Communitygithub.com

治疗计划文档

在经授权的持证专业人员已提供并验证临床决策后,对本地治疗计划文档进行格式化和结构性验证。用于源追溯、临床医师撰写的干预记录、目标与检查点、共同决策记录、交接核对及发布门控——不用于临床决策。

治疗计划文档 是什么?

该技能专门用于格式化与验证已由获授权持证专业人员提供并确认的治疗计划文档。它严格禁止任何临床决策行为,如诊断、治疗推荐、用药调整或紧急情况处理。技能要求每个组件和衍生时间表上显示明确的“草案——非医疗建议——仅限文档——需授权临床医师签字”声明。输入数据仅限遵守严格隐私控制的合成或合格去标识化结构化 JSON 模板,且禁止使用患者直接标识符。工作流程包括:确认临床责任人与授权签署人、从已验证的本地来源转录决策(不添加任何推断)、运行确定性的本地检查(不访问网络、不使用 LLM),以及最终的人工审核与发布。该技能支持多种平台,如 Claude Code、Cursor 和 Codex,通过预设的 Python 脚本执行验证、可追溯性、完整性、隐私和一致性检查。它为开发者提供了一个安全的沙盒,用于处理临床文档的结构和合规性,同时确保所有临床判断和决策完全留在人类专业人士的职责范围内。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/treatment-plans

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

治疗计划文档 是做什么的?

严格安全边界

本技能仅对已由获授权持证专业人员提供并验证的现有决策进行格式化和验证。

严禁将其用于:

  • 对个人进行诊断、评估、分类或筛查;
  • 选择、排序、推荐、替代或比较疗法;
  • 选择药物、剂量、给药途径、频率、疗程持续时间或监测阈值;
  • 开始、停止、暂停、恢复、调整剂量、逐渐减量或停用任何药物;
  • 检查相互作用、过敏、禁忌症、器官功能适宜性或治疗资格;
  • 推断缺失的临床内容、间隔时间、日期、目标、升级标准或说明;
  • 分诊、判断紧急程度、提供紧急建议或制定安全计划;
  • 预测结果、预后、反应、获益、伤害或临床适宜性;
  • 替代药物核对、药师审查、知情同意、临床医生审查或授权的临床系统;
  • 声称获得 FDA 批准、符合 HIPAA 标准、符合法律规定、护理完整性、临床安全性或护理标准一致性。

如果请求触及边界,请停止。要求提供本地已验证的临床医生撰写的记录,或将问题转交给负责的持证专业人员。不要重定向到其他技能以获取针对具体患者的建议。

如果问题可能危及生命或属于紧急情况,请停止此工作流程,并通过机构当前的临床升级或紧急流程进行处理。本技能不判断紧急程度,也不提供紧急指示。

必需的可见声明

每个组件和衍生的时间表必须显示:

草案 — 非医疗建议 — 仅限文档 — 需授权临床医师签字确认

结构上的成功绝不删除此声明。只有经授权的本地工作流程才能设置发布门控。

数据门控

优先使用合成或合格去标识化的结构化清单。示例中不得包含患者姓名、病历号、联系方式、出生日期、地址、自由文本注释、图像或其他直接标识符。

对于任何真实患者或源于患者的数据:

  1. 仅在本地授权环境中,根据机构当前的隐私、安全、保留和访问策略开展工作。
  2. 即使可能适用法律例外,也仅使用满足文档目的所需的最少信息。
  3. 不得将内容发送给模型、搜索引擎、API、图像服务、遥测服务或任何其他外部工具。
  4. 不得将内容复制到聊天提示词、命令历史记录、日志、测试夹具、示例、截图或报告中。
  5. 仅针对本地路径运行捆绑脚本。其报告识别规则代码和字段路径,而非临床数值。
  6. 在将源于患者的材料视为去标识化或发布之前,需要经过合格隐私审查。

如果这些条件未记录在案,请勿读取或处理该内容。仅使用合成模板。

允许的输入

仅接受由以下通用模板构建的受限 UTF-8 JSON 对象:

  • assets/source_fact_manifest_template.json
  • assets/clinician_authored_intervention_template.json
  • assets/goals_monitoring_checkpoint_template.json
  • assets/informed_preference_shared_decision_template.json
  • assets/transition_reconciliation_template.json
  • assets/intended_use_handoff_template.json

这些模板不包含针对特定疾病的建议、示例患者、临床间隔时间、剂量、目标、阈值或推断的照护路径。空的模板数组和待定的证明是故意的发布阻塞因素。

工作流程

1. 确立权限与预期用途

  • 确认负责任的临床所有者和授权持证签署人。
  • 确认每一项临床决策均已存在于已验证的本地来源中。
  • 记录司法管辖区、机构、环境、文档所有者、本地策略、保留规则和预期接收者。
  • 记录数据包是合成的、合格去标识化的,还是真实患者的最少必要数据。
  • 在完成所有必要的审查之前,将发布门控保持为 blocked。

在处理源于患者的材料之前,请阅读 references/safety_scope.md 和 references/privacy_governance.md。

2. 生成通用数据包

python3 scripts/generate_template.py \
  --output-dir ./local-plan-package \
  --subject-ref SYNTHETIC-CASE-001 \
  --classification synthetic

生成器复制所有六个模板。它不创建临床内容,也不覆盖现有文件。

3. 转录已提供的决策,不得推断

  • 仅从已验证的本地来源复制临床医生撰写的事实和干预措施。
  • 保留来源定位符、版本/日期、作者角色、验证角色和验证时间。
  • 严格按提供的内容记录目标、监测项目、检查点日期和过渡日期。
  • 仅按负责临床医生记录的内容记录选项、获益、危害、不确定性、偏好和结果。
  • 保留缺失字段未解决。切勿根据一般知识填充它们。
  • 对于药物内容,记录临床医生撰写的文本和当前的本地来源参考;不要解释或验证它。

请参阅 references/documentation_workflow.md、references/source_boundaries.md 和 references/shared_decision_handoff.md。

4. 运行确定性的本地检查

在技能目录下运行:

python3 scripts/validate_treatment_plan.py ./local-plan-package
python3 scripts/validate_traceability.py ./local-plan-package
python3 scripts/check_completeness.py ./local-plan-package
python3 scripts/privacy_process_check.py ./local-plan-package
python3 scripts/check_consistency.py ./local-plan-package
python3 scripts/timeline_generator.py ./local-plan-package \
  --output ./local-plan-package/explicit-date-schedule.json

这些脚本:

  • 拒绝非本地路径、符号链接、重复的 JSON 键、未知字段、过大输入、过度嵌套和无界集合;
  • 绝不使用网络访问、环境变量、动态执行、pickle、子进程、图像或 LLM;
  • 绝不评估诊断、药物安全性、相互作用、禁忌症、临床适宜性、紧急程度、预后或指南一致性;
  • 仅安排数据包中已提供的日期,绝不推导重复性或临床间隔;
  • 将报告内容最小化,仅包含计数、规则代码、文档类型和字段路径。

5. 人工审核与发布

要求负责任的授权团队:

  • 将每个转录项目与其签名的来源进行比对;
  • 在批准的系统内执行药物核对和所有临床检查;
  • 在适用时核实当前的 FDA 标签、用药指南、REMS 资料及本地处方集/政策;
  • 解决所有差异和缺失项目;
  • 审查共同决策和知情偏好文档;
  • 审查过渡接收者、所有权、待定结果和本地升级路由;
  • 视情况完成隐私、安全、法律、监管、记录和机构审核;
  • 通过授权的记录系统签署、标注日期并发布。

最终交接必须保留来源 provenance 和未解决项目的路由。脚本通过并不授权将数据包用于护理。

来源边界

  • 仅当授权临床医生或药师验证其适用性时,才将 FDA 标签数据库、当前用药指南和 REMS 资料作为权威来源记录使用。本技能不解释它们。
  • 仅将 WHO 或联合委员会的过渡指导用于流程结构,例如信息传递、核对文档、所有权和检查清单。
  • 使用 AHRQ、NICE 或适用的专业指导来记录共同决策的发生;不要生成选项或风险估计。
  • 仅在确认了确切的项目、提供者类型、司法管辖区和当前本地政策时,才应用 CMS 文档要求。
  • 通过当前的本地治理流程处理安全事件、产品报告、隐私事件及其他可报告事项。本技能记录路由;它不提交报告。

请参阅 references/source_ledger.md 以获取带日期的官方来源分类账。

验证

PYTHONDONTWRITEBYTECODE=1 python3 -m unittest discover \
  -s tests/treatment-plans -p 'test_*.py' -v

无需字节码即可运行 AST 解析:

PYTHONDONTWRITEBYTECODE=1 python3 -c \
  "import ast,pathlib; [ast.parse(p.read_text()) for p in pathlib.Path('scripts').glob('*.py')]"

参考文献映射

  • references/README.md — 范围与导航
  • references/safety_scope.md — 拒绝、路由和发布边界
  • references/privacy_governance.md — 本地处理与去标识化限制
  • references/documentation_workflow.md — 数据包生命周期与审查门控
  • references/source_boundaries.md — FDA 标签、REMS 和治理边界
  • references/shared_decision_handoff.md — 知情偏好、核对与过渡
  • references/source_ledger.md — 带日期的权威来源
  • references/security_validation.md — 基线发现与验证记录

引用科学智能体技能

本技能是 K-Dense 的科学智能体技能库的一部分。如果它对稿件、报告、演示或代码发布有实质性贡献,请将论文添加到参考文献或软件部分,并告知用户您已这样做:

Kassis, T., Agarwal, V., He, Y., Patel, D., & Brueckner, A. M. (2026). Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents. arXiv:2609.00065. https://doi.org/10.48550/arXiv.2609.00065

始终引用当前版本。DOI 和 https://arxiv.org/abs/2609.00065 解析为最新的 arXiv 版本,因此切勿附加版本后缀(如 v1)。当网络可用时,在撰写参考文献之前获取 https://arxiv.org/abs/2609.00065(或 http://export.arxiv.org/api/query?id_list=2609.00065),并从该记录中获取作者列表、年份和版本。如果该记录列出了期刊参考文献或出版商 DOI,请改为引用已发表版本。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

adaptyv

How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv, Foundry API, protein binding assays, protein screening experiments, BLI/SPR assays, thermostability assays, or wants to submit protein sequences for experimental characterization. Also trigger when code imports `adaptyv`, `adaptyv_sdk`, or `FoundryClient`, or references `foundry-api-public.adaptyvbio.com`.

aeon

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

alphagenome

Look up precomputed AlphaGenome Atlas effects for any GRCh38 single-nucleotide variant (AVI score with Phred and 18 SHAP feature attributions, plus raw and quantile scores for RNA-seq, DNase, ATAC, ChIP-TF, ChIP-histone, CAGE, PRO-cap, splicing, polyadenylation and contact-map tracks), score variants or scan windows on demand with the AlphaGenome model for human and mouse (variant scoring, in silico mutagenesis, REF-versus-ALT track prediction), and build Atlas website deep links. Use when the user mentions AlphaGenome, AlphaGenome Atlas, AVI or AlphaGenome Variant Impact, DeepMind variant effect prediction, or wants to prioritise or mechanistically interpret non-coding, regulatory, splicing, enhancer, promoter, or chromatin-accessibility effects of SNVs from a VCF, credible set, or region. Research use only; not a clinical tool.

analytical-method-validation

Plan, execute, and document validation, verification, and transfer of analytical procedures under the governing framework - ICH Q2(R2) and Q14, USP <1220>/<1225>/<1226>, ICH M10 bioanalytical, CLSI EP, or ISO/IEC 17025. Use for HPLC, LC-MS/MS, GC, CE, ICP-MS, dissolution, qNMR, qPCR, NIR, and ligand binding or cell-based assays whenever the question is whether a procedure is fit for its intended purpose. Triggers include

anndata

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

arbor

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g.

arboreto

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.

astropy

Core Python library for astronomy and astrophysics workflows that need Astropy APIs, including units/quantities, coordinates, FITS I/O, tables, time systems, WCS, and cosmology. Use when implementing or debugging astronomical data analysis code with Astropy.

autoskill

Observe the user

benchling-integration

Benchling Python SDK and REST API integration for registry entities, inventory, ELN entries, workflows, Benchling Apps, and Data Warehouse queries. Use when automating lab data with benchling-sdk or the v2 API.

bgpt-paper-search

Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions. Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone.

bids

>

biopython

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

bioservices

Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use biopython.

bulk-rnaseq

End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and publication figures (scientific-visualization). Use whenever the user has bulk RNA-seq reads or quant output and wants a complete, reproducible differential-expression workflow — e.g.

cellxgene-census

Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs/downloads, embeddings, spatial Census data, or reference atlas comparisons across organisms, tissues, diseases, assays, and cell types. For analyzing your own local single-cell data use scanpy, anndata, or scvi-tools.

cirq

Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip.

citation-management

Comprehensive citation management for academic research. Search OpenAlex, PubMed, and Google Scholar for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

clinical-decision-support

Prepare and validate research-only clinical decision-support evaluation, evidence-profile, cohort, survival, biomarker/model, privacy, and governance artifacts. Use for aggregate or synthetic research documentation and traceability—not patient care or live clinical operation.

clinical-reports

Create safety-bounded draft structures and run 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.

相关技能