16
01 前言 Front Matter
- name
- clinical-reports
- license
- MIT
- metadata
- { "tags": "clinical reports, CONSORT, case reports, clinical trials, medical writing", "version": "2.1", "category": "clinical-and-health", "maintainer": "Kalaris Labs" }
- description
- Generates fail-closed draft JSON templates and runs local deterministic structure and consistency checks for clinical reports: CARE case reports, radiology, pathology and lab scaffolds, CONSORT 2025, SPIRIT 2025, ICH E3 CSRs, aggregate adverse-event tables, provenance manifests, terminology schemas, and de-identification process checklists. Use when drafting a case report for publication from a verified source-fact manifest. Use when checking a trial results manuscript, protocol, or CSR draft against its reporting structure. Use when building an aggregate safety table from synthetic or de-identified data. Use when routing an artifact to the right guideline. Not for diagnosis, treatment advice, individual case safety report creation, or filing and submission.
- compatibility
- Requires Python 3.11+ only for optional dependency-free local scripts; no network access, credentials, external models, or image services.
02 资源文件 35
- 资产文件assets/adverse_event_aggregate_input_template.csv120 B
- 资产文件assets/case_report_template.json2.1 KB
- 资产文件assets/clinical_trial_csr_template.json2.6 KB
- 资产文件assets/clinical_trial_results_template.json3.8 KB
- 资产文件assets/clinical_trial_safety_aggregate_template.json1.4 KB
- 资产文件assets/consistency_manifest_template.json531 B
- 资产文件assets/deidentification_process_checklist.json2.1 KB
- 资产文件assets/lab_report_template.json1.7 KB
- 资产文件assets/pathology_report_template.json1.7 KB
- 资产文件assets/provenance_manifest_template.json560 B
- 资产文件assets/quality_review_checklist.json1.7 KB
- 资产文件assets/radiology_report_template.json1.5 KB
- 资产文件assets/research_summary_template.json1.6 KB
- 资产文件assets/terminology_manifest_template.json426 B
- 资产文件assets/trial_protocol_reporting_checklist.json4.2 KB
- 参考文档references/case_report_guidelines.md3.3 KB
- 参考文档references/clinical_trial_reporting.md5.0 KB
- 参考文档references/data_presentation.md3.6 KB
- 参考文档references/diagnostic_reports_standards.md4.0 KB
- 参考文档references/medical_terminology.md3.5 KB
- 参考文档references/privacy_and_deidentification.md4.5 KB
- 参考文档references/professional_review.md3.9 KB
- 参考文档references/README.md2.1 KB
- 参考文档references/report_type_routing.md4.2 KB
- 参考文档references/safety_reporting.md5.9 KB
- 参考文档references/sources.md8.4 KB
- 脚本scripts/_common.py9.3 KB
- 脚本scripts/check_deidentification.py11.1 KB
- 脚本scripts/consistency_checker.py12.1 KB
- 脚本scripts/format_adverse_events.py16.1 KB
- 脚本scripts/generate_report_template.py4.0 KB
- 脚本scripts/provenance_validator.py9.9 KB
- 脚本scripts/terminology_validator.py10.1 KB
- 脚本scripts/validate_case_report.py9.5 KB
- 脚本scripts/validate_trial_report.py20.2 KB
03 SKILL.md 正文
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.
Do not accept raw free-text patient records when a structured source-fact manifest can be supplied. Do not copy direct identifiers into this skill’s templates or scripts.
Route Before Drafting
| Artifact | Primary route | Important boundary |
|---|---|---|
| Case report for publication | CARE 2013 checklist and 2017 explanation | Publication consent, privacy, journal policy, and clinical accuracy require human verification |
| Radiology draft scaffold | ACR 2025 communication practice parameter plus modality-specific ACR material | A qualified radiologist authors findings/impression and handles nonroutine communication |
| Pathology draft scaffold | Current specimen-specific CAP Cancer Protocol, if applicable | A qualified pathologist selects the protocol/version and authors diagnosis |
| Laboratory draft scaffold | 42 CFR 493.1291 and laboratory policy | The performing laboratory controls results, reference intervals, corrections, and release |
| Randomized-trial results report | CONSORT 2025 plus every applicable current extension | CONSORT is reporting guidance, not a conduct or submission standard |
| Randomized-trial protocol report | SPIRIT 2025 plus applicable extensions | SPIRIT is for protocols, not results or CSRs |
| Clinical Study Report | ICH E3 plus E3 Q&A; consider ICH E6(R3) and regional requirements | E3 is adaptable guidance, not a rigid universal template |
| Pre-approval safety report | ICH E2A; E2B(R3) for electronic ICSR data; applicable regional law/guidance | Qualified sponsor/investigator safety assessment controls reportability and timing |
| Post-approval individual safety report | ICH E2D(R1), E2B(R3), and regional requirements | Do not automate case assessment, coding, or submission |
| Aggregate safety presentation | Protocol/SAP, ICH E3, CONSORT Harms, and applicable FDA/ICH guidance | Aggregate tables never determine individual-case reportability |
| Aggregate research summary | Study-design-specific reporting guideline and source protocol/SAP | State population, estimand, denominator, missingness, and limitations exactly as verified |
Read references/report_type_routing.md before choosing a route. Use the dated primary-source ledger in references/sources.md; check the live official source when requirements could have changed.
Safe Drafting Workflow
1. Create a source-fact manifest
Use assets/provenance_manifest_template.json. Record only local record locators, field paths, verification state, verifier role, verification date, and a SHA-256 value hash. Do not duplicate source content or direct identifiers.
Every draft claim or populated field must cite one or more fact IDs. Unsupported content remains null or missing; never replace it with plausible text.
2. Generate the correct template
PYTHONDONTWRITEBYTECODE=1 python3 scripts/generate_report_template.py --list
PYTHONDONTWRITEBYTECODE=1 python3 scripts/generate_report_template.py \
--type case-report \
--output ./case-report-draft.json
The generator copies a fail-closed JSON template. It does not populate clinical content, create directories, overwrite files by default, or certify readiness.
3. Populate verified fields only
- Keep
draft_statusunchanged. - Replace
nullonly when a verified fact ID supports the field. - Preserve uncertainty and “not assessed” exactly as recorded.
- Do not translate a raw observation into a diagnosis, code, grade, stage, seriousness, causality, expectedness, or recommendation.
- Use
not_applicable_with_rationaleonly when a qualified reviewer supplied the rationale. - Keep source record and draft separate.
4. Run deterministic checks
CARE structure:
PYTHONDONTWRITEBYTECODE=1 python3 scripts/validate_case_report.py \
./case-report-draft.json
ICH E3, CONSORT 2025, or SPIRIT 2025 structure:
PYTHONDONTWRITEBYTECODE=1 python3 scripts/validate_trial_report.py \
./trial-report-manifest.json
Aggregate adverse-event table:
PYTHONDONTWRITEBYTECODE=1 python3 scripts/format_adverse_events.py \
./aggregate-ae.csv --metadata ./safety-aggregate.json \
--output ./aggregate-ae-table.md
Terminology schema:
PYTHONDONTWRITEBYTECODE=1 python3 scripts/terminology_validator.py \
./terminology-manifest.json
De-identification process documentation:
PYTHONDONTWRITEBYTECODE=1 python3 scripts/check_deidentification.py \
./deidentification-process.json
Traceability and consistency:
PYTHONDONTWRITEBYTECODE=1 python3 scripts/provenance_validator.py ./provenance.json
PYTHONDONTWRITEBYTECODE=1 python3 scripts/consistency_checker.py ./consistency.json
These tools use the Python standard library, local bounded files, and no network, dynamic evaluation, serialization code execution, or patient-record extraction. A successful result still says review is required.
5. Apply the right review
At minimum:
- clinical facts and interpretations: qualified clinician for the specialty;
- statistical results, populations, estimands, denominators, and missingness: qualified statistician;
- safety coding, seriousness, causality, expectedness, and reportability: qualified safety professional;
- HIPAA, consent, authorization, and disclosure: privacy/legal/institutional review;
- CSR or regulatory safety output: sponsor regulatory and medical review;
- publication: all accountable authors and target-journal checks.
Never sign or submit on another person’s behalf.
Case Reports
Use assets/case_report_template.json and references/case_report_guidelines.md.
- CARE’s current core checklist remains the 2013 checklist.
- Report only what the verified record supports.
- Do not turn a case into clinical advice or generalize causality from one case.
- Patient perspective and informed-consent status must be recorded accurately; do not draft a false consent statement.
- De-identification and consent are separate controls. Consent does not erase privacy risk.
Diagnostic Report Scaffolds
Use the radiology, pathology, or laboratory JSON asset and references/diagnostic_reports_standards.md.
- The assets are field maps, not diagnostic authoring systems.
- Never generate findings, impressions, diagnoses, grades, stages, reference intervals, critical thresholds, or follow-up recommendations.
- Preserve preliminary/final/corrected status and source-system version.
- Use current, exact CAP protocol and version for the specimen; do not maintain a generic cancer staging default.
- Communication and correction actions remain with the responsible clinical service.
The former SOAP, H&P, consultation, and discharge-summary interfaces were removed. Do not recreate patient-care notes, medication plans, triage instructions, billing support, or disposition advice.
Trial, CSR, and Safety Reporting
Read references/clinical_trial_reporting.md and references/safety_reporting.md.
- CONSORT 2025 has 30 minimum items for randomized-trial results; select relevant extensions from the current official catalogue.
- SPIRIT 2025 has 34 minimum items for randomized-trial protocols and supersedes SPIRIT 2013.
- ICH E3 remains the CSR basis; its 2012 Q&A explicitly permits justified adaptation.
- ICH E6(R3) consolidated Principles, Annex 1, and Annex 2 were adopted on 16 June 2026; regional implementation can differ.
- Distinguish seriousness from severity and an adverse event from a suspected adverse reaction.
- ICH E2B(R3) defines electronic ICSR data/message structure; it is not an aggregate-table format or a reportability decision rule.
- ICH E2D(R1), adopted 15 September 2025, addresses post-approval individual case safety reporting; aggregate periodic reporting is addressed separately.
- FDA requirements and electronic submission routes are role-, product-, study-, and date-specific. This skill never files or transmits.
Privacy
Read references/privacy_and_deidentification.md.
- Handle only the minimum necessary data locally.
- HHS recognizes Safe Harbor and Expert Determination under 45 CFR 164.514(b).
- Safe Harbor also requires no actual knowledge that remaining information can identify an individual.
- Expert Determination must be performed and documented by an appropriately qualified expert.
- A checklist or pattern scan cannot establish de-identification or HIPAA compliance.
- Rare conditions, small cells, dates, free text, images, metadata, and combinations of quasi-identifiers can retain re-identification risk.
Assets
All assets contain synthetic schemas only and start blocked:
assets/case_report_template.jsonassets/radiology_report_template.jsonassets/pathology_report_template.jsonassets/lab_report_template.jsonassets/clinical_trial_csr_template.jsonassets/clinical_trial_results_template.jsonassets/trial_protocol_reporting_checklist.jsonassets/clinical_trial_safety_aggregate_template.jsonassets/adverse_event_aggregate_input_template.csvassets/research_summary_template.jsonassets/deidentification_process_checklist.jsonassets/quality_review_checklist.jsonassets/provenance_manifest_template.jsonassets/terminology_manifest_template.jsonassets/consistency_manifest_template.json
References
references/README.md— safe use and file mapreferences/report_type_routing.md— artifact-to-guidance routingreferences/case_report_guidelines.md— CARE structure and publication safeguardsreferences/diagnostic_reports_standards.md— ACR, CAP, and CLIA boundariesreferences/clinical_trial_reporting.md— CONSORT 2025, SPIRIT 2025, ICH E3/E6(R3)references/safety_reporting.md— ICH E2/FDA safety distinctionsreferences/privacy_and_deidentification.md— HHS methods and limitationsreferences/medical_terminology.md— versioned terminology and schema checksreferences/data_presentation.md— denominators, units, missingness, and aggregate tablesreferences/professional_review.md— ethics, accountability, and sign-offreferences/sources.md— official source ledger, checked 2026-07-23
Final Handoff
State:
- artifact type and exact guidance/version used;
- allowed data class and local-only handling;
- unresolved
null,missing, conflicts, and unsupported claims; - provenance and deterministic-check results;
- required qualified reviewers;
- the draft/non-submission warning.
Never say “compliant,” “HIPAA-safe,” “validated clinically,” “approved,” “ready to file,” or “ready to submit.”
Related skills
scientific-writing: Draft, revise, and audit scientific manuscripts or reports with explicit evidence provenance, reporting-guideline coverage, authorship acco…clinical-decision-support: Prepare and validate research-only clinical decision-support evaluation, evidence-profile, cohort, survival, biomarker/model, privacy, and…
04 同仓库更多 Skills
plos
Prepare manuscripts for PLOS journals (PLOS ONE, PLOS Biology, PLOS Computational Biology, PLOS Genetics, PLOS Medicine, PLOS Pathogens, PLOS Neglected Tropical Diseases, PLOS Global Public Health and others), covering structure, abstract and author summary, Vancouver-style references, the mandatory data availability policy, ethics and financial disclosure statements, figure requirements (PACE), the PLOS LaTeX template, reporting guidelines and PLOS ONE's publication criteria. Use when targeting any PLOS journal or checking compliance with PLOS policies.
pkpd-modeling
Pharmacokinetic and pharmacodynamic modelling and simulation - non-compartmental analysis, compartmental and population PK, PK/PD and exposure-response, TMDD, PBPK orientation, bioequivalence, allometric scaling and first-in-human dose, drug interaction prediction, and Bayesian therapeutic drug monitoring. Use when analysing concentration-time data, deriving exposure metrics, fitting PK or PD models, or evaluating dosing regimens. Triggers include "pharmacokinetics", "pharmacodynamics", "PK/PD", "NCA", "non-compartmental", "AUC", "Cmax", "lambda z", "half-life", "clearance", "volume of distribution", "compartmental model", "population PK", "popPK", "NONMEM", "nlmixr2", "Pharmpy", "Monolix", "exposure-response", "Emax", "EC50", "indirect response", "effect compartment", "TMDD", "PBPK", "bioequivalence", "RSABE", "ABEL", "allometric scaling", "first-in-human", "MABEL", "drug-drug interaction", "DDI", "ICH M12", "concentration-QTc", "therapeutic drug monitoring", "MIPD", and "dosing regimen".
pinecone
Guides use of Pinecone, a managed serverless vector database, through its Python client and the LangChain and LlamaIndex integrations. Covers creating indexes, upserting and querying vectors, metadata filtering, namespaces, hybrid dense and sparse search, index management, and deleting vectors. Use when building a production RAG system on a hosted vector store, adding semantic search or recommendations without running infrastructure, isolating per-user or per-tenant data with namespaces, combining dense and sparse vectors in one query, or filtering results by metadata. Do not use for self-hosted or local stores (Chroma, Weaviate) or offline similarity search (FAISS).
pi-agent
Build with and use Pi, the minimal terminal coding harness. Use for installing Pi, configuring providers/models/settings/environment variables, creating Pi skills/extensions/packages/themes/prompt templates, embedding Pi through the SDK, integrating over RPC or JSON event streams, parsing sessions, running local models through the llama.cpp router, developing custom Pi providers and TUI components, or using ecosystem packages such as pi-subagents (delegation/orchestration), pi-mcp-adapter (MCP servers), pi-interview (interactive forms), and pi-web-access (web search, fetching, video understanding).
phoenix-observability
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
peft-fine-tuning
Fine-tunes LLMs with Hugging Face PEFT, using LoRA, QLoRA, IA3, AdaLoRA, prefix tuning, and prompt tuning so that under 1% of parameters are trained. Covers rank, alpha, and target module selection, loading and merging adapters, multi-adapter serving, and integration with TRL SFTTrainer, Axolotl, and vLLM. Use when fine-tuning 7B-70B models on limited GPU memory, when running QLoRA on a single 24GB GPU, when choosing LoRA rank and alpha, when merging or swapping adapters on one base model, or when debugging CUDA OOM or an adapter that does not apply. Not for full fine-tuning of small models under 1B parameters or cases needing all weights updated.