[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F5DCF023XWSDJ2NB3EGYTY":3,"skill-same:01M7F5DCF023XWSDJ2NB3EGYTY":56},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":13,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M7F5DCF023XWSDJ2NB3EGYTY","folklore-variant-evidence",null,"Retrieves ClinGen gene-disease validity assertions for a public gene or disease, and reviews source-linked public evidence and literature for one supported GRCh38 germline nuclear SNV or simple indel through Folklore Clinical Variant Interpretation MCP. Used when a scientific agent must branch deterministically on resolved, ambiguous, not-found, invalid, unsupported, or unavailable variant outcomes; chain a resolved public variant into related literature or publication details; or preserve evidence provenance without accepting patient, phenotype, family, segregation, or private case data.","beanspowt\u002Fbeancode","beanspowt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F333943283?v=4","01M7F39F0GDWKS57BCKW8JJH7F","01M7F39F1B1TVPDJMS37BZQHWM",0,"MIT","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-research\u002Fskills\u002Ffolklore-variant-evidence\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: folklore-variant-evidence\ndescription: \"Retrieves ClinGen gene-disease validity assertions for a public gene or disease, and reviews source-linked public evidence and literature for one supported GRCh38 germline nuclear SNV or simple indel through Folklore Clinical Variant Interpretation MCP. Used when a scientific agent must branch deterministically on resolved, ambiguous, not-found, invalid, unsupported, or unavailable variant outcomes; chain a resolved public variant into related literature or publication details; or preserve evidence provenance without accepting patient, phenotype, family, segregation, or private case data.\"\nlicense: MIT\ncompatibility: Requires network access to api.helena.bio (stateless Streamable HTTP MCP, no credentials) and a host supporting its advertised protocol, or curl for direct JSON-RPC POST requests.\nmetadata:\n  version: \"1.2\"\n  last-reviewed: \"2026-09-30\"\n  skill-author: \"Helena Bioinformatics\"\n  website: \"https:\u002F\u002Ffolklore.helena.bio\"\n  github: \"https:\u002F\u002Fgithub.com\u002Fhelena-bioinformatics\u002Ffolklore-mcp\"\n---\n\n# Folklore Variant Evidence\n\nUse Folklore Clinical Variant Interpretation MCP to retrieve structured public\nvariant evidence, automated variant-level ACMG\u002FAMP decision support, provenance,\nand source-linked literature for professional review. Keep the workflow limited\nto public identifiers and preserve every explicit outcome state. Adapter 1.5.0 also provides ClinGen Gene-Disease Validity assertions; source coverage is bounded, not every known association.\n\nFolklore Clinical Variant Interpretation MCP is published by Helena\nBioinformatics. Its hosted endpoint is:\n\n```text\nhttps:\u002F\u002Fapi.helena.bio\u002Ffolklore\u002Fv1\u002Fmcp\n```\n\nNo account or API key is required. The public Apache-2.0 adapter and contract are\navailable at \u003Chttps:\u002F\u002Fgithub.com\u002Fhelena-bioinformatics\u002Ffolklore-mcp>.\n\n## Minimal connection example\n\nA host without native MCP support can make the same public JSON-RPC call:\n\n```bash\ncurl --silent --show-error --fail-with-body --max-time 60 \\\n  -X POST https:\u002F\u002Fapi.helena.bio\u002Ffolklore\u002Fv1\u002Fmcp \\\n  -H 'Content-Type: application\u002Fjson' \\\n  -H 'Accept: application\u002Fjson, text\u002Fevent-stream' \\\n  -H 'MCP-Protocol-Version: 2026-07-28' \\\n  -H 'Mcp-Method: tools\u002Fcall' \\\n  -H 'Mcp-Name: search_variant_evidence' \\\n  -d '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"tools\u002Fcall\",\"params\":{\"_meta\":{\"io.modelcontextprotocol\u002FprotocolVersion\":\"2026-07-28\",\"io.modelcontextprotocol\u002FclientCapabilities\":{}},\"name\":\"search_variant_evidence\",\"arguments\":{\"assembly\":\"GRCh38\",\"query\":\"rs80357914\"}}}'\n```\n\nThe routing headers must match the JSON-RPC method and tool name. A successful\nHTTP response is not sufficient: inspect JSON-RPC `error`, then\n`result.structuredContent.adapter_error`, then this tool's\n`result.structuredContent.result.status`. Other tools use different response\nshapes; use the [contract table](references\u002Fmcp-contract.md).\n\nInspect the returned outcome before continuing. This example can return\n`ambiguous` with multiple candidates: stop and request an unambiguous public\nvariant notation instead of selecting a candidate automatically.\n\n## Select the right skill\n\nUse this skill when the task is one public variant to structured Folklore\nevidence, explicit resolution-state handling, variant-linked literature, or ClinGen gene-to-disease\u002Fdisease-to-gene assertions.\n\n- Use `database-lookup` for broad direct queries across ClinVar, dbSNP, gnomAD,\n  Ensembl VEP, COSMIC, or multiple databases.\n- Use `genomic-coordinates` first when the assembly, coordinate convention,\n  contig name, or variant representation is uncertain.\n- Do not use this skill for VCF annotation, batch processing, somatic variants,\n  structural variants, polygenic scores, or patient-specific interpretation.\n\nFolklore Clinical Variant Interpretation MCP complements those skills with one\nsource-linked public evidence contract. It does not replace direct database\nreview or qualified clinical judgment.\n\n## Enforce the input boundary\n\nBefore a variant tool call:\n\n1. Extract exactly one public variant identifier or notation.\n2. Require GRCh38 and a germline nuclear SNV or simple insertion\u002Fdeletion shorter\n   than 50 base pairs. An unsupported assembly may be rejected by the input\n   schema before any scientific `unsupported` status exists.\n3. Remove or refuse patient names, case identifiers, phenotypes, family history,\n   segregation evidence, clinical records, uploaded files, and other private or\n   patient-specific context.\n4. If the task depends on patient context, stop and explain that Folklore\n   Clinical Variant Interpretation MCP does not accept or evaluate it.\n5. Never transform a patient-specific request into a public variant query while\n   implying that the result answers the patient-specific question.\n\nAccepted public variant forms include genomic coordinates, genomic\u002Fcoding\u002F\nprotein HGVS, SPDI, rsID, or a `canonical_key` returned by Folklore Clinical\nVariant Interpretation MCP.\n\n## Verify the live tool catalog\n\nConnect to the hosted endpoint and call `tools\u002Flist`. Verify the available tools\ninstead of relying on model memory. The documented public catalog contains:\n\n- `search_variant_evidence`\n- `search_variant_literature`\n- `get_publication_details`\n- `search_literature_corpus`\n- `get_gene_disease_associations`\n- `search_disease_genes`\n\nThe separate seventh tool `support_helena` is not scientific evidence; use it only when explicitly requested.\n\nIf discovery or a tool call fails, preserve the failure as an availability\nproblem. Do not reinterpret it as lack of scientific evidence.\n\nRead [the public MCP contract](references\u002Fmcp-contract.md) before composing tool\ncalls or interpreting response states.\n\n## Retrieve gene-disease assertions\n\nUse `get_gene_disease_associations` for one exact gene symbol or HGNC identifier, or `search_disease_genes` for an exact MONDO identifier or public disease-name substring. Both accept `limit` (default 20, 1–50) and `offset` (default 0, 0–1000). See the reference for request examples. This is a separate source lookup and requires no variant input or assembly.\n\nPreserve each returned disease identity, inheritance, evidence assessment, source\nURL, date, `source.version` and `source.snapshotSha256`. This is a local ClinGen\nsnapshot, not a guarantee of the latest ClinGen release. Follow\n`pagination.nextOffset` while it is present; preserve pagination-ceiling warnings.\nAn empty page after the total has been passed does not mean the initial query had\nno matches. Do not combine distinct diseases or silently choose among name matches.\nGene-disease validity does not classify a particular variant. A `not_found`\nresponse means no matching assertion in the available source, not no association.\nNo patient, phenotype, family, segregation, private case data or sequencing files\nmay be sent. Qualified professional review remains required.\n\n## Run the variant-evidence workflow\n\n### 1. Resolve and retrieve evidence\n\nCall `search_variant_evidence` with:\n\n```text\nassembly: GRCh38\nquery: \u003Cone public variant identifier or notation>\n```\n\nDo not add phenotype, disease, patient, family, or treatment context to this\ncall. Preserve the returned contract fields, source links, limitations, and\nusage boundary.\n\n### 2. Branch on the returned status\n\nRead transport\u002FJSON-RPC errors and `adapter_error` first. For\n`search_variant_evidence`, let `envelope = result.structuredContent`; only if\n`envelope.result` is non-null, branch on `envelope.result.status`. An\n`invalid_arguments` adapter error is distinct from scientific `invalid_request`.\nPreserve `isError` and any typed failure, including `resolution_unavailable`.\nTreat the status as a control-flow value, not prose:\n\n| Status | Required action |\n|---|---|\n| `resolved` | Reuse the returned `canonical_key`; review the structured interpretation, provenance, source links, and limitations. |\n| `ambiguous` | Show the returned candidates and ask for an explicit public variant selection. Never choose a candidate automatically. |\n| `not_found` | Report that no result was found within this service and query scope. Do not claim universal absence. |\n| `invalid_request` | Report the validation problem and request a corrected public variant. Do not silently reinterpret the input. |\n| `unsupported` | State the relevant service boundary and stop. Do not force the query into a supported form. |\n| `resolution_unavailable` | Report a temporary resolution or availability failure. Do not treat it as evidence absence. |\n\nOnly a `resolved` result may proceed automatically into a variant-linked\nliterature workflow. Its canonical key is `envelope.result.identity.canonical_key`.\nIf `envelope.result.interpretation.status` is `unavailable`, preserve its typed\nerror; identity resolution has succeeded, but classification has not. Do not read\nor invent a classification for that outcome.\n\n### 3. Review the evidence without overclaiming\n\nFor a resolved result:\n\n- Present the returned variant identity and `canonical_key`.\n- Preserve the automated variant-level ACMG\u002FAMP decision-support result exactly\n  as returned.\n- Cite the returned public sources and provenance.\n- Keep submitted ClinVar assertions separate from Folklore's automated result,\n  as required by the [upstream interpretation guidance](https:\u002F\u002Fgithub.com\u002Fhelena-bioinformatics\u002Ffolklore-mcp).\n  If they disagree, report each assertion with its source\u002Fdate and preserve\n  the disagreement; do not present a merged consensus classification.\n- Separate returned facts from the agent's synthesis.\n- State that qualified professional review is required.\n- Do not turn the result into a diagnosis, individual risk estimate, treatment\n  recommendation, or standalone clinical report.\n\n## Chain into literature\n\n### Variant-linked literature\n\nAfter a resolved evidence call, pass the returned `canonical_key` to\n`search_variant_literature`. Keep `assembly` as `GRCh38`. An optional `question`\nmay narrow the literature focus, but it must remain a public scientific question\nand must not contain patient context.\n\nDistinguish each result's match type:\n\n- `exact_variant`: direct match to the resolved variant\n- `variant_alias`: match through a reported alias\n- `gene_association`: broader gene-level association, not variant-specific proof\n\nLiterature associations do not alter the returned ACMG\u002FAMP classification.\n\n### Publication details\n\nCall `get_publication_details` only with a PMID returned by the literature tools.\nPreserve PubMed URLs, DOI\u002FPMCID fields when present, retraction status, and the\ndistinction between gene mentions and variant mentions.\n\n### Semantic corpus search\n\nUse `search_literature_corpus` for a public natural-language scientific question\nor for discovery by publication identifier, gene, variant, phenotype, HPO, or\nOMIM concept. Treat results as source-linked candidates for professional review.\nA zero-result response means no result was returned for that bounded query, not\nthat no relevant publication exists anywhere.\n\nThe query is 3–200 characters, with `limit` 1–25 and `sort` set to `relevance`,\n`newest`, or `oldest`. For another page, reuse the returned opaque `next_cursor`\nwith the same query and sort; do not construct an offset. Keep `match_types` and\n`article_entities` distinct from variant-literature match types. Report\n`semantic_index_used` and `semantic_degraded_reason`; a returned lexical match\ndoes not prove semantic retrieval worked. Preserve additional retrieval metadata\nreturned by the live service.\n\nDo not place patient information into a corpus query, even if the query is not\nvariant-specific.\n\n## Report a reproducible result\n\nInclude:\n\n1. The exact public query and `GRCh38` assembly.\n2. The returned status and, if resolved, the `canonical_key`.\n3. The structured evidence or literature result without changing its meaning.\n4. Source links and publication identifiers.\n5. Match type for literature results.\n6. Access date and any availability limitation.\n7. This boundary statement:\n\n> This is public, variant-level decision support for qualified professional\n> review. It does not evaluate patient, phenotype, family, segregation, or\n> private case data and is not a diagnosis or treatment recommendation.\n\n## Falsifiable smoke test\n\nUse the public rsID `rs80357914` to test ambiguity handling:\n\n```text\nCall search_variant_evidence with assembly GRCh38 and query rs80357914. If the\nresult is ambiguous, list the returned candidates and stop for explicit\nselection. Do not select a candidate or call downstream literature tools.\n```\n\nThe ambiguity branch passes only if an ambiguous response causes the workflow to\nstop without automatic candidate selection. If the live response changes, record\nthe actual status; a resolved response does not test ambiguity handling.\n\nOn 2026-09-30, live discovery reported adapter 1.5.0 and protocol 2026-07-28.\nThe rsID example returned `ambiguous`; a separate public HGVS query resolved and\nwas chained through its returned key to literature and a returned PMID. Corpus\ncursor pagination and gene-disease offset pagination were exercised. These are\ndated protocol checks, not validation of clinical accuracy. See the reference\nfor exact response shapes and source\u002Flive differences.\n\n## Official references\n\n- Integration setup: \u003Chttps:\u002F\u002Ffolklore.helena.bio\u002Fintegrations>\n- Technical guide: \u003Chttps:\u002F\u002Ffolklore.helena.bio\u002Fdocs\u002Ffolklore-connector>\n- Public adapter and contract: \u003Chttps:\u002F\u002Fgithub.com\u002Fhelena-bioinformatics\u002Ffolklore-mcp>\n- Official MCP Registry identity: `io.github.helena-bioinformatics\u002Ffolklore`\n","# Folklore Variant Evidence\n\nUse Folklore Clinical Variant Interpretation MCP to retrieve structured public\nvariant evidence, automated variant-level ACMG\u002FAMP decision support, provenance,\nand source-linked literature for professional review. Keep the workflow limited\nto public identifiers and preserve every explicit outcome state. Adapter 1.5.0 also provides ClinGen Gene-Disease Validity assertions; source coverage is bounded, not every known association.\n\nFolklore Clinical Variant Interpretation MCP is published by Helena\nBioinformatics. Its hosted endpoint is:\n\n```text\nhttps:\u002F\u002Fapi.helena.bio\u002Ffolklore\u002Fv1\u002Fmcp\n```\n\nNo account or API key is required. The public Apache-2.0 adapter and contract are\navailable at \u003Chttps:\u002F\u002Fgithub.com\u002Fhelena-bioinformatics\u002Ffolklore-mcp>.\n\n## Minimal connection example\n\nA host without native MCP support can make the same public JSON-RPC call:\n\n```bash\ncurl --silent --show-error --fail-with-body --max-time 60 \\\n  -X POST https:\u002F\u002Fapi.helena.bio\u002Ffolklore\u002Fv1\u002Fmcp \\\n  -H 'Content-Type: application\u002Fjson' \\\n  -H 'Accept: application\u002Fjson, text\u002Fevent-stream' \\\n  -H 'MCP-Protocol-Version: 2026-07-28' \\\n  -H 'Mcp-Method: tools\u002Fcall' \\\n  -H 'Mcp-Name: search_variant_evidence' \\\n  -d '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"tools\u002Fcall\",\"params\":{\"_meta\":{\"io.modelcontextprotocol\u002FprotocolVersion\":\"2026-07-28\",\"io.modelcontextprotocol\u002FclientCapabilities\":{}},\"name\":\"search_variant_evidence\",\"arguments\":{\"assembly\":\"GRCh38\",\"query\":\"rs80357914\"}}}'\n```\n\nThe routing headers must match the JSON-RPC method and tool name. A successful\nHTTP response is not sufficient: inspect JSON-RPC `error`, then\n`result.structuredContent.adapter_error`, then this tool's\n`result.structuredContent.result.status`. Other tools use different response\nshapes; use the [contract table](references\u002Fmcp-contract.md).\n\nInspect the returned outcome before continuing. This example can return\n`ambiguous` with multiple candidates: stop and request an unambiguous public\nvariant notation instead of selecting a candidate automatically.\n\n## Select the right skill\n\nUse this skill when the task is one public variant to structured Folklore\nevidence, explicit resolution-state handling, variant-linked literature, or ClinGen gene-to-disease\u002Fdisease-to-gene assertions.\n\n- Use `database-lookup` for broad direct queries across ClinVar, dbSNP, gnomAD,\n  Ensembl VEP, COSMIC, or multiple databases.\n- Use `genomic-coordinates` first when the assembly, coordinate convention,\n  contig name, or variant representation is uncertain.\n- Do not use this skill for VCF annotation, batch processing, somatic variants,\n  structural variants, polygenic scores, or patient-specific interpretation.\n\nFolklore Clinical Variant Interpretation MCP complements those skills with one\nsource-linked public evidence contract. It does not replace direct database\nreview or qualified clinical judgment.\n\n## Enforce the input boundary\n\nBefore a variant tool call:\n\n1. Extract exactly one public variant identifier or notation.\n2. Require GRCh38 and a germline nuclear SNV or simple insertion\u002Fdeletion shorter\n   than 50 base pairs. An unsupported assembly may be rejected by the input\n   schema before any scientific `unsupported` status exists.\n3. Remove or refuse patient names, case identifiers, phenotypes, family history,\n   segregation evidence, clinical records, uploaded files, and other private or\n   patient-specific context.\n4. If the task depends on patient context, stop and explain that Folklore\n   Clinical Variant Interpretation MCP does not accept or evaluate it.\n5. Never transform a patient-specific request into a public variant query while\n   implying that the result answers the patient-specific question.\n\nAccepted public variant forms include genomic coordinates, genomic\u002Fcoding\u002F\nprotein HGVS, SPDI, rsID, or a `canonical_key` returned by Folklore Clinical\nVariant Interpretation MCP.\n\n## Verify the live tool catalog\n\nConnect to the hosted endpoint and call `tools\u002Flist`. Verify the available tools\ninstead of relying on model memory. The documented public catalog contains:\n\n- `search_variant_evidence`\n- `search_variant_literature`\n- `get_publication_details`\n- `search_literature_corpus`\n- `get_gene_disease_associations`\n- `search_disease_genes`\n\nThe separate seventh tool `support_helena` is not scientific evidence; use it only when explicitly requested.\n\nIf discovery or a tool call fails, preserve the failure as an availability\nproblem. Do not reinterpret it as lack of scientific evidence.\n\nRead [the public MCP contract](references\u002Fmcp-contract.md) before composing tool\ncalls or interpreting response states.\n\n## Retrieve gene-disease assertions\n\nUse `get_gene_disease_associations` for one exact gene symbol or HGNC identifier, or `search_disease_genes` for an exact MONDO identifier or public disease-name substring. Both accept `limit` (default 20, 1–50) and `offset` (default 0, 0–1000). See the reference for request examples. This is a separate source lookup and requires no variant input or assembly.\n\nPreserve each returned disease identity, inheritance, evidence assessment, source\nURL, date, `source.version` and `source.snapshotSha256`. This is a local ClinGen\nsnapshot, not a guarantee of the latest ClinGen release. Follow\n`pagination.nextOffset` while it is present; preserve pagination-ceiling warnings.\nAn empty page after the total has been passed does not mean the initial query had\nno matches. Do not combine distinct diseases or silently choose among name matches.\nGene-disease validity does not classify a particular variant. A `not_found`\nresponse means no matching assertion in the available source, not no association.\nNo patient, phenotype, family, segregation, private case data or sequencing files\nmay be sent. Qualified professional review remains required.\n\n## Run the variant-evidence workflow\n\n### 1. Resolve and retrieve evidence\n\nCall `search_variant_evidence` with:\n\n```text\nassembly: GRCh38\nquery: \u003Cone public variant identifier or notation>\n```\n\nDo not add phenotype, disease, patient, family, or treatment context to this\ncall. Preserve the returned contract fields, source links, limitations, and\nusage boundary.\n\n### 2. Branch on the returned status\n\nRead transport\u002FJSON-RPC errors and `adapter_error` first. For\n`search_variant_evidence`, let `envelope = result.structuredContent`; only if\n`envelope.result` is non-null, branch on `envelope.result.status`. An\n`invalid_arguments` adapter error is distinct from scientific `invalid_request`.\nPreserve `isError` and any typed failure, including `resolution_unavailable`.\nTreat the status as a control-flow value, not prose:\n\n| Status | Required action |\n|---|---|\n| `resolved` | Reuse the returned `canonical_key`; review the structured interpretation, provenance, source links, and limitations. |\n| `ambiguous` | Show the returned candidates and ask for an explicit public variant selection. Never choose a candidate automatically. |\n| `not_found` | Report that no result was found within this service and query scope. Do not claim universal absence. |\n| `invalid_request` | Report the validation problem and request a corrected public variant. Do not silently reinterpret the input. |\n| `unsupported` | State the relevant service boundary and stop. Do not force the query into a supported form. |\n| `resolution_unavailable` | Report a temporary resolution or availability failure. Do not treat it as evidence absence. |\n\nOnly a `resolved` result may proceed automatically into a variant-linked\nliterature workflow. Its canonical key is `envelope.result.identity.canonical_key`.\nIf `envelope.result.interpretation.status` is `unavailable`, preserve its typed\nerror; identity resolution has succeeded, but classification has not. Do not read\nor invent a classification for that outcome.\n\n### 3. Review the evidence without overclaiming\n\nFor a resolved result:\n\n- Present the returned variant identity and `canonical_key`.\n- Preserve the automated variant-level ACMG\u002FAMP decision-support result exactly\n  as returned.\n- Cite the returned public sources and provenance.\n- Keep submitted ClinVar assertions separate from Folklore's automated result,\n  as required by the [upstream interpretation guidance](https:\u002F\u002Fgithub.com\u002Fhelena-bioinformatics\u002Ffolklore-mcp).\n  If they disagree, report each assertion with its source\u002Fdate and preserve\n  the disagreement; do not present a merged consensus classification.\n- Separate returned facts from the agent's synthesis.\n- State that qualified professional review is required.\n- Do not turn the result into a diagnosis, individual risk estimate, treatment\n  recommendation, or standalone clinical report.\n\n## Chain into literature\n\n### Variant-linked literature\n\nAfter a resolved evidence call, pass the returned `canonical_key` to\n`search_variant_literature`. Keep `assembly` as `GRCh38`. An optional `question`\nmay narrow the literature focus, but it must remain a public scientific question\nand must not contain patient context.\n\nDistinguish each result's match type:\n\n- `exact_variant`: direct match to the resolved variant\n- `variant_alias`: match through a reported alias\n- `gene_association`: broader gene-level association, not variant-specific proof\n\nLiterature associations do not alter the returned ACMG\u002FAMP classification.\n\n### Publication details\n\nCall `get_publication_details` only with a PMID returned by the literature tools.\nPreserve PubMed URLs, DOI\u002FPMCID fields when present, retraction status, and the\ndistinction between gene mentions and variant mentions.\n\n### Semantic corpus search\n\nUse `search_literature_corpus` for a public natural-language scientific question\nor for discovery by publication identifier, gene, variant, phenotype, HPO, or\nOMIM concept. Treat results as source-linked candidates for professional review.\nA zero-result response means no result was returned for that bounded query, not\nthat no relevant publication exists anywhere.\n\nThe query is 3–200 characters, with `limit` 1–25 and `sort` set to `relevance`,\n`newest`, or `oldest`. For another page, reuse the returned opaque `next_cursor`\nwith the same query and sort; do not construct an offset. Keep `match_types` and\n`article_entities` distinct from variant-literature match types. Report\n`semantic_index_used` and `semantic_degraded_reason`; a returned lexical match\ndoes not prove semantic retrieval worked. Preserve additional retrieval metadata\nreturned by the live service.\n\nDo not place patient information into a corpus query, even if the query is not\nvariant-specific.\n\n## Report a reproducible result\n\nInclude:\n\n1. The exact public query and `GRCh38` assembly.\n2. The returned status and, if resolved, the `canonical_key`.\n3. The structured evidence or literature result without changing its meaning.\n4. Source links and publication identifiers.\n5. Match type for literature results.\n6. Access date and any availability limitation.\n7. This boundary statement:\n\n> This is public, variant-level decision support for qualified professional\n> review. It does not evaluate patient, phenotype, family, segregation, or\n> private case data and is not a diagnosis or treatment recommendation.\n\n## Falsifiable smoke test\n\nUse the public rsID `rs80357914` to test ambiguity handling:\n\n```text\nCall search_variant_evidence with assembly GRCh38 and query rs80357914. If the\nresult is ambiguous, list the returned candidates and stop for explicit\nselection. Do not select a candidate or call downstream literature tools.\n```\n\nThe ambiguity branch passes only if an ambiguous response causes the workflow to\nstop without automatic candidate selection. If the live response changes, record\nthe actual status; a resolved response does not test ambiguity handling.\n\nOn 2026-09-30, live discovery reported adapter 1.5.0 and protocol 2026-07-28.\nThe rsID example returned `ambiguous`; a separate public HGVS query resolved and\nwas chained through its returned key to literature and a returned PMID. Corpus\ncursor pagination and gene-disease offset pagination were exercised. These are\ndated protocol checks, not validation of clinical accuracy. See the reference\nfor exact response shapes and source\u002Flive differences.\n\n## Official references\n\n- Integration setup: \u003Chttps:\u002F\u002Ffolklore.helena.bio\u002Fintegrations>\n- Technical guide: \u003Chttps:\u002F\u002Ffolklore.helena.bio\u002Fdocs\u002Ffolklore-connector>\n- Public adapter and contract: \u003Chttps:\u002F\u002Fgithub.com\u002Fhelena-bioinformatics\u002Ffolklore-mcp>\n- Official MCP Registry identity: `io.github.helena-bioinformatics\u002Ffolklore`\n",{"name":5,"license":14,"metadata":23,"description":7,"compatibility":29},{"github":24,"version":25,"website":26,"skill-author":27,"last-reviewed":28},"https:\u002F\u002Fgithub.com\u002Fhelena-bioinformatics\u002Ffolklore-mcp","1.2","https:\u002F\u002Ffolklore.helena.bio","Helena Bioinformatics","2026-09-30","Requires network access to api.helena.bio (stateless Streamable HTTP MCP, no credentials) and a host supporting its advertised protocol, or curl for direct JSON-RPC POST requests.","main","66c9bd32ac14a921980362cf85872a1c402101c2","hermes\u002Fprofiles\u002Fworker-research\u002Fskills\u002Ffolklore-variant-evidence","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode","https:\u002F\u002Fgithub.com\u002Fbeanspowt","2026-11-10 23:22:33",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add beanspowt\u002Fbeancode --skill folklore-variant-evidence",{"tool":42,"command":43},"bunx","bunx skills add beanspowt\u002Fbeancode --skill folklore-variant-evidence",{"tool":45,"command":46},"pnpm","pnpm dlx skills add beanspowt\u002Fbeancode --skill folklore-variant-evidence","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-research\u002Fskills\u002Ffolklore-variant-evidence\u002FSKILL.md",true,[50],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fmcp-contract.md","REFERENCE","参考文档",11040,"https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-research\u002Fskills\u002Ffolklore-variant-evidence\u002Freferences\u002Fmcp-contract.md",[57,64,71,78,85,92],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":18},"01M7F6BB3VS43C65P23JR4ZN5G","venue-templates","Prepares journal manuscripts, conference papers, research posters, and grant documents using venue-specific formatting guidance and bundled LaTeX scaffolds. Supports selecting an official template, checking current page or anonymity rules, adapting academic writing to a venue, or inspecting a submission PDF.","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-writer\u002Fskills\u002Fvenue-templates\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M7F6B4CBVEHY1RKVW55X8484","scientific-writing","Drafts, revises, and audits scientific manuscripts or reports with explicit evidence provenance, reporting-guideline coverage, authorship accountability, confidentiality controls, and local consistency checks. Use for manuscript sections, references, declarations, tables, figures, or submission preparation when scientific accuracy and traceability matter.","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-writer\u002Fskills\u002Fscientific-writing\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M7F6AXKSP5AXE8B7RCE1KP0C","scientific-visualization","Creates and audits truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly. Use it for figure design, multi-panel layouts, uncertainty and missing-data displays, color\u002Fcontrast review, image metadata validation, and journal export planning.","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-writer\u002Fskills\u002Fscientific-visualization\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M7F6AMRHS0QH64CMKE8TP9Y7","scientific-slides","Builds slide decks and presentations for research talks. Used for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-writer\u002Fskills\u002Fscientific-slides\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M7F6ACZ7GQJNNW0682235MC3","scientific-schematics","Generates scientific diagram drafts using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.7 Flash for quality review. Refines when the review requests improvement, with at most two generations. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-writer\u002Fskills\u002Fscientific-schematics\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M7F6A2JDHTYABYSA4NCE82VG","research-grants","Supports research proposal preparation and review for NSF, NIH, DOE, DARPA, and Taiwan NSTC, including opportunity-specific requirements, aims, review criteria, budgets, broader impacts, forms, and resubmissions. Use for investigator-authored grant development, compliance matrices, and proposal critiques.","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-writer\u002Fskills\u002Fresearch-grants\u002FSKILL.md",[],[]]