{ "ok": true, "resource": { "id": "RES_A702563F8F36", "resource_type": "skill", "canonical_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/pkpd-modeling", "name": "pkpd-modeling", "summary_en": "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\".", "summary_zh": "药代动力学和药效学建模与模拟——非房室分析、房室和群体PK、PK/PD和暴露-反应、TMDD、PBPK方向、生物等效性、异速缩放和首次人体剂量、药物相互作用预测以及贝叶斯治疗药物监测。当分析浓度-时间数据、推导暴露指标、拟合PK或PD模型或评估给药方案时使用。触发词包括“药代动力学”、“药效学”、“PK/PD”、“NCA”、“非房室”、“AUC”、“Cmax”、“lambda z”、“半衰期”、“清除率”、“分布容积”、“房室模型”、“群体PK”、“popPK”、“NONMEM”、“nlmixr2”、“Pharmpy”、“Monolix”、“暴露-反应”、“Emax”、“EC50”、“间接反应”、“效应室”、“TMDD”、“PBPK”、“生物等效性”、“RSABE”、“ABEL”、“异速缩放”、“首次人体”、“MABEL”、“药物-药物相互作用”、“DDI”、“ICH M12”、“浓度-QTc”、“治疗药物监测”、“MIPD”和“给药方案”。", "description_en": "This Agent Skill provides scripts and guidance for pharmacokinetic (PK) and pharmacodynamic (PD) modeling and simulation. It covers non-compartmental analysis (NCA), compartmental and population PK, PK/PD and exposure-response analysis, target-mediated drug disposition (TMDD), physiologically-based pharmacokinetic (PBPK) orientation, bioequivalence assessment, allometric scaling and first-in-human dose prediction, drug-drug interaction (DDI) prediction, and Bayesian therapeutic drug monitoring (TDM). The skill includes command-line scripts (e.g., nca.py, fit_compartmental.py, simulate_regimen.py, check_popk_dataset.py, exposure_response.py, bioequivalence.py, allometry_and_fih.py, ddi_static.py, tdm_bayes.py) that compute and diagnose, but do not make regulatory or clinical decisions. It requires Python 3.11+ with numpy and scipy, and does not require network access or proprietary software. The skill is distributed under the MIT license.", "description_zh": "该Agent技能提供药代动力学（PK）和药效学（PD）建模与模拟的脚本和指导。涵盖非房室分析（NCA）、房室和群体PK、PK/PD和暴露-反应分析、靶点介导的药物处置（TMDD）、生理药代动力学（PBPK）方向、生物等效性评估、异速缩放和首次人体剂量预测、药物-药物相互作用（DDI）预测以及贝叶斯治疗药物监测（TDM）。该技能包括命令行脚本（如nca.py、fit_compartmental.py、simulate_regimen.py、check_popk_dataset.py、exposure_response.py、bioequivalence.py、allometry_and_fih.py、ddi_static.py、tdm_bayes.py），这些脚本进行计算和诊断，但不做出监管或临床决策。需要Python 3.11+及numpy和scipy，不需要网络访问或专有软件。该技能根据MIT许可证分发。", "provider_name": "K-Dense-AI", "homepage_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/pkpd-modeling", "endpoint_url": null, "source_url": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/pkpd-modeling/SKILL.md", "icon_url": null, "cover_image_url": null, "capabilities": [ "data.analyze", "data.simulate", "data.model", "research.assist" ], "categories": [ "research", "data", "developer-tools" ], "industries": [ "health", "software" ], "protocols": [ "agent-skills" ], "auth": { "type": "none", "required": false }, "pricing": { "model": "free" }, "input_schema": {}, "output_schema": {}, "metadata": { "content_language": "en", "translation_status": "original-only", "license": { "spdx_id": "MIT", "source": "https://github.com/K-Dense-AI/scientific-agent-skills/blob/1e5eeffbdad3749125afe7ab48a39694e27f181c/LICENSE" }, "github": { "repository": "K-Dense-AI/scientific-agent-skills", "owner": "K-Dense-AI", "path": "skills/pkpd-modeling/SKILL.md", "commit": "1e5eeffbdad3749125afe7ab48a39694e27f181c", "stars": 42124, "forks": 3870, "updated_at": "2026-09-03T02:47:03Z" }, "skill": { "compatibility": "Requires Python 3.11+ with numpy and scipy. No network access and no proprietary software. The estimation tools this skill orients you towards (NONMEM, Monolix, Phoenix, Simcyp, GastroPlus) are licensed separately and are never invoked by these scripts.", "allowed_tools": "Read Write Edit Bash", "content_hash": "5b555b3139ddfbe4edddeed55fc99ad7c4912dc09ac4d03e8be34cffde37e066", "line_count": 399 }, "review_gate": { "passed": true, "reasons": [], "policy_version": "review-gate-v1", "evaluated_at": "2026-09-03T06:03:50.127Z" } }, "latest_version": "1e5eeffbdad3", "status": "listed", "health_status": "unknown", "source_kind": "imported", "source_agent": "aiworkshub-skill-reviewer", "trust": { "signal": "none", "reason": "No suspicious or malicious evidence found.", "signals": { "yellow": 0, "red": 0 } }, "review_summary": { "method_version": "capability-evidence-v2", "capability_definition": "strong", "contract_completeness": "strong", "access_friction": "low", "operational_transparency": "strong", "evidence_strength": "source_inspected", "use_readiness": "guided_use", "reviewed_at": "2026-09-03T06:03:51.006Z" }, "experience_count": 0, "verified_experience_count": 0, "usage_count": 0, "success_rate": null, "first_seen_at": "2026-09-03T02:50:48.635Z", "last_seen_at": "2026-09-03T06:03:50.404Z", "published_at": "2026-09-03T06:03:50.404Z", "created_at": "2026-09-03T02:50:48.635Z", "updated_at": "2026-09-03T06:03:51.006Z", "api_url": "https://aiworkshub.io/api/v1/resources/RES_A702563F8F36", "reviews_url": "https://aiworkshub.io/api/v1/resources/RES_A702563F8F36/reviews", "public_url": "https://aiworkshub.io/resources/RES_A702563F8F36", "distribution": { "canonical_identity": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/pkpd-modeling", "syndicatable": true, "origins": [ { "registry_url": "https://github.com/", "upstream_resource_id": "K-Dense-AI/scientific-agent-skills:skills/pkpd-modeling/SKILL.md", "upstream_record_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/pkpd-modeling", "relation": "syndicated", "metadata": { "source": "github-skill-import" }, "first_seen_at": "2026-09-03T02:50:48.635Z", "last_seen_at": "2026-09-03T06:03:50.404Z" } ] }, "tools": [], "review_profile": { "schema_version": "aiworkshub.resource-review/0.2", "method_version": "capability-evidence-v2", "review_state": { "identity": "verified", "source": "verified", "connectivity": "unknown", "contract": "strong", "safe_use": "untested", "real_use": "unobserved" }, "assessment": { "capability_definition": "strong", "contract_completeness": "strong", "access_friction": "low", "operational_transparency": "strong", "evidence_strength": "source_inspected", "use_readiness": "guided_use" }, "profile": { "capabilities": [ { "id": "data.analyze", "weight": 90, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "data.simulate", "weight": 80, "confidence": 80, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "data.model", "weight": 85, "confidence": 85, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "research.assist", "weight": 70, "confidence": 70, "evidence_ids": [ "source-record" ] } ], "domains": [ { "id": "pharmacokinetics", "weight": 100, "confidence": 95, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "pharmacodynamics", "weight": 100, "confidence": 95, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "clinical-pharmacology", "weight": 90, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "drug-development", "weight": 80, "confidence": 80, "evidence_ids": [ "source-record" ] } ], "workflow_roles": [ "analyze", "design", "execute", "instruct" ] }, "capability_units": [ { "id": "skill:pkpd-modeling", "kind": "skill_action", "capability_id": "data.analyze", "effect": "unknown", "open_world": false, "idempotency": "safe_to_retry", "confirmation": "explicit policy", "input_contract": "natural_language", "output_contract": "natural_language", "accepts": [ "task context" ], "produces": [ "task result" ], "runtime_auth": {}, "pricing": {}, "evidence_ids": [ "source-inspection" ], "metadata": {} } ], "access": { "distribution_license": { "spdx_id": "MIT", "source": "https://github.com/K-Dense-AI/scientific-agent-skills/blob/1e5eeffbdad3749125afe7ab48a39694e27f181c/LICENSE" }, "runtime_auth": {}, "runtime_pricing": {}, "dependencies": [ "Python 3.11+", "numpy", "scipy" ] }, "operational_flags": [], "trust": { "signal": "none", "evidence_ids": [], "reason": "No suspicious or malicious evidence found." }, "fit": { "good_for": [ "Analyzing concentration-time data to derive exposure metrics (AUC, Cmax, half-life, etc.)", "Fitting compartmental PK models and performing model selection", "Simulating drug regimens and assessing target attainment in a population", "Checking population PK datasets for common errors before NONMEM runs", "Conducting exposure-response analysis, including Emax and concentration-QTc", "Assessing bioequivalence using average BE, ABEL, or RSABE criteria", "Scaling pharmacokinetics across species or to pediatric populations", "Predicting drug-drug interactions using static models per ICH M12" ], "not_for": [ "Making regulatory decisions or concluding bioequivalence", "Selecting doses for clinical trials or recommending doses for patients", "Concluding absence of QT liability", "Replacing a qualified pharmacometrician or clinical pharmacologist", "Invoking proprietary software like NONMEM, Monolix, Phoenix, Simcyp, or GastroPlus" ] }, "evidence": [ { "id": "source-record", "type": "source_record", "source": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/pkpd-modeling/SKILL.md", "observation": "Submitted Skill record for pkpd-modeling; declared license MIT.", "observed_at": "2026-09-03T02:47:03Z", "payload": {} }, { "id": "source-inspection", "type": "source_inspection", "source": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/pkpd-modeling/SKILL.md", "observation": "The Skill source was fetched and inspected (21997 bytes; SHA-256 5b555b3139ddfbe4edddeed55fc99ad7c4912dc09ac4d03e8be34cffde37e066).", "observed_at": "2026-09-03T06:03:37.469Z", "payload": {} } ], "unknowns": [ "Real-world usage and adoption metrics are not observed.", "Runtime connectivity and behavior in a live agent environment are not tested.", "The skill's scripts have not been executed in a safe test environment to verify outputs.", "The skill's compatibility with specific agent frameworks or runtimes is not verified beyond the declared Python requirements.", "The skill's content may become outdated; the last review date is 2026-07-27." ], "id": "REV_D2DD20928DA4", "resource_id": "RES_A702563F8F36", "evaluator_type": "platform_ai", "provider": "deepseek", "model": "deepseek-v4-flash", "review_scope": "source-inspected-skill", "created_at": "2026-09-03T06:03:51.006Z" } } }