Skill Tracer
Skills › Scientific Agent Skills › clinical-reports

clinical-reports

skill · 271 lines · MIT · skills/clinical-reports/SKILL.md

The facts

Its description

Creates safety-bounded draft structures and runs local deterministic checks for clinical case, diagnostic, trial, safety, and aggregate research reports. Use only with synthetic, de-identified, or aggregate inputs and verified source-fact manifests; every output requires qualified review.

The description the agent reads to decide when to use it.

From its settingsline 3

Runs scripts

python3 scripts/generate_report_template.py, python3 scripts/validate_case_report.py, python3 scripts/validate_trial_report.py, python3 scripts/format_adverse_events.py (first 5 of 9 lines)

Scripts the text names. Found by matching words, so treat them as pointers.

Found by matching wordsline 85 line 86 line 107 line 114 line 121

Files it mentions

references/report_type_routing.md, references/sources.md, assets/provenance_manifest_template.json, assets/case_report_template.json, references/case_report_guidelines.md, references/diagnostic_reports_standards.md, references/clinical_trial_reporting.md, references/safety_reporting.md (first 5 of 31 lines)

Files the text names, such as ones to read or write. Found by matching words, so treat them as pointers.

Found by matching wordsline 72 line 78 line 164 line 174 line 186

Licence

MIT, from the skill file

The terms its author shares it under, which let it be shown here.

From its settingsline 4 licence text

Other settings

compatibility: Requires Python 3.11+ for optional dependency-free local scripts. No credentials or network needed for data processing; network access is needed only to review current public guidance. metadata: version: "2.3" last-reviewed: "2026-09-30" skill-author: K-Dense Inc.

More settings at the top of the file, shown as written.

From its settingsline 5 line 6
Other files in this skill (34) Close

The text

Open on GitHub

Most marks come from matching words in the file, so treat them as pointers.

1---
2name: clinical-reports
3description: Creates safety-bounded draft structures and runs local deterministic checks for clinical case, diagnostic, trial, safety, and aggregate research reports. Use only with synthetic, de-identified, or aggregate inputs and verified source-fact manifests; every output requires qualified review.
4license: MIT
5compatibility: Requires Python 3.11+ for optional dependency-free local scripts. No credentials or network needed for data processing; network access is needed only to review current public guidance.
6metadata:
7 version: "2.3"
8 last-reviewed: "2026-09-30"
9 skill-author: K-Dense Inc.
10---
12# Clinical Reports

Clinical Reports

Raw lines 1 to 13
14## Purpose
16Prepare **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.
18This skill does not establish legal, regulatory, ethical, journal, accreditation, or institutional compliance. Its scripts check structure and internal consistency only.

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.

Raw lines 14 to 19
20## Non-Negotiable Boundary
22Never:
24- diagnose, recommend treatment, choose or change dosing, triage, or provide return precautions;
25- interpret images, specimens, raw laboratory results, symptoms, or other clinical observations;
26- invent, infer, normalize, “complete,” or silently reconcile observations, results, dates, units, denominators, causality, expectedness, seriousness, outcomes, or conclusions;
27- create an individual case safety report from patient-level narrative or decide reportability;
28- 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;
29- use real PHI in examples, assets, tests, prompts, logs, or external services;
30- send report inputs, manifests, source locators, or clinical content to an external model, image service, API, or another skill.
32Public official guidance may be retrieved separately using only public URLs or generic topic queries; include no patient or unpublished study details.
34All generated artifacts must remain visibly marked:
36> DRAFT — NOT FOR CLINICAL USE, SIGNATURE, FILING, OR SUBMISSION. Populate only from verified authorized source records. Qualified review and sign-off are required.
38If 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.

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;
  • send report inputs, manifests, source locators, or clinical content to an external model, image service, API, or another skill.

Public official guidance may be retrieved separately using only public URLs or generic topic queries; include no patient or unpublished study details.

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.

Raw lines 20 to 39
40## Input Gate
42Proceed only when all conditions are true:
441. **Purpose is explicit**: publication draft, diagnostic-report scaffold, trial-results manuscript, protocol reporting review, CSR draft, aggregate safety table, or aggregate research summary.
452. **Data class is allowed**: `synthetic`, `deidentified`, or `aggregate`.
463. **Authority is documented**: the requester is authorized to use the records for the stated purpose.
474. **Local-only handling is feasible**: no upload, remote API, telemetry, or credential is needed.
485. **Minimum necessary is defined**: exclude fields not needed for the artifact.
496. **Provenance exists**: every populated field or claim maps to one or more verified source-fact IDs.
507. **Review owner is identified**: qualified clinical, statistical, safety, privacy, legal, journal, and/or regulatory review as applicable.
52These gates depend on documented human assessments. Scripts inspect declarations; they do not independently establish authorization, de-identification, reviewer qualifications, or jurisdictional applicability.
54Do 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.

Input Gate

Proceed only when all conditions are true:

  1. Purpose is explicit: publication draft, diagnostic-report scaffold, trial-results manuscript, protocol reporting review, CSR draft, aggregate safety table, or aggregate research summary.
  2. Data class is allowed: synthetic, deidentified, or aggregate.
  3. Authority is documented: the requester is authorized to use the records for the stated purpose.
  4. Local-only handling is feasible: no upload, remote API, telemetry, or credential is needed.
  5. Minimum necessary is defined: exclude fields not needed for the artifact.
  6. Provenance exists: every populated field or claim maps to one or more verified source-fact IDs.
  7. Review owner is identified: qualified clinical, statistical, safety, privacy, legal, journal, and/or regulatory review as applicable.

These gates depend on documented human assessments. Scripts inspect declarations; they do not independently establish authorization, de-identification, reviewer qualifications, or jurisdictional applicability.

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.

Raw lines 40 to 55
56## Route Before Drafting
58| Artifact | Primary route | Important boundary |
59|---|---|---|
60| Case report for publication | CARE 2013 checklist and 2017 explanation | Publication consent, privacy, journal policy, and clinical accuracy require human verification |
61| Radiology draft scaffold | ACR 2025 communication practice parameter plus modality-specific ACR material | A qualified radiologist authors findings/impression and handles nonroutine communication |
62| Pathology draft scaffold | Current specimen-specific CAP Cancer Protocol, if applicable | A qualified pathologist selects the protocol/version and authors diagnosis |
63| Laboratory draft scaffold | 42 CFR 493.1291 and laboratory policy | The performing laboratory controls results, reference intervals, corrections, and release |
64| Randomized-trial results report | CONSORT 2025 plus every applicable current extension | CONSORT is reporting guidance, not a conduct or submission standard |
65| Randomized-trial protocol report | SPIRIT 2025 plus applicable extensions | SPIRIT is for protocols, not results or CSRs |
66| 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 |
67| 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 |
68| Post-approval individual safety report | ICH E2D(R1), E2B(R3), and regional requirements | Do not automate case assessment, coding, or submission |
69| Aggregate safety presentation | Protocol/SAP, ICH E3, CONSORT Harms, and applicable FDA/ICH guidance | Aggregate tables never determine individual-case reportability |
70| Aggregate research summary | Study-design-specific reporting guideline and source protocol/SAP | State population, estimand, denominator, missingness, and limitations exactly as verified |
72Read `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.

Route Before Drafting

ArtifactPrimary routeImportant boundary
Case report for publicationCARE 2013 checklist and 2017 explanationPublication consent, privacy, journal policy, and clinical accuracy require human verification
Radiology draft scaffoldACR 2025 communication practice parameter plus modality-specific ACR materialA qualified radiologist authors findings/impression and handles nonroutine communication
Pathology draft scaffoldCurrent specimen-specific CAP Cancer Protocol, if applicableA qualified pathologist selects the protocol/version and authors diagnosis
Laboratory draft scaffold42 CFR 493.1291 and laboratory policyThe performing laboratory controls results, reference intervals, corrections, and release
Randomized-trial results reportCONSORT 2025 plus every applicable current extensionCONSORT is reporting guidance, not a conduct or submission standard
Randomized-trial protocol reportSPIRIT 2025 plus applicable extensionsSPIRIT is for protocols, not results or CSRs
Clinical Study ReportICH E3 plus E3 Q&A; consider ICH E6(R3) and regional requirementsE3 is adaptable guidance, not a rigid universal template
Pre-approval safety reportICH E2A; E2B(R3) for electronic ICSR data; applicable regional law/guidanceQualified sponsor/investigator safety assessment controls reportability and timing
Post-approval individual safety reportICH E2D(R1), E2B(R3), and regional requirementsDo not automate case assessment, coding, or submission
Aggregate safety presentationProtocol/SAP, ICH E3, CONSORT Harms, and applicable FDA/ICH guidanceAggregate tables never determine individual-case reportability
Aggregate research summaryStudy-design-specific reporting guideline and source protocol/SAPState 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.

Raw lines 56 to 73
74## Safe Drafting Workflow

Safe Drafting Workflow

Raw lines 74 to 75
76### 1. Create a source-fact manifest
78Use `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. Hashes are integrity metadata, not de-identification; do not hash an identifier as a substitute for removing it.
80Every draft claim or populated field must cite one or more fact IDs. Unsupported content remains `null` or `missing`; never replace it with plausible text.

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. Hashes are integrity metadata, not de-identification; do not hash an identifier as a substitute for removing it.

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.

Raw lines 76 to 81
82### 2. Generate the correct template
84```bash
85PYTHONDONTWRITEBYTECODE=1 python3 scripts/generate_report_template.py --list
86PYTHONDONTWRITEBYTECODE=1 python3 scripts/generate_report_template.py \
87 --type case-report \
88 --output ./case-report-draft.json
89```
91The generator copies a fail-closed JSON template. It does not populate clinical content, create directories, overwrite files by default, or certify readiness.

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.

Raw lines 82 to 92
Runs code python3 scripts/generate_report_template.py :85
93### 3. Populate verified fields only
95- Keep `draft_status` unchanged.
96- Replace `null` only when a verified fact ID supports the field.
97- Preserve uncertainty and “not assessed” exactly as recorded.
98- Do not translate a raw observation into a diagnosis, code, grade, stage, seriousness, causality, expectedness, or recommendation.
99- Use `not_applicable_with_rationale` only when a qualified reviewer supplied the rationale.
100- Keep source record and draft separate.

3. Populate verified fields only

  • Keep draft_status unchanged.
  • Replace null only 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_rationale only when a qualified reviewer supplied the rationale.
  • Keep source record and draft separate.
Raw lines 93 to 101
102### 4. Run deterministic checks
104CARE structure:
106```bash
107PYTHONDONTWRITEBYTECODE=1 python3 scripts/validate_case_report.py \
108 ./case-report-draft.json
109```
111ICH E3, CONSORT 2025, or SPIRIT 2025 structure:
113```bash
114PYTHONDONTWRITEBYTECODE=1 python3 scripts/validate_trial_report.py \
115 ./trial-report-manifest.json
116```
118Aggregate adverse-event table:
120```bash
121PYTHONDONTWRITEBYTECODE=1 python3 scripts/format_adverse_events.py \
122 ./aggregate-ae.csv --metadata ./safety-aggregate.json \
123 --output ./aggregate-ae-table.md
124```
126Terminology schema:
128```bash
129PYTHONDONTWRITEBYTECODE=1 python3 scripts/terminology_validator.py \
130 ./terminology-manifest.json
131```
133De-identification process documentation:
135```bash
136PYTHONDONTWRITEBYTECODE=1 python3 scripts/check_deidentification.py \
137 ./deidentification-process.json
138```
140Traceability and consistency:
142```bash
143PYTHONDONTWRITEBYTECODE=1 python3 scripts/provenance_validator.py ./provenance.json
144PYTHONDONTWRITEBYTECODE=1 python3 scripts/consistency_checker.py ./consistency.json
145```
147These tools use the Python standard library and bounded local files, with no network or patient-record extraction. Case/trial checks validate fact-ID shape, not whether those IDs exist in a separate provenance file. Run the provenance check separately and have the reviewer verify the links across artifacts; that checker does not open source records or recompute hashes. A successful result still says review is required.

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 and bounded local files, with no network or patient-record extraction. Case/trial checks validate fact-ID shape, not whether those IDs exist in a separate provenance file. Run the provenance check separately and have the reviewer verify the links across artifacts; that checker does not open source records or recompute hashes. A successful result still says review is required.

Raw lines 102 to 148
Runs code python3 scripts/validate_case_report.py :107
Runs code python3 scripts/validate_trial_report.py :114
Runs code python3 scripts/format_adverse_events.py :121
Runs code python3 scripts/terminology_validator.py :129
Runs code python3 scripts/check_deidentification.py :136
Runs code python3 scripts/provenance_validator.py :143
Runs code python3 scripts/consistency_checker.py :144
149### 5. Apply the right review
151At minimum:
153- clinical facts and interpretations: qualified clinician for the specialty;
154- statistical results, populations, estimands, denominators, and missingness: qualified statistician;
155- safety coding, seriousness, causality, expectedness, and reportability: qualified safety professional;
156- HIPAA, consent, authorization, and disclosure: privacy/legal/institutional review;
157- CSR or regulatory safety output: sponsor regulatory and medical review;
158- publication: all accountable authors and target-journal checks.
160Never sign or submit on another person’s behalf.

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.

Raw lines 149 to 161
162## Case Reports
166- CARE’s current core checklist remains the 2013 checklist.
167- Report only what the verified record supports.
168- Do not turn a case into clinical advice or generalize causality from one case.
169- Patient perspective and informed-consent status must be recorded accurately; do not draft a false consent statement.
170- De-identification and consent are separate controls. Consent does not erase privacy risk.

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.
Raw lines 162 to 171
172## Diagnostic Report Scaffolds
174Use the radiology, pathology, or laboratory JSON asset and `references/diagnostic_reports_standards.md`.
176- The assets are field maps, not diagnostic authoring systems.
177- Never generate findings, impressions, diagnoses, grades, stages, reference intervals, critical thresholds, or follow-up recommendations.
178- Preserve preliminary/final/corrected status and source-system version.
179- Use current, exact CAP protocol and version for the specimen; do not maintain a generic cancer staging default.
180- Communication and correction actions remain with the responsible clinical service.
182The 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.

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.

Raw lines 172 to 183
184## Trial, CSR, and Safety Reporting
188- CONSORT 2025 has 30 minimum items for randomized-trial results; select relevant extensions from the current official catalogue.
189- SPIRIT 2025 has 34 minimum items for randomized-trial protocols and supersedes SPIRIT 2013.
190- ICH E3 remains the CSR basis; its 2012 Q&A explicitly permits justified adaptation.
191- ICH E6(R3) consolidated Principles, Annex 1, and Annex 2 were adopted on 16 June 2026; regional implementation can differ.
192- Distinguish seriousness from severity and an adverse event from a suspected adverse reaction.
193- Preserve the verified harms counting rule: participants with at least one event, total/recurrent events, and exposure-time rates are different quantities. Label the denominator and observation window for each, and never apply the subject-proportion bound `n <= N` to recurrent event counts.
194- ICH E2B(R3) defines electronic ICSR data/message structure; it is not an aggregate-table format or a reportability decision rule.
195- ICH E2D(R1), adopted 15 September 2025, addresses post-approval individual case safety reporting; aggregate periodic reporting is addressed separately.
196- FDA requirements and electronic submission routes are role-, product-, study-, and date-specific. This skill never files or transmits.

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.
  • Preserve the verified harms counting rule: participants with at least one event, total/recurrent events, and exposure-time rates are different quantities. Label the denominator and observation window for each, and never apply the subject-proportion bound n <= N to recurrent event counts.
  • 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.
Raw lines 184 to 197
198## Privacy
202- Handle only the minimum necessary data locally.
203- HHS recognizes Safe Harbor and Expert Determination under 45 CFR 164.514(b).
204- Safe Harbor also requires no actual knowledge that remaining information can identify an individual.
205- Expert Determination must be performed and documented by an appropriately qualified expert.
206- A checklist or pattern scan cannot establish de-identification or HIPAA compliance.
207- Rare conditions, small cells, dates, free text, images, metadata, and combinations of quasi-identifiers can retain re-identification risk.

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.
Raw lines 198 to 208
229## References
231- `references/README.md` — safe use and file map
232- `references/report_type_routing.md` — artifact-to-guidance routing
233- `references/case_report_guidelines.md` — CARE structure and publication safeguards
234- `references/diagnostic_reports_standards.md` — ACR, CAP, and CLIA boundaries
235- `references/clinical_trial_reporting.md` — CONSORT 2025, SPIRIT 2025, ICH E3/E6(R3)
236- `references/safety_reporting.md` — ICH E2/FDA safety distinctions
237- `references/privacy_and_deidentification.md` — HHS methods and limitations
238- `references/medical_terminology.md` — versioned terminology and schema checks
239- `references/data_presentation.md` — denominators, units, missingness, and aggregate tables
240- `references/professional_review.md` — ethics, accountability, and sign-off
241- `references/sources.md` — official source ledger, checked 2026-09-30

References

Raw lines 229 to 242
243## Final Handoff
245State:
2471. artifact type and exact guidance/version used;
2482. allowed data class and local-only handling;
2493. unresolved `null`, `missing`, conflicts, and unsupported claims;
2504. provenance and deterministic-check results;
2515. required qualified reviewers;
2526. the draft/non-submission warning.
254Never say “compliant,” “HIPAA-safe,” “validated clinically,” “approved,” “ready to file,” or “ready to submit.”

Final Handoff

State:

  1. artifact type and exact guidance/version used;
  2. allowed data class and local-only handling;
  3. unresolved null, missing, conflicts, and unsupported claims;
  4. provenance and deterministic-check results;
  5. required qualified reviewers;
  6. the draft/non-submission warning.

Never say “compliant,” “HIPAA-safe,” “validated clinically,” “approved,” “ready to file,” or “ready to submit.”

Raw lines 243 to 255
Boilerplate, lines 256 to 271. The same text appears in 125 other files here. Close
256## Citing Scientific Agent Skills
258This skill is part of Scientific Agent Skills by K-Dense. If it materially contributed to a
259manuscript, report, presentation, or code release, add the paper to the references or
260software section and tell the user you did so:
262> Kassis, T., Agarwal, V., He, Y., Patel, D., & Brueckner, A. M. (2026). Scientific Agent
263> Skills: A Library of Procedural Knowledge for Research Agents. arXiv:2609.00065.
264> https://doi.org/10.48550/arXiv.2609.00065
266Always cite the current version. The DOI and https://arxiv.org/abs/2609.00065 resolve to the
267latest arXiv version, so never append a version suffix such as `v1`. When network access is
268available, fetch https://arxiv.org/abs/2609.00065 (or
269http://export.arxiv.org/api/query?id_list=2609.00065) before writing the reference and take
270the author list, year, and version from that record. If the record lists a journal reference
271or publisher DOI, cite the published version instead.

From K-Dense-AI/scientific-agent-skills at 5f2bc03, 2026-10-26. Not read by a model yet. Summary and techniques by Claude Opus 5.5 on 2026-11-06.