[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAWTJ27AQQH8SWYJ6R2V30":3,"skill-same:01M6DAWTJ27AQQH8SWYJ6R2V30":57},{"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":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":14,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":42,"install":43,"resources":56},"01M6DAWTJ27AQQH8SWYJ6R2V30","tooluniverse-regulatory-genomics",null,"Investigate transcription factor binding, cis-regulatory elements, chromatin accessibility, and regulatory variant annotation. Use when asked about TF binding sites, enhancers, promoters, ChIP-seq data, ATAC-seq signals, candidate cis-regulatory elements (cCREs), or the regulatory impact of genomic variants.","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-regulatory-genomics\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31],"regulatory","genomics","tooluniverse regulatory genomics","accessibility","data","investigate","use","cis","transcription","signals","elements","atac","factor","2026-11-10 10:12:30",false,"---\nname: tooluniverse-regulatory-genomics\ndescription: >\n  Investigate transcription factor binding, cis-regulatory elements, chromatin\n  accessibility, and regulatory variant annotation. Use when asked about TF binding\n  sites, enhancers, promoters, ChIP-seq data, ATAC-seq signals, candidate cis-regulatory\n  elements (cCREs), or the regulatory impact of genomic variants.\n---\n\n# Regulatory Genomics Research Skill\n\nSystematic investigation of gene regulation through transcription factor binding, chromatin state, and regulatory element annotation. Integrates JASPAR (TF motifs), ENCODE (functional genomics experiments), RegulomeDB (regulatory variant scoring), and UCSC cCREs.\n\n## Domain Reasoning\n\nRegulatory element identification requires converging lines of evidence: sequence conservation alone is insufficient (many conserved sequences are not regulatory), chromatin accessibility is necessary but not sufficient (open chromatin can be structural), TF binding peaks require motif validation, and eQTL evidence ties the element to a transcriptional outcome. No single data type is sufficient. A high-confidence regulatory element requires at least two independent evidence types, and ideally all four.\n\n## LOOK UP DON'T GUESS\n\n- TF binding motifs: retrieve from `jaspar_search_matrices` and `jaspar_get_matrix`; do not describe motifs from memory.\n- Experimental ChIP-seq data: search `ENCODE_search_experiments`; do not assume a TF has been profiled in a given cell type.\n- cCRE annotations for a genomic region: call `UCSC_get_encode_cCREs` with exact coordinates; do not guess element types.\n- Regulatory impact of a variant: query `RegulomeDB_query_variant`; never estimate regulatory importance from position alone.\n\n---\n\n**KEY PRINCIPLES**:\n1. **English-first queries** - Use English gene\u002FTF names in all tool calls; respond in user's language\n2. **Evidence layering** - Combine motif (JASPAR) + experimental (ENCODE ChIP-seq) + variant (RegulomeDB) evidence\n3. **Coordinate precision** - Genome coordinates must specify assembly (GRCh38 preferred)\n4. **Negative results documented** - Report when a TF has no ChIP-seq data in ENCODE\n\n---\n\n## COMPUTE, DON'T DESCRIBE\nWhen analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.\n\n## When to Use\n\n- \"What transcription factors bind near gene X?\"\n- \"Does this SNP affect a regulatory element?\"\n- \"Find CTCF binding sites in liver tissue\"\n- \"What are the enhancers active in this cell type?\"\n- \"Show me ChIP-seq experiments for H3K27ac in T cells\"\n- \"Is rs1234567 in a regulatory region?\"\n- \"What TF motifs overlap this genomic region?\"\n- \"Find ENCODE experiments for ATAC-seq in cancer cell lines\"\n\n---\n\n## Key Tools\n\n| Tool | Purpose | Key Params |\n|------|---------|-----------|\n| `jaspar_search_matrices` | Find TF binding motifs by TF name or organism | `name`, `species`, `collection`, `tax_id` |\n| `jaspar_get_matrix` | Get full PWM\u002FPFM for a specific JASPAR matrix | `matrix_id` (e.g., \"MA0139.1\") |\n| `JASPAR_get_transcription_factors` | List all TF matrices (paginated) | `page`, `page_size` |\n| `ENCODE_search_experiments` | Search ENCODE ChIP-seq\u002FATAC-seq\u002FWGBS experiments | `assay_title`, `target`, `biosample_term_name`, `limit` |\n| `ENCODE_search_histone_experiments` | Search histone mark ChIP-seq specifically | `histone_mark`, `biosample_term_name`, `limit` |\n| `ENCODE_search_chromatin_accessibility` | Search ATAC-seq\u002FDNase-seq experiments | `biosample_term_name`, `limit` |\n| `ENCODE_get_experiment` | Get full metadata for a specific ENCODE experiment | `accession` (e.g., \"ENCSR000EGM\") |\n| `ENCODE_search_annotations` | Search ENCODE cCRE and chromatin state annotations | `annotation_type`, `biosample_term_name`, `limit` |\n| `ENCODE_get_chromatin_state` | Search ChromHMM segmentation data | `biosample_term_name`, `limit` |\n| `UCSC_get_encode_cCREs` | Get cCREs overlapping a genomic region | `chrom`, `start`, `end` |\n| `RegulomeDB_query_variant` | Score regulatory impact of a variant | `rsid` (e.g., \"rs4994\") |\n| `ENCODE_search_biosamples` | Find available cell lines\u002Ftissues in ENCODE | `term_name`, `biosample_type`, `limit` |\n\n---\n\n## Workflow\n\n### Phase 1: TF Motif Discovery (JASPAR)\n\nWhen asked about TF binding motifs or what TFs might regulate a gene:\n\n```\n1. jaspar_search_matrices(name=\"TF_NAME\", species=\"Homo sapiens\")\n   -> Returns list of matrices with matrix_id, collection, version\n\n2. jaspar_get_matrix(matrix_id=\"MA0139.1\")\n   -> Returns full PFM\u002FPWM matrix, sequence logo URL, binding sites URL\n\n3. For broad TF family search:\n   jaspar_search_matrices(species=\"Homo sapiens\", collection=\"CORE\")\n   -> Filter by TF family name in results\n```\n\n**JASPAR Collections**:\n- `CORE`: High-quality, non-redundant matrices (best for most use cases)\n- `CNE`: Conserved non-coding elements\n- `POLII`: RNA Pol II binding sites\n\n**Key Response Fields**:\n- `matrix_id`: Versioned ID (e.g., \"MA0139.1\") — use for jaspar_get_matrix\n- `name`: TF gene symbol\n- `sequence_logo`: URL to binding site logo PNG\u002FSVG\n- `collection`: Which JASPAR collection\n\n### Phase 2: ENCODE Experiment Search\n\nWhen looking for ChIP-seq, ATAC-seq, or other functional genomics data:\n\n**For TF ChIP-seq**:\n```\nENCODE_search_experiments(\n    assay_title=\"TF ChIP-seq\",\n    target=\"CTCF\",              # TF gene name\n    biosample_term_name=\"HepG2\", # Cell line or tissue\n    limit=10\n)\n```\n\n**For histone marks**:\n```\nENCODE_search_histone_experiments(\n    histone_mark=\"H3K27ac\",         # or H3K4me3, H3K27me3, H3K36me3\n    biosample_term_name=\"liver\",\n    limit=10\n)\n```\n\n**For chromatin accessibility**:\n```\nENCODE_search_chromatin_accessibility(\n    biosample_term_name=\"T cell\",\n    limit=10\n)\n```\n\n**For regulatory annotations (cCREs, ChromHMM)**:\n```\nENCODE_search_annotations(\n    annotation_type=\"candidate Cis-Regulatory Elements\",\n    biosample_term_name=\"K562\",\n    limit=10\n)\n```\n\n**Common assay_title values**:\n- `\"TF ChIP-seq\"` - Transcription factor binding\n- `\"Histone ChIP-seq\"` - Histone modification\n- `\"ATAC-seq\"` - Chromatin accessibility\n- `\"DNase-seq\"` - Open chromatin (older method)\n- `\"WGBS\"` - DNA methylation\n\n**Note**: `ENCODE_search_experiments` returns experiment metadata only (accession, biosample, status). Use `ENCODE_get_experiment(accession)` to get file download links and detailed metadata.\n\n### Phase 3: cCRE Annotation (UCSC + ENCODE)\n\nWhen annotating a specific genomic region:\n\n```\nUCSC_get_encode_cCREs(\n    chrom=\"chr8\",       # Chromosome (GRCh38)\n    start=37966000,     # Start coordinate\n    end=37967000        # End coordinate\n)\n# Returns cCREs with type: pELS (proximal enhancer), dELS (distal enhancer),\n# PLS (promoter-like), CTCF-only, DNase-H3K4me3\n```\n\n**cCRE Types**:\n- **PLS** (Promoter-like): High DNase + H3K4me3 + H3K27ac signal near TSS\n- **pELS** (Proximal Enhancer): High DNase + H3K27ac, within 2kb of TSS\n- **dELS** (Distal Enhancer): High DNase + H3K27ac, >2kb from TSS\n- **CTCF-only**: CTCF binding without enhancer marks\n- **DNase-H3K4me3**: Unclassified accessible region\n\n### Phase 4: Regulatory Variant Scoring (RegulomeDB)\n\nWhen assessing regulatory impact of a variant:\n\n```\nRegulomeDB_query_variant(rsid=\"rs4994\")\n# Returns:\n#   regulome_score.ranking: \"1a\"-\"7\" (1a = highest regulatory evidence)\n#   regulome_score.probability: 0-1 continuous score\n#   tissue_specific_scores: dict of tissue -> score\n#   overlapping features: eQTLs, TF binding, DNase peaks, motifs\n```\n\n**RegulomeDB Score Interpretation**:\n| Rank | Meaning |\n|------|---------|\n| 1a | eQTL + TF binding + matched TF motif + DNase peak |\n| 1b | eQTL + TF binding + DNase peak |\n| 1c | eQTL + TF binding or DNase peak |\n| 1d | eQTL + motif or protein binding |\n| 1e | eQTL + motif hit |\n| 1f | eQTL only |\n| 2a | TF binding + motif match + DNase |\n| 2b | TF binding + matched motif |\n| 2c | TF binding with\u002Fwithout motif |\n| 3a | DNase peak + motif |\n| 3b | DNase peak only |\n| 4 | Motif hit only |\n| 5 | Proximity to Footprint |\n| 6 | Proximity to Footprint + TF |\n| 7 | No evidence |\n\nVariants with rank 1a-2b are most likely to affect gene regulation.\n\n---\n\n## Tool Parameter Reference\n\n| Tool | Required Params | Optional Params | Notes |\n|------|----------------|-----------------|-------|\n| `jaspar_search_matrices` | (none — returns all if empty) | `name`, `species`, `collection`, `tax_id`, `page`, `page_size` | Use `name` for TF name search |\n| `jaspar_get_matrix` | `matrix_id` | — | Full version required: \"MA0139.1\" not \"MA0139\" |\n| `JASPAR_get_transcription_factors` | (none) | `page`, `page_size` | Paginated; default page_size=10 |\n| `jaspar_get_matrix_versions` | `base_id` | — | base_id is unversioned (e.g., \"MA0139\") |\n| `ENCODE_search_experiments` | (none — returns all if empty) | `assay_title`, `target`, `biosample_term_name`, `limit` | assay_title must match ENCODE vocabulary exactly |\n| `ENCODE_search_histone_experiments` | (none) | `histone_mark`, `biosample_term_name`, `limit` | histone_mark: \"H3K27ac\", \"H3K4me3\", etc. |\n| `ENCODE_search_chromatin_accessibility` | (none) | `biosample_term_name`, `limit` | Returns ATAC-seq and DNase-seq |\n| `ENCODE_get_experiment` | `accession` | — | accession: \"ENCSR...\" format |\n| `ENCODE_search_annotations` | (none) | `annotation_type`, `biosample_term_name`, `limit` | annotation_type: \"candidate Cis-Regulatory Elements\" |\n| `ENCODE_get_chromatin_state` | (none) | `biosample_term_name`, `limit` | Returns ChromHMM segmentation |\n| `ENCODE_search_biosamples` | (none) | `term_name`, `biosample_type`, `limit` | biosample_type: \"cell line\", \"tissue\", \"primary cell\" |\n| `UCSC_get_encode_cCREs` | `chrom`, `start`, `end` | — | Coordinates in GRCh38; chrom format: \"chr1\" |\n| `RegulomeDB_query_variant` | `rsid` | — | rsid format: \"rs4994\" (with rs prefix) |\n\n---\n\n## Common Patterns\n\n### Pattern 1: TF Binding Site Investigation\n```\nGoal: Find where TF X binds and what motif it recognizes\nFlow:\n  1. jaspar_search_matrices(name=\"CTCF\") -> get matrix_id\n  2. jaspar_get_matrix(matrix_id) -> get full PWM, logo URL\n  3. ENCODE_search_experiments(assay_title=\"TF ChIP-seq\", target=\"CTCF\") -> experimental binding data\n  4. For specific tissue: add biosample_term_name=\"HepG2\"\nOutput: Motif logo + experimental binding evidence\n```\n\n### Pattern 2: Regulatory Variant Interpretation\n```\nGoal: Assess if variant rs1234567 affects gene regulation\nFlow:\n  1. RegulomeDB_query_variant(rsid=\"rs1234567\") -> score + overlapping features\n  2. If score \u003C= 2b: ENCODE_search_experiments(target=overlapping_TF) -> experimental evidence\n  3. UCSC_get_encode_cCREs(chrom, start, end) -> check if variant in known cCRE\nOutput: Regulatory score + supporting evidence + cCRE context\n```\n\n### Pattern 3: Cell-Type Regulatory Landscape\n```\nGoal: Characterize active enhancers in a cell type\nFlow:\n  1. ENCODE_search_histone_experiments(histone_mark=\"H3K27ac\", biosample_term_name=\"K562\") -> active enhancers\n  2. ENCODE_search_chromatin_accessibility(biosample_term_name=\"K562\") -> open chromatin\n  3. ENCODE_search_annotations(annotation_type=\"candidate Cis-Regulatory Elements\", biosample_term_name=\"K562\")\n  4. ENCODE_get_chromatin_state(biosample_term_name=\"K562\") -> ChromHMM states\nOutput: Active regulatory elements specific to the cell type\n```\n\n### Pattern 4: Gene Regulatory Region Mapping\n```\nGoal: Find all regulatory elements near a gene\nFlow:\n  1. Get gene coordinates from MyGene_query_genes or ensembl_lookup_gene\n  2. UCSC_get_encode_cCREs(chrom, start-50000, end+50000) -> nearby cCREs\n  3. ENCODE_search_experiments(target=TF_OF_INTEREST) -> TF binding data\n  4. jaspar_search_matrices(name=TF_NAME) -> motif for TF\nOutput: Map of regulatory elements around gene with evidence types\n```\n\n---\n\n## Fallback Strategies\n\n| Primary Tool | Fallback | When |\n|-------------|----------|------|\n| `ENCODE_search_experiments` with specific biosample | Remove `biosample_term_name` filter | No results for specific tissue |\n| `jaspar_search_matrices(name=TF)` | `jaspar_search_matrices(name=TF_family)` | TF not found by exact name |\n| `UCSC_get_encode_cCREs` | `ENCODE_search_annotations` without coordinates | If coordinates unknown |\n| `RegulomeDB_query_variant(rsid)` | Use `ENCODE_search_experiments` + `JASPAR` to manually assess overlap | rsid not in RegulomeDB |\n\n---\n\n## Limitations\n\n- **ENCODE TF ChIP-seq**: `assay_title=\"TF ChIP-seq\"` uses ENCODE's exact controlled vocabulary — avoid \"ChIP-seq\" (too general)\n- **UCSC cCREs**: Coordinates must be in GRCh38 (hg38); liftOver required for hg19 variants\n- **RegulomeDB**: Only scores variants with known rsIDs; novel variants not supported\n- **JASPAR**: Provides motif databases only — not genomic binding locations; combine with ENCODE for experimental evidence\n- **ENCODE experiment results**: The `@graph` field may be empty if query filters are too restrictive; relax filters and retry\n","# Regulatory Genomics Research Skill\n\nSystematic investigation of gene regulation through transcription factor binding, chromatin state, and regulatory element annotation. Integrates JASPAR (TF motifs), ENCODE (functional genomics experiments), RegulomeDB (regulatory variant scoring), and UCSC cCREs.\n\n## Domain Reasoning\n\nRegulatory element identification requires converging lines of evidence: sequence conservation alone is insufficient (many conserved sequences are not regulatory), chromatin accessibility is necessary but not sufficient (open chromatin can be structural), TF binding peaks require motif validation, and eQTL evidence ties the element to a transcriptional outcome. No single data type is sufficient. A high-confidence regulatory element requires at least two independent evidence types, and ideally all four.\n\n## LOOK UP DON'T GUESS\n\n- TF binding motifs: retrieve from `jaspar_search_matrices` and `jaspar_get_matrix`; do not describe motifs from memory.\n- Experimental ChIP-seq data: search `ENCODE_search_experiments`; do not assume a TF has been profiled in a given cell type.\n- cCRE annotations for a genomic region: call `UCSC_get_encode_cCREs` with exact coordinates; do not guess element types.\n- Regulatory impact of a variant: query `RegulomeDB_query_variant`; never estimate regulatory importance from position alone.\n\n---\n\n**KEY PRINCIPLES**:\n1. **English-first queries** - Use English gene\u002FTF names in all tool calls; respond in user's language\n2. **Evidence layering** - Combine motif (JASPAR) + experimental (ENCODE ChIP-seq) + variant (RegulomeDB) evidence\n3. **Coordinate precision** - Genome coordinates must specify assembly (GRCh38 preferred)\n4. **Negative results documented** - Report when a TF has no ChIP-seq data in ENCODE\n\n---\n\n## COMPUTE, DON'T DESCRIBE\nWhen analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.\n\n## When to Use\n\n- \"What transcription factors bind near gene X?\"\n- \"Does this SNP affect a regulatory element?\"\n- \"Find CTCF binding sites in liver tissue\"\n- \"What are the enhancers active in this cell type?\"\n- \"Show me ChIP-seq experiments for H3K27ac in T cells\"\n- \"Is rs1234567 in a regulatory region?\"\n- \"What TF motifs overlap this genomic region?\"\n- \"Find ENCODE experiments for ATAC-seq in cancer cell lines\"\n\n---\n\n## Key Tools\n\n| Tool | Purpose | Key Params |\n|------|---------|-----------|\n| `jaspar_search_matrices` | Find TF binding motifs by TF name or organism | `name`, `species`, `collection`, `tax_id` |\n| `jaspar_get_matrix` | Get full PWM\u002FPFM for a specific JASPAR matrix | `matrix_id` (e.g., \"MA0139.1\") |\n| `JASPAR_get_transcription_factors` | List all TF matrices (paginated) | `page`, `page_size` |\n| `ENCODE_search_experiments` | Search ENCODE ChIP-seq\u002FATAC-seq\u002FWGBS experiments | `assay_title`, `target`, `biosample_term_name`, `limit` |\n| `ENCODE_search_histone_experiments` | Search histone mark ChIP-seq specifically | `histone_mark`, `biosample_term_name`, `limit` |\n| `ENCODE_search_chromatin_accessibility` | Search ATAC-seq\u002FDNase-seq experiments | `biosample_term_name`, `limit` |\n| `ENCODE_get_experiment` | Get full metadata for a specific ENCODE experiment | `accession` (e.g., \"ENCSR000EGM\") |\n| `ENCODE_search_annotations` | Search ENCODE cCRE and chromatin state annotations | `annotation_type`, `biosample_term_name`, `limit` |\n| `ENCODE_get_chromatin_state` | Search ChromHMM segmentation data | `biosample_term_name`, `limit` |\n| `UCSC_get_encode_cCREs` | Get cCREs overlapping a genomic region | `chrom`, `start`, `end` |\n| `RegulomeDB_query_variant` | Score regulatory impact of a variant | `rsid` (e.g., \"rs4994\") |\n| `ENCODE_search_biosamples` | Find available cell lines\u002Ftissues in ENCODE | `term_name`, `biosample_type`, `limit` |\n\n---\n\n## Workflow\n\n### Phase 1: TF Motif Discovery (JASPAR)\n\nWhen asked about TF binding motifs or what TFs might regulate a gene:\n\n```\n1. jaspar_search_matrices(name=\"TF_NAME\", species=\"Homo sapiens\")\n   -> Returns list of matrices with matrix_id, collection, version\n\n2. jaspar_get_matrix(matrix_id=\"MA0139.1\")\n   -> Returns full PFM\u002FPWM matrix, sequence logo URL, binding sites URL\n\n3. For broad TF family search:\n   jaspar_search_matrices(species=\"Homo sapiens\", collection=\"CORE\")\n   -> Filter by TF family name in results\n```\n\n**JASPAR Collections**:\n- `CORE`: High-quality, non-redundant matrices (best for most use cases)\n- `CNE`: Conserved non-coding elements\n- `POLII`: RNA Pol II binding sites\n\n**Key Response Fields**:\n- `matrix_id`: Versioned ID (e.g., \"MA0139.1\") — use for jaspar_get_matrix\n- `name`: TF gene symbol\n- `sequence_logo`: URL to binding site logo PNG\u002FSVG\n- `collection`: Which JASPAR collection\n\n### Phase 2: ENCODE Experiment Search\n\nWhen looking for ChIP-seq, ATAC-seq, or other functional genomics data:\n\n**For TF ChIP-seq**:\n```\nENCODE_search_experiments(\n    assay_title=\"TF ChIP-seq\",\n    target=\"CTCF\",              # TF gene name\n    biosample_term_name=\"HepG2\", # Cell line or tissue\n    limit=10\n)\n```\n\n**For histone marks**:\n```\nENCODE_search_histone_experiments(\n    histone_mark=\"H3K27ac\",         # or H3K4me3, H3K27me3, H3K36me3\n    biosample_term_name=\"liver\",\n    limit=10\n)\n```\n\n**For chromatin accessibility**:\n```\nENCODE_search_chromatin_accessibility(\n    biosample_term_name=\"T cell\",\n    limit=10\n)\n```\n\n**For regulatory annotations (cCREs, ChromHMM)**:\n```\nENCODE_search_annotations(\n    annotation_type=\"candidate Cis-Regulatory Elements\",\n    biosample_term_name=\"K562\",\n    limit=10\n)\n```\n\n**Common assay_title values**:\n- `\"TF ChIP-seq\"` - Transcription factor binding\n- `\"Histone ChIP-seq\"` - Histone modification\n- `\"ATAC-seq\"` - Chromatin accessibility\n- `\"DNase-seq\"` - Open chromatin (older method)\n- `\"WGBS\"` - DNA methylation\n\n**Note**: `ENCODE_search_experiments` returns experiment metadata only (accession, biosample, status). Use `ENCODE_get_experiment(accession)` to get file download links and detailed metadata.\n\n### Phase 3: cCRE Annotation (UCSC + ENCODE)\n\nWhen annotating a specific genomic region:\n\n```\nUCSC_get_encode_cCREs(\n    chrom=\"chr8\",       # Chromosome (GRCh38)\n    start=37966000,     # Start coordinate\n    end=37967000        # End coordinate\n)\n# Returns cCREs with type: pELS (proximal enhancer), dELS (distal enhancer),\n# PLS (promoter-like), CTCF-only, DNase-H3K4me3\n```\n\n**cCRE Types**:\n- **PLS** (Promoter-like): High DNase + H3K4me3 + H3K27ac signal near TSS\n- **pELS** (Proximal Enhancer): High DNase + H3K27ac, within 2kb of TSS\n- **dELS** (Distal Enhancer): High DNase + H3K27ac, >2kb from TSS\n- **CTCF-only**: CTCF binding without enhancer marks\n- **DNase-H3K4me3**: Unclassified accessible region\n\n### Phase 4: Regulatory Variant Scoring (RegulomeDB)\n\nWhen assessing regulatory impact of a variant:\n\n```\nRegulomeDB_query_variant(rsid=\"rs4994\")\n# Returns:\n#   regulome_score.ranking: \"1a\"-\"7\" (1a = highest regulatory evidence)\n#   regulome_score.probability: 0-1 continuous score\n#   tissue_specific_scores: dict of tissue -> score\n#   overlapping features: eQTLs, TF binding, DNase peaks, motifs\n```\n\n**RegulomeDB Score Interpretation**:\n| Rank | Meaning |\n|------|---------|\n| 1a | eQTL + TF binding + matched TF motif + DNase peak |\n| 1b | eQTL + TF binding + DNase peak |\n| 1c | eQTL + TF binding or DNase peak |\n| 1d | eQTL + motif or protein binding |\n| 1e | eQTL + motif hit |\n| 1f | eQTL only |\n| 2a | TF binding + motif match + DNase |\n| 2b | TF binding + matched motif |\n| 2c | TF binding with\u002Fwithout motif |\n| 3a | DNase peak + motif |\n| 3b | DNase peak only |\n| 4 | Motif hit only |\n| 5 | Proximity to Footprint |\n| 6 | Proximity to Footprint + TF |\n| 7 | No evidence |\n\nVariants with rank 1a-2b are most likely to affect gene regulation.\n\n---\n\n## Tool Parameter Reference\n\n| Tool | Required Params | Optional Params | Notes |\n|------|----------------|-----------------|-------|\n| `jaspar_search_matrices` | (none — returns all if empty) | `name`, `species`, `collection`, `tax_id`, `page`, `page_size` | Use `name` for TF name search |\n| `jaspar_get_matrix` | `matrix_id` | — | Full version required: \"MA0139.1\" not \"MA0139\" |\n| `JASPAR_get_transcription_factors` | (none) | `page`, `page_size` | Paginated; default page_size=10 |\n| `jaspar_get_matrix_versions` | `base_id` | — | base_id is unversioned (e.g., \"MA0139\") |\n| `ENCODE_search_experiments` | (none — returns all if empty) | `assay_title`, `target`, `biosample_term_name`, `limit` | assay_title must match ENCODE vocabulary exactly |\n| `ENCODE_search_histone_experiments` | (none) | `histone_mark`, `biosample_term_name`, `limit` | histone_mark: \"H3K27ac\", \"H3K4me3\", etc. |\n| `ENCODE_search_chromatin_accessibility` | (none) | `biosample_term_name`, `limit` | Returns ATAC-seq and DNase-seq |\n| `ENCODE_get_experiment` | `accession` | — | accession: \"ENCSR...\" format |\n| `ENCODE_search_annotations` | (none) | `annotation_type`, `biosample_term_name`, `limit` | annotation_type: \"candidate Cis-Regulatory Elements\" |\n| `ENCODE_get_chromatin_state` | (none) | `biosample_term_name`, `limit` | Returns ChromHMM segmentation |\n| `ENCODE_search_biosamples` | (none) | `term_name`, `biosample_type`, `limit` | biosample_type: \"cell line\", \"tissue\", \"primary cell\" |\n| `UCSC_get_encode_cCREs` | `chrom`, `start`, `end` | — | Coordinates in GRCh38; chrom format: \"chr1\" |\n| `RegulomeDB_query_variant` | `rsid` | — | rsid format: \"rs4994\" (with rs prefix) |\n\n---\n\n## Common Patterns\n\n### Pattern 1: TF Binding Site Investigation\n```\nGoal: Find where TF X binds and what motif it recognizes\nFlow:\n  1. jaspar_search_matrices(name=\"CTCF\") -> get matrix_id\n  2. jaspar_get_matrix(matrix_id) -> get full PWM, logo URL\n  3. ENCODE_search_experiments(assay_title=\"TF ChIP-seq\", target=\"CTCF\") -> experimental binding data\n  4. For specific tissue: add biosample_term_name=\"HepG2\"\nOutput: Motif logo + experimental binding evidence\n```\n\n### Pattern 2: Regulatory Variant Interpretation\n```\nGoal: Assess if variant rs1234567 affects gene regulation\nFlow:\n  1. RegulomeDB_query_variant(rsid=\"rs1234567\") -> score + overlapping features\n  2. If score \u003C= 2b: ENCODE_search_experiments(target=overlapping_TF) -> experimental evidence\n  3. UCSC_get_encode_cCREs(chrom, start, end) -> check if variant in known cCRE\nOutput: Regulatory score + supporting evidence + cCRE context\n```\n\n### Pattern 3: Cell-Type Regulatory Landscape\n```\nGoal: Characterize active enhancers in a cell type\nFlow:\n  1. ENCODE_search_histone_experiments(histone_mark=\"H3K27ac\", biosample_term_name=\"K562\") -> active enhancers\n  2. ENCODE_search_chromatin_accessibility(biosample_term_name=\"K562\") -> open chromatin\n  3. ENCODE_search_annotations(annotation_type=\"candidate Cis-Regulatory Elements\", biosample_term_name=\"K562\")\n  4. ENCODE_get_chromatin_state(biosample_term_name=\"K562\") -> ChromHMM states\nOutput: Active regulatory elements specific to the cell type\n```\n\n### Pattern 4: Gene Regulatory Region Mapping\n```\nGoal: Find all regulatory elements near a gene\nFlow:\n  1. Get gene coordinates from MyGene_query_genes or ensembl_lookup_gene\n  2. UCSC_get_encode_cCREs(chrom, start-50000, end+50000) -> nearby cCREs\n  3. ENCODE_search_experiments(target=TF_OF_INTEREST) -> TF binding data\n  4. jaspar_search_matrices(name=TF_NAME) -> motif for TF\nOutput: Map of regulatory elements around gene with evidence types\n```\n\n---\n\n## Fallback Strategies\n\n| Primary Tool | Fallback | When |\n|-------------|----------|------|\n| `ENCODE_search_experiments` with specific biosample | Remove `biosample_term_name` filter | No results for specific tissue |\n| `jaspar_search_matrices(name=TF)` | `jaspar_search_matrices(name=TF_family)` | TF not found by exact name |\n| `UCSC_get_encode_cCREs` | `ENCODE_search_annotations` without coordinates | If coordinates unknown |\n| `RegulomeDB_query_variant(rsid)` | Use `ENCODE_search_experiments` + `JASPAR` to manually assess overlap | rsid not in RegulomeDB |\n\n---\n\n## Limitations\n\n- **ENCODE TF ChIP-seq**: `assay_title=\"TF ChIP-seq\"` uses ENCODE's exact controlled vocabulary — avoid \"ChIP-seq\" (too general)\n- **UCSC cCREs**: Coordinates must be in GRCh38 (hg38); liftOver required for hg19 variants\n- **RegulomeDB**: Only scores variants with known rsIDs; novel variants not supported\n- **JASPAR**: Provides motif databases only — not genomic binding locations; combine with ENCODE for experimental evidence\n- **ENCODE experiment results**: The `@graph` field may be empty if query filters are too restrictive; relax filters and retry\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-regulatory-genomics","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-regulatory-genomics",{"tool":49,"command":50},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-regulatory-genomics",{"tool":52,"command":53},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-regulatory-genomics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-regulatory-genomics\u002FSKILL.md",true,[],[58,79,110,137,151,167],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":32},"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",[],[65,66,67,68,69,70,71,72,73,25,74,75,76,77,78],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":90,"publishedAt":32},"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",[85],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[91,92,93,94,95,96,97,98,99,100,101,102,103,104,25,105,106,107,108,109],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":122,"publishedAt":32},"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",[116,119],{"categoryNo":117,"categoryName":118,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":120,"categoryName":121,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000008","测试与质量",[123,124,125,126,127,128,129,130,131,132,92,133,134,135,136],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":32},"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",[],[139,144,145,146,147,148,149,150],"setup","report","project","installation","project setup","issues","state",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":158,"publishedAt":32},"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",[157],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},[153,159,70,160,161,162,25,163,164,165,166],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":168,"name":144,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":172,"publishedAt":32},"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",[],[144,146,107,173,148,174],"files","interactive"]