[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6R5ZPRJQZ1Y8CBPT3WHSWCB":3,"skill-same:01M6R5ZPRJQZ1Y8CBPT3WHSWCB":130},{"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":23,"publishedAt":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":46,"ownerHtmlUrl":47,"ownerBlogUrl":46,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M6R5ZPRJQZ1Y8CBPT3WHSWCB","vuln-triage",null,"Prioritize actual exact-coordinate vulnerability findings, preserve unknown exposure and partial coverage, and return practical remediation or an unsent advisory draft.","runxhq\u002Frunx","runxhq","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F278566904?v=4","01M6R54JKTWZNT4VQZ0K0DZ7V2","runx","01M6R54JRGDE4MDVDDR0E9MN0K",103,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35],"triage","vuln triage","coverage","practical","coordinate","unknown","vulnerability","preserve","advisory","draft","remediation","prioritize","2026-11-10 10:12:30",false,"---\nname: vuln-triage\ndescription: Prioritize actual exact-coordinate vulnerability findings, preserve unknown exposure and partial coverage, and return practical remediation or an unsent advisory draft.\n---\n\n# Vulnerability triage\n\nTurn dependency findings into an operational decision: what deserves attention,\nwhat exposure is established, what remains unknown, and which remediation is\njustified. This is the judgment step after evidence acquisition. It does not\nscan a repository, install packages, modify code or publish an advisory.\n\nUse the default `scan` with `target`, actual `evidence` and any relevant\n`scan_context`. Evidence can be a current `runx\u002Fcve-audit.audit.v1` packet or a\nfindings object from another source. Each finding needs `dependency`,\n`exact_version` and `advisory_id`; retain ecosystem, source URL, affected ranges,\nseverity, paths and original provenance when available. A CVE finding's `dependency_locations` may be\na bounded preview; preserve its count, completeness flag and component artifact.\nUse the producer's paged `locations` phase before treating that preview as the\ncomplete affected-location set. An audit delivery digest\nor `verified: true` is not a finding. Use `cve-audit` when the missing work is\nactually reading a lockfile and querying OSV; use `sbom-generate` for inventory\nand CycloneDX output.\n\n## Keep facts, exposure and judgment separate\n\nAn exact-coordinate match says that the source associates an advisory with a\npackage version. It does not establish that the vulnerable function is reachable\nin this deployment, that the package is installed at runtime, or that an exploit\nhas occurred. The review preserves the supplied source and binds its exact bytes\nwith a native digest. That binds the input; it does not independently verify a\nprovider, a caller's receipt id or the truth of a supplied deployment claim.\n\nDescribe relevant deployment observations in `scan_context.evidence`, with an\n`id`, a `source` and an `excerpt` for each. A confirmed-exposure assessment must\nreference those ids in `exposure_evidence`. Internet-facing status alone is not\nproof that a vulnerable code path is used. If the necessary trace, call site,\nconfiguration or runtime evidence is missing, retain `not_established` and name\nwhat would settle it. Confidence describes the judgment, not cryptographic proof.\n\nPrioritize from impact, reachability, deployment role, available mitigations and\nthe cost of delaying a fix. Do not repeat a severity label as the entire\nrationale. Give each finding a concrete next action: validate an upgrade, inspect\na named call site, apply an evidenced mitigation, or obtain the missing trace.\nAn exact `fixed_version` must occur in the affected package's supplied advisory\nevents; otherwise describe version verification as pending. Do not invent a\nrelease or assume that the highest suggested version is compatible.\n\n## Use it directly or inside a workflow\n\nThe default returns `vulnerability_review` (`runx\u002Fvuln-triage.scan.v1`), with\nthe original findings, one assessment and recommendation per coordinate\u002Fadvisory\nidentity, escalation criteria, useful operator summary and source coverage.\nRepeated identities keep their locations together. No arbitrary finding count\nis silently discarded. Runtime byte and model-turn budgets still apply; for a\nlarge audit, consume its bounded result parts and retain the overall scope.\n\nA parent can pass a current CVE result directly while its workflow is still open.\nThere is no requirement to fabricate a sealed parent receipt first. The final\nparent receipt records the actual provider and triage steps. If an independent\nconsumer needs sealed evidence, verify the original receipt tree through native\nreceipt tools and retrieve the declared claim; a receipt proves recorded claim\nintegrity, not external truth.\n\nPartial scans are useful: triage the known findings now and keep the scan's\ncontinuation and previous result-part references. Inline findings may cover only\none part. An empty part is not a clean overall review. `no_matches_in_scope` is\navailable only for a complete selected scan with full inventory coverage, no\nomissions and all observations present. Unknown exposure remains unknown even\nwhen scan coverage is complete. The review never certifies a project secure.\n\n## Advisory drafting and recovery\n\n`advisory` takes the exact validated review and an audience, then prepares a\ntitle, summary, body, affected advisory ids and disclosure checklist. It reuses\nthe findings and remediation rather than rescanning or reclassifying the source.\nThe result is `ready_for_review`, `not_published` and `not_called`; no repository,\nemail or other provider is invoked. Publication is a separate authorized action.\n\nMissing identities, omitted assessments, unbound exposure references and invented\nfix versions produce `needs_more_evidence` while retaining the known findings.\nCorrect the precise missing input or assessment. Continue the original audit or\nread its earlier result parts when coverage is incomplete. Never replace missing\nevidence with a receipt-shaped string, silently shorten the findings list, or\nreport an incomplete scan as a negative result.\n\n## Agent task: vuln-triage-assess\n\nUse `triage_context.findings` and the supplied deployment context. Return\n`risk_assessment_draft` with `decision` (`remediate`, `monitor` or `needs_human`),\n`operator_summary.summary`, and `advisory_assessments`. Each assessment contains\nthe unchanged `finding_key`, `priority` (`urgent`, `high`, `normal`, `low` or\n`unknown`), `confidence` (`high`, `medium`, `low`), `exposure` (`confirmed` or\n`not_established`), `exposure_evidence` ids, a substantive `rationale` and a\nconcrete `recommendation`. Add `fixed_version` only from the matching supplied\nadvisory's fixed events. Cover every finding once; do not invent findings,\ndeployment evidence, independent verification or completed remediation.\n\n## Agent task: vuln-triage-advisory\n\nReturn `advisory_draft` with title, summary, body, affected_advisory_ids and\ndisclosure_checklist. Cite only admitted ids. Preserve partial coverage and\nunknown exposure; do not turn a suggested upgrade into a completed deployment.\nDo not claim publication or provider execution.\n","# Vulnerability triage\n\nTurn dependency findings into an operational decision: what deserves attention,\nwhat exposure is established, what remains unknown, and which remediation is\njustified. This is the judgment step after evidence acquisition. It does not\nscan a repository, install packages, modify code or publish an advisory.\n\nUse the default `scan` with `target`, actual `evidence` and any relevant\n`scan_context`. Evidence can be a current `runx\u002Fcve-audit.audit.v1` packet or a\nfindings object from another source. Each finding needs `dependency`,\n`exact_version` and `advisory_id`; retain ecosystem, source URL, affected ranges,\nseverity, paths and original provenance when available. A CVE finding's `dependency_locations` may be\na bounded preview; preserve its count, completeness flag and component artifact.\nUse the producer's paged `locations` phase before treating that preview as the\ncomplete affected-location set. An audit delivery digest\nor `verified: true` is not a finding. Use `cve-audit` when the missing work is\nactually reading a lockfile and querying OSV; use `sbom-generate` for inventory\nand CycloneDX output.\n\n## Keep facts, exposure and judgment separate\n\nAn exact-coordinate match says that the source associates an advisory with a\npackage version. It does not establish that the vulnerable function is reachable\nin this deployment, that the package is installed at runtime, or that an exploit\nhas occurred. The review preserves the supplied source and binds its exact bytes\nwith a native digest. That binds the input; it does not independently verify a\nprovider, a caller's receipt id or the truth of a supplied deployment claim.\n\nDescribe relevant deployment observations in `scan_context.evidence`, with an\n`id`, a `source` and an `excerpt` for each. A confirmed-exposure assessment must\nreference those ids in `exposure_evidence`. Internet-facing status alone is not\nproof that a vulnerable code path is used. If the necessary trace, call site,\nconfiguration or runtime evidence is missing, retain `not_established` and name\nwhat would settle it. Confidence describes the judgment, not cryptographic proof.\n\nPrioritize from impact, reachability, deployment role, available mitigations and\nthe cost of delaying a fix. Do not repeat a severity label as the entire\nrationale. Give each finding a concrete next action: validate an upgrade, inspect\na named call site, apply an evidenced mitigation, or obtain the missing trace.\nAn exact `fixed_version` must occur in the affected package's supplied advisory\nevents; otherwise describe version verification as pending. Do not invent a\nrelease or assume that the highest suggested version is compatible.\n\n## Use it directly or inside a workflow\n\nThe default returns `vulnerability_review` (`runx\u002Fvuln-triage.scan.v1`), with\nthe original findings, one assessment and recommendation per coordinate\u002Fadvisory\nidentity, escalation criteria, useful operator summary and source coverage.\nRepeated identities keep their locations together. No arbitrary finding count\nis silently discarded. Runtime byte and model-turn budgets still apply; for a\nlarge audit, consume its bounded result parts and retain the overall scope.\n\nA parent can pass a current CVE result directly while its workflow is still open.\nThere is no requirement to fabricate a sealed parent receipt first. The final\nparent receipt records the actual provider and triage steps. If an independent\nconsumer needs sealed evidence, verify the original receipt tree through native\nreceipt tools and retrieve the declared claim; a receipt proves recorded claim\nintegrity, not external truth.\n\nPartial scans are useful: triage the known findings now and keep the scan's\ncontinuation and previous result-part references. Inline findings may cover only\none part. An empty part is not a clean overall review. `no_matches_in_scope` is\navailable only for a complete selected scan with full inventory coverage, no\nomissions and all observations present. Unknown exposure remains unknown even\nwhen scan coverage is complete. The review never certifies a project secure.\n\n## Advisory drafting and recovery\n\n`advisory` takes the exact validated review and an audience, then prepares a\ntitle, summary, body, affected advisory ids and disclosure checklist. It reuses\nthe findings and remediation rather than rescanning or reclassifying the source.\nThe result is `ready_for_review`, `not_published` and `not_called`; no repository,\nemail or other provider is invoked. Publication is a separate authorized action.\n\nMissing identities, omitted assessments, unbound exposure references and invented\nfix versions produce `needs_more_evidence` while retaining the known findings.\nCorrect the precise missing input or assessment. Continue the original audit or\nread its earlier result parts when coverage is incomplete. Never replace missing\nevidence with a receipt-shaped string, silently shorten the findings list, or\nreport an incomplete scan as a negative result.\n\n## Agent task: vuln-triage-assess\n\nUse `triage_context.findings` and the supplied deployment context. Return\n`risk_assessment_draft` with `decision` (`remediate`, `monitor` or `needs_human`),\n`operator_summary.summary`, and `advisory_assessments`. Each assessment contains\nthe unchanged `finding_key`, `priority` (`urgent`, `high`, `normal`, `low` or\n`unknown`), `confidence` (`high`, `medium`, `low`), `exposure` (`confirmed` or\n`not_established`), `exposure_evidence` ids, a substantive `rationale` and a\nconcrete `recommendation`. Add `fixed_version` only from the matching supplied\nadvisory's fixed events. Cover every finding once; do not invent findings,\ndeployment evidence, independent verification or completed remediation.\n\n## Agent task: vuln-triage-advisory\n\nReturn `advisory_draft` with title, summary, body, affected_advisory_ids and\ndisclosure_checklist. Cite only admitted ids. Preserve partial coverage and\nunknown exposure; do not turn a suggested upgrade into a completed deployment.\nDo not claim publication or provider execution.\n",{"name":5,"description":7},"main","14cf84bcc80d7abf0008335efac4d92aacfa682e","skills\u002Fvuln-triage",108,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx","https:\u002F\u002Frunx.ai","https:\u002F\u002Fgithub.com\u002Frunxhq","the governed runtime for agent skills","2026-11-13 21:42:05",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add runxhq\u002Frunx --skill vuln-triage",{"tool":56,"command":57},"bunx","bunx skills add runxhq\u002Frunx --skill vuln-triage",{"tool":59,"command":60},"pnpm","pnpm dlx skills add runxhq\u002Frunx --skill vuln-triage","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002FSKILL.md",true,[64,70,74,78,84,88,92,96,100,104,108,112,116,120,126],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"eval_queries.json","REFERENCE","参考文档",2246,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002Feval_queries.json",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"evals\u002Fevals.json",939,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002Fevals\u002Fevals.json",{"path":75,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":76,"sourceHtmlUrl":77},"evals\u002Ffiles\u002Fcurrent-risk-review.json",3536,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002Fevals\u002Ffiles\u002Fcurrent-risk-review.json",{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"mark.svg","ASSET","资产文件",501,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002Fmark.svg",{"path":85,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":86,"sourceHtmlUrl":87},"packets\u002Fadvisory.v1.schema.json",472,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002Fpackets\u002Fadvisory.v1.schema.json",{"path":89,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":90,"sourceHtmlUrl":91},"packets\u002Fscan.v1.schema.json",3352,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002Fpackets\u002Fscan.v1.schema.json",{"path":93,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fcatalog.md",203,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002Freferences\u002Fcatalog.md",{"path":97,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fmark-license.md",3208,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002Freferences\u002Fmark-license.md",{"path":101,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":102,"sourceHtmlUrl":103},"run.yaml",6883,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002Frun.yaml",{"path":105,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":106,"sourceHtmlUrl":107},"tests\u002Fcomposes-in-workflow.yaml",1491,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002Ftests\u002Fcomposes-in-workflow.yaml",{"path":109,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":110,"sourceHtmlUrl":111},"tests\u002Fscan-rejects-invented-assessment.yaml",1459,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002Ftests\u002Fscan-rejects-invented-assessment.yaml",{"path":113,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":114,"sourceHtmlUrl":115},"tests\u002Fscan-rejects-unverified-evidence.yaml",329,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002Ftests\u002Fscan-rejects-unverified-evidence.yaml",{"path":117,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":118,"sourceHtmlUrl":119},"tests\u002Fscan-verified-finding.yaml",1757,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002Ftests\u002Fscan-verified-finding.yaml",{"path":121,"resourceType":122,"resourceTypeDesc":123,"sizeBytes":124,"sourceHtmlUrl":125},"vuln-triage.mjs","SCRIPT","脚本",12983,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002Fvuln-triage.mjs",{"path":127,"resourceType":122,"resourceTypeDesc":123,"sizeBytes":128,"sourceHtmlUrl":129},"vuln-triage.test.mjs",7156,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002Fvuln-triage.test.mjs",[131,157,180,196,213,228],{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":138,"publishedAt":36},"01M6R60D2HHP5C47QZ7ZBYBHSM","webhook-handoff","Validate a runx execution context and deliver a governed payload once to an n8n Cloud workflow webhook or a Zapier Catch Hook, with exact approval and the receiver's acknowledgement receipted.","https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fwebhook-handoff\u002FSKILL.md",[137],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[139,140,141,142,12,143,144,145,146,147,148,149,150,151,152,153,154,155,156],"webhook","handoff","webhook handoff","hook","context","approval","validate","catch","with","zapier","workflow","execution","acknowledgement","deliver","receiver","n8n","payload","cloud",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":36},"01M6R609BT4F4MFVK9M2YZPQTV","web-search","Discover a bounded set of fresh web source candidates from one explicit search query, preserve provider evidence and reported cost, and prepare source selection for fetching and research.","https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fweb-search\u002FSKILL.md",[],[164,165,166,31,167,168,169,170,171,172,173,174,175,176,177,178,179],"web search","search","web","query","selection","provider","for","discover","evidence","SET","fresh","cost","bounded","prepare","source","research",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":186,"publishedAt":36},"01M6R5ZV4Z3FK8AHATF7AARXYD","web-fetch","Fetch and extract one public web source, optionally restrict its hosts, and return the content by digest with full provenance.","https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fweb-fetch\u002FSKILL.md",[],[166,187,188,189,190,191,192,193,194,147,195,178],"web fetch","fetch","extract","content","full","public","digest","hosts","provenance",{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":200,"categories":201,"keywords":203,"publishedAt":36},"01M6R5Z9RR7V456TAW4J5AJG0R","twitter","Govern X (Twitter) account work through three lanes: evidence reads, typed act plans for posting and account hygiene, and gated execution with per-act provider evidence. Nothing reaches a live timeline or mutates an account without an explicit approval recorded in the receipt.","https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Ftwitter\u002FSKILL.md",[202],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[198,172,204,205,144,206,207,208,209,210,147,211,150,169,170,212],"posting","hygiene","timeline","live","act","gated","work","plans","three",{"skillNo":214,"name":215,"nameZh":6,"description":216,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":217,"categories":218,"keywords":220,"publishedAt":36},"01M6R5Z3XRVR0V5XTES05XJRV8","team-delegate","Divide bounded work across an operator-selected team and return exact member assignments with source context, scope ceilings and acceptance checks.","https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fteam-delegate\u002FSKILL.md",[219],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[221,222,223,224,176,143,178,225,210,147,226,227],"team delegate","team","delegate","scope","operator","across","acceptance",{"skillNo":229,"name":230,"nameZh":6,"description":231,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":232,"categories":233,"keywords":235,"publishedAt":36},"01M6R5YRXFTX914206WAEY5BD8","taste-profile","Build a scoped taste profile packet from examples, preferences, and explicit dislikes so downstream agents can make style decisions without inventing the user's taste.","https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-profile\u002FSKILL.md",[234],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[236,237,238,239,240,241,242,243,244,245,246,247],"taste","profile","taste profile","make","user","build","style","examples","can","decisions","preferences","scoped"]