{ "ok": true, "resource": { "id": "RES_609E6BF69428", "resource_type": "skill", "canonical_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/medchem", "name": "medchem", "summary_en": "Medicinal chemistry filters for compound triage. Apply drug-likeness rules (Lipinski, Veber, CNS), structural alert catalogs (PAINS, NIBR, ChEMBL), complexity metrics, and the medchem query language for library filtering.", "summary_zh": "用于化合物分类的药用化学过滤器。应用类药性规则（Lipinski、Veber、CNS）、结构警报目录（PAINS、NIBR、ChEMBL）、复杂性指标以及药用化学查询语言进行库过滤。", "description_en": "This skill provides medicinal chemistry filters for compound triage. It applies drug-likeness rules (Lipinski, Veber, CNS), structural alert catalogs (PAINS, NIBR, ChEMBL), complexity metrics, and a medchem query language for library filtering. The skill is based on the medchem Python library (version 2.0.5) and requires Python 3.9+ and datamol. It supports batch filtering with parallelization and returns pandas DataFrames for rule and structural filters. The skill is designed for use in drug discovery workflows, including hit-to-lead and lead optimization.", "description_zh": "该技能提供用于化合物分类的药用化学过滤器。它应用类药性规则（Lipinski、Veber、CNS）、结构警报目录（PAINS、NIBR、ChEMBL）、复杂性指标以及药用化学查询语言进行库过滤。该技能基于medchem Python库（版本2.0.5），需要Python 3.9+和datamol。它支持并行批量过滤，并为规则和结构过滤器返回pandas DataFrame。该技能旨在用于药物发现工作流程，包括命中到先导和先导优化。", "provider_name": "K-Dense-AI", "homepage_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/medchem", "endpoint_url": null, "source_url": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/medchem/SKILL.md", "icon_url": null, "cover_image_url": null, "capabilities": [ "data.analyze", "data.filter", "science.chemistry", "software.execute" ], "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/medchem/SKILL.md", "commit": "1e5eeffbdad3749125afe7ab48a39694e27f181c", "stars": 42124, "forks": 3870, "updated_at": "2026-09-03T02:47:03Z" }, "skill": { "compatibility": "Requires Python 3.9+ and datamol (installed with medchem). Optional Lilly demerit filter requires separate `lilly-medchem-rules` conda package.", "allowed_tools": "Read Write Edit Bash", "content_hash": "2386610565d2758918e64b0b4821598a4f63fa4e4e6daac7af770a26a0a20480", "line_count": 339 }, "review_gate": { "passed": true, "reasons": [], "policy_version": "review-gate-v1", "evaluated_at": "2026-09-03T06:10:39.260Z" } }, "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.", "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": "ready_for_guidance", "reviewed_at": "2026-09-03T06:10:40.289Z" }, "experience_count": 0, "verified_experience_count": 0, "usage_count": 0, "success_rate": null, "first_seen_at": "2026-09-03T02:50:42.256Z", "last_seen_at": "2026-09-03T06:10:39.487Z", "published_at": "2026-09-03T06:10:39.487Z", "created_at": "2026-09-03T02:50:42.256Z", "updated_at": "2026-09-03T06:10:40.289Z", "api_url": "https://aiworkshub.io/api/v1/resources/RES_609E6BF69428", "reviews_url": "https://aiworkshub.io/api/v1/resources/RES_609E6BF69428/reviews", "public_url": "https://aiworkshub.io/resources/RES_609E6BF69428", "distribution": { "canonical_identity": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/medchem", "syndicatable": true, "origins": [ { "registry_url": "https://github.com/", "upstream_resource_id": "K-Dense-AI/scientific-agent-skills:skills/medchem/SKILL.md", "upstream_record_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/medchem", "relation": "syndicated", "metadata": { "source": "github-skill-import" }, "first_seen_at": "2026-09-03T02:50:42.256Z", "last_seen_at": "2026-09-03T06:10:39.487Z" } ] }, "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": "ready_for_guidance" }, "profile": { "capabilities": [ { "id": "data.analyze", "weight": 90, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "data.filter", "weight": 90, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "science.chemistry", "weight": 90, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "software.execute", "weight": 70, "confidence": 80, "evidence_ids": [ "source-inspection" ] } ], "domains": [ { "id": "health", "weight": 90, "confidence": 90, "evidence_ids": [ "source-record" ] }, { "id": "research", "weight": 90, "confidence": 90, "evidence_ids": [ "source-record" ] } ], "workflow_roles": [ "analyze", "execute" ] }, "capability_units": [ { "id": "skill:medchem", "kind": "skill_action", "capability_id": "data.analyze", "effect": "compute", "open_world": false, "idempotency": "idempotent", "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": { "type": "none", "required": false }, "runtime_pricing": { "model": "free" }, "dependencies": [ "Python 3.9+", "datamol", "RDKit", "medchem 2.0.5", "optional: lilly-medchem-rules" ] }, "operational_flags": [], "trust": { "signal": "none", "evidence_ids": [], "reason": "No suspicious or malicious evidence." }, "fit": { "good_for": [ "Applying drug-likeness rules (Lipinski, Veber, CNS) to compound libraries", "Filtering molecules by structural alerts (PAINS, NIBR, ChEMBL)", "Prioritizing compounds for hit-to-lead or lead optimization", "Calculating complexity metrics against ZINC-derived thresholds", "Detecting functional groups or named substructure catalogs", "Building multi-criteria filters with the medchem query language" ], "not_for": [ "Predicting biological activity or toxicity", "Replacing domain expertise in medicinal chemistry decisions", "Handling molecules outside the scope of the implemented rules" ] }, "evidence": [ { "id": "source-record", "type": "source_record", "source": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/medchem/SKILL.md", "observation": "Submitted Skill record for medchem; 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/medchem/SKILL.md", "observation": "The Skill source was fetched and inspected (11717 bytes; SHA-256 2386610565d2758918e64b0b4821598a4f63fa4e4e6daac7af770a26a0a20480).", "observed_at": "2026-09-03T06:10:31.203Z", "payload": {} } ], "unknowns": [ "Real-world usage and performance in production environments", "Compatibility with all molecular file formats beyond those mentioned", "Exact behavior of optional Lilly demerit filter without installation", "Potential performance limitations on very large compound libraries" ], "id": "REV_1E1B3154E4CA", "resource_id": "RES_609E6BF69428", "evaluator_type": "platform_ai", "provider": "deepseek", "model": "deepseek-v4-flash", "review_scope": "source-inspected-skill", "created_at": "2026-09-03T06:10:40.289Z" } } }