[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAMJZAA7KJ7J868GSX6T88":3,"skill-same:01M6DAMJZAA7KJ7J868GSX6T88":59},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":14,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":44,"install":45,"resources":58},"01M6DAMJZAA7KJ7J868GSX6T88","tooluniverse-cancer-classification",null,"Translate free-text tumor descriptions to OncoTree codes, look up cancer subtypes and tissue hierarchies, resolve UMLS\u002FNCI cross-references, and obtain OncoKB-compatible tumor type codes for variant annotation. Use when asked to find the OncoTree code for a tumor type, enumerate subtypes of a cancer, list cancers by tissue of origin, or standardize tumor nomenclature for downstream precision oncology analysis.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-cancer-classification\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"classification","tooluniverse cancer classification","translate","code","analysis","text","find","list","use","up","look","references","origin","type","free","2026-11-10 10:12:30",false,"---\nname: tooluniverse-cancer-classification\ndescription: >\n  Translate free-text tumor descriptions to OncoTree codes, look up cancer subtypes and tissue\n  hierarchies, resolve UMLS\u002FNCI cross-references, and obtain OncoKB-compatible tumor type codes\n  for variant annotation. Use when asked to find the OncoTree code for a tumor type, enumerate\n  subtypes of a cancer, list cancers by tissue of origin, or standardize tumor nomenclature for\n  downstream precision oncology analysis.\n---\n\n# Cancer Classification via OncoTree\n\nStandardize cancer type nomenclature using the OncoTree ontology. Resolves free-text tumor\ndescriptions to structured codes with UMLS\u002FNCI cross-references, enabling downstream use in\nOncoKB variant annotation and GDC cohort selection.\n\n## When to Use\n\nApply when researcher asks about:\n- \"What is the OncoTree code for [tumor description]?\"\n- \"Find all subtypes of [cancer type]\"\n- \"What cancers originate in [tissue]?\"\n- \"I need the tumor type code for OncoKB annotation\"\n- \"What is the TCGA\u002FCOSMIC code for [cancer]?\"\n- \"List all CNS\u002FBrain cancer subtypes\"\n- \"What NCI code corresponds to glioblastoma?\"\n\n## Key Tools\n\n| Tool | Purpose | Key Params |\n|------|---------|-----------|\n| `OncoTree_search` | Free-text search for cancer types | `query` (tumor name or description) |\n| `OncoTree_get_type` | Full details for a known OncoTree code | `code` (e.g., \"LUAD\", \"AML\") |\n| `OncoTree_list_tissues` | List all 32 tissue categories | (no params) |\n| `OncoKB_annotate_variant` | Variant annotation using OncoTree code | `gene`, `variant`, `tumor_type` |\n| `GDC_get_mutation_frequency` | Pan-cancer mutation frequency (TCGA) | `gene_symbol` |\n\n## Workflow\n\n### Phase 1: Cancer Type Discovery\n\nStart with free-text search to find matching OncoTree codes:\n\n```\nOncoTree_search(query=\"breast cancer\")\n-> Returns list: code, name, main_type, tissue, parent, level, external_references\n```\n\nKey response fields:\n- `code`: OncoTree code (e.g., \"BRCA\", \"IBC\") — use this in OncoKB calls\n- `level`: hierarchy depth (1=tissue, 2=main type, 3-5=subtypes)\n- `parent`: parent node code for navigating the hierarchy\n- `external_references.UMLS`: UMLS CUI list\n- `external_references.NCI`: NCI thesaurus code list\n\nSearch tips:\n- Broad terms (\"lung cancer\") return many results; narrow by tissue or level\n- Use tissue-specific terms (\"invasive breast carcinoma\") for precise matching\n- Acronyms work: query=\"GBM\" finds glioblastoma, query=\"AML\" finds leukemia types\n\n### Phase 2: Code Validation and Detail Retrieval\n\nOnce you have a candidate code, retrieve full details:\n\n```\nOncoTree_get_type(code=\"LUAD\")\n-> Returns: name, main_type, tissue, color, parent, level, history, external_references\n```\n\nNote: Not all codes are valid. \"GBM\" returns 404 — correct code is \"GB\" (Glioblastoma, IDH-Wildtype).\nAlways validate via `OncoTree_get_type` before using in downstream tools.\n\n### Phase 3: Tissue-Level Exploration\n\nWhen the user wants all cancers in a tissue category:\n\n```\nOncoTree_list_tissues()\n-> Returns 32 tissue names: \"Breast\", \"CNS\u002FBrain\", \"Lung\", \"Myeloid\", ...\n\nOncoTree_search(query=\"CNS\u002FBrain\")\n-> All cancer types with tissue=\"CNS\u002FBrain\"\n```\n\n### Phase 4: Downstream Use in Variant Annotation\n\nPass validated OncoTree code to OncoKB for cancer-type-specific therapeutic levels:\n\n```\nOncoKB_annotate_variant(gene=\"EGFR\", variant=\"L858R\", tumor_type=\"LUAD\")\n-> highestSensitiveLevel: \"1\" (FDA-approved therapy for this tumor+variant)\n```\n\nWithout `tumor_type`, OncoKB returns pan-cancer levels which may be less specific.\n\n## Tool Parameter Reference\n\n| Tool | Required | Optional | Notes |\n|------|---------|---------|-------|\n| `OncoTree_search` | `query` | — | Free text; returns list sorted by relevance |\n| `OncoTree_get_type` | `code` | — | Case-sensitive; \"BRCA\" not \"brca\". Returns 404 for invalid codes |\n| `OncoTree_list_tissues` | — | — | No params; returns list of 32 tissue strings |\n| `OncoKB_annotate_variant` | `gene`, `variant` | `tumor_type` | `tumor_type` is OncoTree code; omit for pan-cancer |\n| `GDC_get_mutation_frequency` | `gene_symbol` | — | Pan-cancer TCGA only; no per-subtype breakdown |\n\n## Common OncoTree Codes (verified working)\n\n| Code | Name | Tissue |\n|------|------|--------|\n| `BRCA` | Invasive Breast Carcinoma | Breast |\n| `LUAD` | Lung Adenocarcinoma | Lung |\n| `LUSC` | Lung Squamous Cell Carcinoma | Lung |\n| `MEL` | Melanoma | Skin |\n| `CRC` | Colorectal Cancer | Bowel |\n| `PAAD` | Pancreatic Adenocarcinoma | Pancreas |\n| `GBM` | (invalid — use `GB`) | CNS\u002FBrain |\n| `GB` | Glioblastoma, IDH-Wildtype | CNS\u002FBrain |\n| `AML` | Acute Myeloid Leukemia | Myeloid |\n| `PRAD` | Prostate Adenocarcinoma | Prostate |\n\n## Common Patterns\n\n```python\n# Pattern: Resolve free-text to OncoTree code\nresults = OncoTree_search(query=\"pancreatic ductal adenocarcinoma\")\n# Pick result with lowest level number (most specific match)\ncode = results[\"data\"][0][\"code\"]  # e.g., \"PAAD\"\n\n# Pattern: Get all subtypes within a main type\nresults = OncoTree_search(query=\"Glioma\")\nsubtypes = [r for r in results[\"data\"] if r[\"main_type\"] == \"Glioma\"]\n\n# Pattern: Validate code before OncoKB call\ndetail = OncoTree_get_type(code=\"GB\")\nif detail[\"status\"] == \"success\":\n    OncoKB_annotate_variant(gene=\"IDH1\", variant=\"R132H\", tumor_type=\"GB\")\n```\n\n## Tumor Classification Reasoning (CRITICAL)\n\n**LOOK UP DON'T GUESS** -- tumor classification determines treatment. Always verify codes and biomarker interpretation via tools rather than relying on memory.\n\n### Histological vs Molecular Classification\n\nTumors are classified on TWO axes -- both matter for treatment selection:\n- **Histological** (what it looks like under microscope): adenocarcinoma, squamous, small cell, etc. This determines the OncoTree hierarchy level 3+.\n- **Molecular** (what mutations\u002Falterations drive it): EGFR-mutant, HER2-amplified, MSI-high, etc. This determines OncoKB therapeutic levels.\n\nA tumor can be histologically identical to another but molecularly different, requiring different treatment. Example: two lung adenocarcinomas (both LUAD) but one is EGFR-mutant (targeted therapy) and another is KRAS-mutant (different targeted therapy). **Always check both axes.**\n\n### Biomarker Interpretation Strategy\n\nWhen interpreting cancer biomarkers, use OncoKB for actionability:\n- **HER2**: Positive = IHC 3+ or FISH-amplified. Use `OncoKB_annotate_variant(gene=\"ERBB2\", variant=\"Amplification\", tumor_type=\"BRCA\")` for therapeutic level\n- **ER\u002FPR**: Positive = hormone-receptor positive breast cancer. Changes treatment class (endocrine therapy)\n- **Ki67**: Proliferation index. High (>20%) suggests aggressive biology; used in breast cancer grading (Luminal A vs B)\n- **TMB (Tumor Mutational Burden)**: High TMB (>10 mut\u002FMb) predicts immunotherapy response across tumor types. Use `OncoKB_annotate_variant(gene=\"Other Biomarkers\", variant=\"TMB-H\")`\n- **MSI (Microsatellite Instability)**: MSI-High is FDA-approved biomarker for pembrolizumab pan-cancer. Use `OncoKB_annotate_variant(gene=\"Other Biomarkers\", variant=\"MSI-H\")`\n\n### Staging vs Grading -- Different Concepts\n\n- **Stage** (TNM): How far has it spread? T=tumor size, N=lymph nodes, M=metastasis. Stage I-IV. Determines prognosis and surgery eligibility.\n- **Grade**: How abnormal do the cells look? Grade 1 (well-differentiated, slow) to Grade 3 (poorly-differentiated, aggressive). Determines aggressiveness.\n- A Stage I, Grade 3 tumor (small but aggressive) has different implications than Stage III, Grade 1 (spread but slow-growing).\n\n### Actionability Assessment\n\nAfter classifying the tumor, assess whether findings are clinically actionable:\n1. **Level 1** (FDA-approved, specific tumor type): Immediate treatment implication. Example: EGFR L858R in LUAD\n2. **Level 2** (Standard care): Strong evidence but context-dependent\n3. **Level 3** (Compelling evidence): Clinical trial candidates\n4. **Level 4** (Biological evidence): Research-stage only\n5. Always provide the OncoTree code to OncoKB -- without it, you get pan-cancer levels which may understate or overstate actionability for the specific tumor type\n\n## Reasoning Framework for Result Interpretation\n\n### Evidence Grading\n\n| Grade | Criteria | Example |\n|-------|----------|---------|\n| **Confirmed** | Exact OncoTree code validated via `OncoTree_get_type`, UMLS + NCI cross-refs present | LUAD: validated, UMLS C0152013, NCI C3512 |\n| **Probable** | OncoTree search returns match, but code not yet validated or missing cross-refs | Search for \"cholangiocarcinoma\" returns CHOL with partial external refs |\n| **Ambiguous** | Multiple OncoTree codes match the description at different hierarchy levels | \"Breast cancer\" matches BRCA (invasive), BREAST (tissue), IBC (inflammatory) |\n| **Unresolved** | No OncoTree match; tumor type too rare or novel for the ontology | Ultra-rare sarcoma subtype not in OncoTree |\n\n### Interpretation Guidance\n\n- **OncoTree code confidence**: Always validate candidate codes with `OncoTree_get_type` before downstream use. Some common acronyms (e.g., \"GBM\") are NOT valid OncoTree codes (correct code is \"GB\"). A validated code with UMLS and NCI cross-references is highest confidence.\n- **UMLS\u002FNCI cross-reference priority**: For standardized reporting, NCI Thesaurus codes are preferred for cancer-specific contexts (used by caDSR, GDC). UMLS CUIs are broader (cross-disease) and useful for literature mining. When both are available, report both; when only one exists, NCI is preferred for oncology workflows.\n- **Tissue hierarchy interpretation**: OncoTree levels represent specificity: Level 1 = tissue of origin (e.g., \"Lung\"), Level 2 = main cancer type (e.g., \"Non-Small Cell Lung Cancer\"), Level 3+ = histological subtypes (e.g., \"Lung Adenocarcinoma\"). For OncoKB variant annotation, use the most specific (deepest) level that accurately describes the tumor. For cohort-level analysis (e.g., TCGA), the Level 2-3 code is typically appropriate.\n- **OncoKB tumor type impact**: Providing a tumor type code to OncoKB can change the therapeutic level (e.g., EGFR L858R is Level 1 in LUAD but Level 3B pan-cancer). Always use the validated OncoTree code for the patient's specific tumor type.\n- **Deprecated or renamed codes**: OncoTree evolves across versions. The `history` field in `OncoTree_get_type` response shows prior names. Always use the current code.\n\n### Synthesis Questions\n\n1. Does the chosen OncoTree code represent the most specific histological subtype, or could a more precise code provide better therapeutic annotation in OncoKB?\n2. When the free-text tumor description maps to multiple OncoTree codes, which hierarchy level best balances specificity and coverage for the analysis goal (variant annotation vs cohort selection)?\n3. Are the UMLS\u002FNCI cross-references consistent with external classifications (WHO, ICD-O), or are there discrepancies that need resolution?\n\n---\n\n## Fallback Chains\n\n| Primary | Fallback | When |\n|---------|---------|------|\n| `OncoTree_get_type(code=\"GBM\")` | `OncoTree_search(query=\"glioblastoma\")` | 404 for common aliases |\n| `OncoTree_search` (no results) | `OncoTree_list_tissues` + tissue-level search | Very rare\u002Fnovel tumor types |\n| OncoTree code for OncoKB | Omit `tumor_type` param | Code not recognized by OncoKB |\n","# Cancer Classification via OncoTree\n\nStandardize cancer type nomenclature using the OncoTree ontology. Resolves free-text tumor\ndescriptions to structured codes with UMLS\u002FNCI cross-references, enabling downstream use in\nOncoKB variant annotation and GDC cohort selection.\n\n## When to Use\n\nApply when researcher asks about:\n- \"What is the OncoTree code for [tumor description]?\"\n- \"Find all subtypes of [cancer type]\"\n- \"What cancers originate in [tissue]?\"\n- \"I need the tumor type code for OncoKB annotation\"\n- \"What is the TCGA\u002FCOSMIC code for [cancer]?\"\n- \"List all CNS\u002FBrain cancer subtypes\"\n- \"What NCI code corresponds to glioblastoma?\"\n\n## Key Tools\n\n| Tool | Purpose | Key Params |\n|------|---------|-----------|\n| `OncoTree_search` | Free-text search for cancer types | `query` (tumor name or description) |\n| `OncoTree_get_type` | Full details for a known OncoTree code | `code` (e.g., \"LUAD\", \"AML\") |\n| `OncoTree_list_tissues` | List all 32 tissue categories | (no params) |\n| `OncoKB_annotate_variant` | Variant annotation using OncoTree code | `gene`, `variant`, `tumor_type` |\n| `GDC_get_mutation_frequency` | Pan-cancer mutation frequency (TCGA) | `gene_symbol` |\n\n## Workflow\n\n### Phase 1: Cancer Type Discovery\n\nStart with free-text search to find matching OncoTree codes:\n\n```\nOncoTree_search(query=\"breast cancer\")\n-> Returns list: code, name, main_type, tissue, parent, level, external_references\n```\n\nKey response fields:\n- `code`: OncoTree code (e.g., \"BRCA\", \"IBC\") — use this in OncoKB calls\n- `level`: hierarchy depth (1=tissue, 2=main type, 3-5=subtypes)\n- `parent`: parent node code for navigating the hierarchy\n- `external_references.UMLS`: UMLS CUI list\n- `external_references.NCI`: NCI thesaurus code list\n\nSearch tips:\n- Broad terms (\"lung cancer\") return many results; narrow by tissue or level\n- Use tissue-specific terms (\"invasive breast carcinoma\") for precise matching\n- Acronyms work: query=\"GBM\" finds glioblastoma, query=\"AML\" finds leukemia types\n\n### Phase 2: Code Validation and Detail Retrieval\n\nOnce you have a candidate code, retrieve full details:\n\n```\nOncoTree_get_type(code=\"LUAD\")\n-> Returns: name, main_type, tissue, color, parent, level, history, external_references\n```\n\nNote: Not all codes are valid. \"GBM\" returns 404 — correct code is \"GB\" (Glioblastoma, IDH-Wildtype).\nAlways validate via `OncoTree_get_type` before using in downstream tools.\n\n### Phase 3: Tissue-Level Exploration\n\nWhen the user wants all cancers in a tissue category:\n\n```\nOncoTree_list_tissues()\n-> Returns 32 tissue names: \"Breast\", \"CNS\u002FBrain\", \"Lung\", \"Myeloid\", ...\n\nOncoTree_search(query=\"CNS\u002FBrain\")\n-> All cancer types with tissue=\"CNS\u002FBrain\"\n```\n\n### Phase 4: Downstream Use in Variant Annotation\n\nPass validated OncoTree code to OncoKB for cancer-type-specific therapeutic levels:\n\n```\nOncoKB_annotate_variant(gene=\"EGFR\", variant=\"L858R\", tumor_type=\"LUAD\")\n-> highestSensitiveLevel: \"1\" (FDA-approved therapy for this tumor+variant)\n```\n\nWithout `tumor_type`, OncoKB returns pan-cancer levels which may be less specific.\n\n## Tool Parameter Reference\n\n| Tool | Required | Optional | Notes |\n|------|---------|---------|-------|\n| `OncoTree_search` | `query` | — | Free text; returns list sorted by relevance |\n| `OncoTree_get_type` | `code` | — | Case-sensitive; \"BRCA\" not \"brca\". Returns 404 for invalid codes |\n| `OncoTree_list_tissues` | — | — | No params; returns list of 32 tissue strings |\n| `OncoKB_annotate_variant` | `gene`, `variant` | `tumor_type` | `tumor_type` is OncoTree code; omit for pan-cancer |\n| `GDC_get_mutation_frequency` | `gene_symbol` | — | Pan-cancer TCGA only; no per-subtype breakdown |\n\n## Common OncoTree Codes (verified working)\n\n| Code | Name | Tissue |\n|------|------|--------|\n| `BRCA` | Invasive Breast Carcinoma | Breast |\n| `LUAD` | Lung Adenocarcinoma | Lung |\n| `LUSC` | Lung Squamous Cell Carcinoma | Lung |\n| `MEL` | Melanoma | Skin |\n| `CRC` | Colorectal Cancer | Bowel |\n| `PAAD` | Pancreatic Adenocarcinoma | Pancreas |\n| `GBM` | (invalid — use `GB`) | CNS\u002FBrain |\n| `GB` | Glioblastoma, IDH-Wildtype | CNS\u002FBrain |\n| `AML` | Acute Myeloid Leukemia | Myeloid |\n| `PRAD` | Prostate Adenocarcinoma | Prostate |\n\n## Common Patterns\n\n```python\n# Pattern: Resolve free-text to OncoTree code\nresults = OncoTree_search(query=\"pancreatic ductal adenocarcinoma\")\n# Pick result with lowest level number (most specific match)\ncode = results[\"data\"][0][\"code\"]  # e.g., \"PAAD\"\n\n# Pattern: Get all subtypes within a main type\nresults = OncoTree_search(query=\"Glioma\")\nsubtypes = [r for r in results[\"data\"] if r[\"main_type\"] == \"Glioma\"]\n\n# Pattern: Validate code before OncoKB call\ndetail = OncoTree_get_type(code=\"GB\")\nif detail[\"status\"] == \"success\":\n    OncoKB_annotate_variant(gene=\"IDH1\", variant=\"R132H\", tumor_type=\"GB\")\n```\n\n## Tumor Classification Reasoning (CRITICAL)\n\n**LOOK UP DON'T GUESS** -- tumor classification determines treatment. Always verify codes and biomarker interpretation via tools rather than relying on memory.\n\n### Histological vs Molecular Classification\n\nTumors are classified on TWO axes -- both matter for treatment selection:\n- **Histological** (what it looks like under microscope): adenocarcinoma, squamous, small cell, etc. This determines the OncoTree hierarchy level 3+.\n- **Molecular** (what mutations\u002Falterations drive it): EGFR-mutant, HER2-amplified, MSI-high, etc. This determines OncoKB therapeutic levels.\n\nA tumor can be histologically identical to another but molecularly different, requiring different treatment. Example: two lung adenocarcinomas (both LUAD) but one is EGFR-mutant (targeted therapy) and another is KRAS-mutant (different targeted therapy). **Always check both axes.**\n\n### Biomarker Interpretation Strategy\n\nWhen interpreting cancer biomarkers, use OncoKB for actionability:\n- **HER2**: Positive = IHC 3+ or FISH-amplified. Use `OncoKB_annotate_variant(gene=\"ERBB2\", variant=\"Amplification\", tumor_type=\"BRCA\")` for therapeutic level\n- **ER\u002FPR**: Positive = hormone-receptor positive breast cancer. Changes treatment class (endocrine therapy)\n- **Ki67**: Proliferation index. High (>20%) suggests aggressive biology; used in breast cancer grading (Luminal A vs B)\n- **TMB (Tumor Mutational Burden)**: High TMB (>10 mut\u002FMb) predicts immunotherapy response across tumor types. Use `OncoKB_annotate_variant(gene=\"Other Biomarkers\", variant=\"TMB-H\")`\n- **MSI (Microsatellite Instability)**: MSI-High is FDA-approved biomarker for pembrolizumab pan-cancer. Use `OncoKB_annotate_variant(gene=\"Other Biomarkers\", variant=\"MSI-H\")`\n\n### Staging vs Grading -- Different Concepts\n\n- **Stage** (TNM): How far has it spread? T=tumor size, N=lymph nodes, M=metastasis. Stage I-IV. Determines prognosis and surgery eligibility.\n- **Grade**: How abnormal do the cells look? Grade 1 (well-differentiated, slow) to Grade 3 (poorly-differentiated, aggressive). Determines aggressiveness.\n- A Stage I, Grade 3 tumor (small but aggressive) has different implications than Stage III, Grade 1 (spread but slow-growing).\n\n### Actionability Assessment\n\nAfter classifying the tumor, assess whether findings are clinically actionable:\n1. **Level 1** (FDA-approved, specific tumor type): Immediate treatment implication. Example: EGFR L858R in LUAD\n2. **Level 2** (Standard care): Strong evidence but context-dependent\n3. **Level 3** (Compelling evidence): Clinical trial candidates\n4. **Level 4** (Biological evidence): Research-stage only\n5. Always provide the OncoTree code to OncoKB -- without it, you get pan-cancer levels which may understate or overstate actionability for the specific tumor type\n\n## Reasoning Framework for Result Interpretation\n\n### Evidence Grading\n\n| Grade | Criteria | Example |\n|-------|----------|---------|\n| **Confirmed** | Exact OncoTree code validated via `OncoTree_get_type`, UMLS + NCI cross-refs present | LUAD: validated, UMLS C0152013, NCI C3512 |\n| **Probable** | OncoTree search returns match, but code not yet validated or missing cross-refs | Search for \"cholangiocarcinoma\" returns CHOL with partial external refs |\n| **Ambiguous** | Multiple OncoTree codes match the description at different hierarchy levels | \"Breast cancer\" matches BRCA (invasive), BREAST (tissue), IBC (inflammatory) |\n| **Unresolved** | No OncoTree match; tumor type too rare or novel for the ontology | Ultra-rare sarcoma subtype not in OncoTree |\n\n### Interpretation Guidance\n\n- **OncoTree code confidence**: Always validate candidate codes with `OncoTree_get_type` before downstream use. Some common acronyms (e.g., \"GBM\") are NOT valid OncoTree codes (correct code is \"GB\"). A validated code with UMLS and NCI cross-references is highest confidence.\n- **UMLS\u002FNCI cross-reference priority**: For standardized reporting, NCI Thesaurus codes are preferred for cancer-specific contexts (used by caDSR, GDC). UMLS CUIs are broader (cross-disease) and useful for literature mining. When both are available, report both; when only one exists, NCI is preferred for oncology workflows.\n- **Tissue hierarchy interpretation**: OncoTree levels represent specificity: Level 1 = tissue of origin (e.g., \"Lung\"), Level 2 = main cancer type (e.g., \"Non-Small Cell Lung Cancer\"), Level 3+ = histological subtypes (e.g., \"Lung Adenocarcinoma\"). For OncoKB variant annotation, use the most specific (deepest) level that accurately describes the tumor. For cohort-level analysis (e.g., TCGA), the Level 2-3 code is typically appropriate.\n- **OncoKB tumor type impact**: Providing a tumor type code to OncoKB can change the therapeutic level (e.g., EGFR L858R is Level 1 in LUAD but Level 3B pan-cancer). Always use the validated OncoTree code for the patient's specific tumor type.\n- **Deprecated or renamed codes**: OncoTree evolves across versions. The `history` field in `OncoTree_get_type` response shows prior names. Always use the current code.\n\n### Synthesis Questions\n\n1. Does the chosen OncoTree code represent the most specific histological subtype, or could a more precise code provide better therapeutic annotation in OncoKB?\n2. When the free-text tumor description maps to multiple OncoTree codes, which hierarchy level best balances specificity and coverage for the analysis goal (variant annotation vs cohort selection)?\n3. Are the UMLS\u002FNCI cross-references consistent with external classifications (WHO, ICD-O), or are there discrepancies that need resolution?\n\n---\n\n## Fallback Chains\n\n| Primary | Fallback | When |\n|---------|---------|------|\n| `OncoTree_get_type(code=\"GBM\")` | `OncoTree_search(query=\"glioblastoma\")` | 404 for common aliases |\n| `OncoTree_search` (no results) | `OncoTree_list_tissues` + tissue-level search | Very rare\u002Fnovel tumor types |\n| OncoTree code for OncoKB | Omit `tumor_type` param | Code not recognized by OncoKB |\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-cancer-classification","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-cancer-classification",{"tool":51,"command":52},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-cancer-classification",{"tool":54,"command":55},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-cancer-classification","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-cancer-classification\u002FSKILL.md",true,[],[60,81,111,138,152,168],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":34},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[67,68,69,70,71,72,73,74,75,27,76,77,78,79,80],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":92,"publishedAt":34},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[87],{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[93,94,95,96,97,98,99,100,101,102,103,104,105,106,27,33,107,108,109,110],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","molecular dynamics","local","do","MCP",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":123,"publishedAt":34},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[117,120],{"categoryNo":118,"categoryName":119,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":121,"categoryName":122,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000008","测试与质量",[124,125,126,127,128,129,130,131,132,133,94,134,135,136,137],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":34},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[140,145,146,147,148,149,150,151],"setup","report","project","installation","project setup","issues","state",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":159,"publishedAt":34},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[158],{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},[154,160,72,161,162,163,27,164,165,166,167],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":169,"name":145,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":34},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[145,147,108,174,149,175],"files","interactive"]