[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DF0N2CZ4SNNMZDSPK5X3JH":3,"skill-same:01M7DF0N2CZ4SNNMZDSPK5X3JH":123},{"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":15,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":13,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M7DF0N2CZ4SNNMZDSPK5X3JH","fmri-bids",null,"Inspect and audit BIDS fMRI datasets with bidser: inherited metadata, derivatives, events, confounds, and acquisition matching. Use for dataset discovery or analysis readiness; do not fit models or preprocess images.","bbuchsbaum\u002Fbrbskills","bbuchsbaum","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F53819?v=4","01M7DEQDWCB5Q14MV6V9QK719R","01M7DEQDX2QYX57H9RFJGRH22C",0,"MIT","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: fmri-bids\ndescription: \"Inspect and audit BIDS fMRI datasets with bidser: inherited metadata, derivatives, events, confounds, and acquisition matching. Use for dataset discovery or analysis readiness; do not fit models or preprocess images.\"\nlicense: MIT\ncompatibility: Requires local filesystem access; R for package execution and Python 3.10+ for optional helpers.\nmetadata:\n  version: \"0.1.0\"\n  reviewed: \"2026-09-27\"\n---\n\n# BIDS discovery with bidser\n\nProduce a traceable inventory and an analysis-readiness assessment before asking\nthe user questions answered by files. This skill stands alone; group analysis\nand first-level fitting are not required.\n\nFor a new analysis, read the [operating contract](references\u002Foperating-contract.md).\nUse [capability checks](references\u002Fcapabilities.md) before relying on unfamiliar\ninstalled arguments. Read the [discovery procedure](references\u002Fdiscovery.md), then\nuse `scripts\u002Fdiscover_bids.R` for an initial file\u002Fmetadata\u002Fheader inventory. This\nscript is a **first pass**, not a BIDS validator or complete scientific audit.\nFinish the [timing and join checks](references\u002Ftiming-and-joins.md) explicitly.\n\n## Discover cheaply, then selectively inspect\n\nSeparate raw and derivative roots, pipeline\u002Fversion, file representation, task,\nsubject, session, acquisition, direction, run, echo, space, and resolution\u002Fdensity.\nUse `bidser::query_files()` with explicit scope and exact entity selection.\nResolve effective metadata with `get_metadata(..., inherit=TRUE,\nprovenance=TRUE)` and retain its sources. Never ask for a TR already established\nper acquisition; never silently take the first TR when values differ. Check\nmetadata against headers with units. Detect inherited events\u002Fsidecars, ambiguous\nsame-level sidecars, stale indexes, alternate representations, and missing files.\n\nInspect events and confounds locally: schema\u002Funits, timing origin, durations,\ncondition counts, missingness, available confound sets, rows vs volumes, and\nnonsteady-state handling. Condition labels and metadata can suggest a task but\ncannot establish the user's hypothesis or contrast direction. Negative onsets\nand zero-duration events are not inherently invalid. Do not shift onsets merely\nbecause metadata records volumes discarded before the stored image.\n\nFor onboarding, use [events to candidate designs](references\u002Fevents-to-design.md)\nto identify factors, modulators, phases and candidate contrasts from those files.\nReturn evidence-backed proposals and remaining questions; proposing a design\ndoes not require fitting a model or inventing the study's primary hypothesis.\n\n## Match by meaning, not order\n\nUse full acquisition keys and explicit projection rules for event\u002Fconfound joins.\nOne event file may legitimately serve several echoes; several BOLD representations\nmust not become extra runs or subjects. Check cardinalities and exclusions.\nA mask and a space label are insufficient without grid\u002Faffine compatibility.\nReport unsupported CIFTI\u002Fsurface, nonuniform timing, or other adapter limits rather\nthan coercing data to a different representation without approval.\n\nFor the source-reviewed fmrireg importer, `from_bids()` is a convenience path,\nnot a universal discovery oracle: it orders by numeric run, selects the first TR,\nand uses a single supplied mask. Certify its preconditions or create explicit\nbindings through `as_manifest()` downstream. Do not send session\u002Fecho filters in\n`...` and assume they filter scans; those arguments go to confounds.\n\n## Handoff\n\nWrite inventory\u002Fprovenance, validation states, exact selections, unresolved\nscientific questions, and a concise dataset card. Use the [artifact contract](references\u002Fartifact-contracts.md).\nRun the official BIDS validator locally when available and authorized; preserve\nversion and structured findings. Missing validator or unchecked header\u002Fjoins\nmust remain \"not checked\". File discovery alone never certifies readiness.\nOnly ask about gaps that affect the requested scope. Read only the applicable\npreference fields; do not save new preferences without explicit consent.\n","# BIDS discovery with bidser\n\nProduce a traceable inventory and an analysis-readiness assessment before asking\nthe user questions answered by files. This skill stands alone; group analysis\nand first-level fitting are not required.\n\nFor a new analysis, read the [operating contract](references\u002Foperating-contract.md).\nUse [capability checks](references\u002Fcapabilities.md) before relying on unfamiliar\ninstalled arguments. Read the [discovery procedure](references\u002Fdiscovery.md), then\nuse `scripts\u002Fdiscover_bids.R` for an initial file\u002Fmetadata\u002Fheader inventory. This\nscript is a **first pass**, not a BIDS validator or complete scientific audit.\nFinish the [timing and join checks](references\u002Ftiming-and-joins.md) explicitly.\n\n## Discover cheaply, then selectively inspect\n\nSeparate raw and derivative roots, pipeline\u002Fversion, file representation, task,\nsubject, session, acquisition, direction, run, echo, space, and resolution\u002Fdensity.\nUse `bidser::query_files()` with explicit scope and exact entity selection.\nResolve effective metadata with `get_metadata(..., inherit=TRUE,\nprovenance=TRUE)` and retain its sources. Never ask for a TR already established\nper acquisition; never silently take the first TR when values differ. Check\nmetadata against headers with units. Detect inherited events\u002Fsidecars, ambiguous\nsame-level sidecars, stale indexes, alternate representations, and missing files.\n\nInspect events and confounds locally: schema\u002Funits, timing origin, durations,\ncondition counts, missingness, available confound sets, rows vs volumes, and\nnonsteady-state handling. Condition labels and metadata can suggest a task but\ncannot establish the user's hypothesis or contrast direction. Negative onsets\nand zero-duration events are not inherently invalid. Do not shift onsets merely\nbecause metadata records volumes discarded before the stored image.\n\nFor onboarding, use [events to candidate designs](references\u002Fevents-to-design.md)\nto identify factors, modulators, phases and candidate contrasts from those files.\nReturn evidence-backed proposals and remaining questions; proposing a design\ndoes not require fitting a model or inventing the study's primary hypothesis.\n\n## Match by meaning, not order\n\nUse full acquisition keys and explicit projection rules for event\u002Fconfound joins.\nOne event file may legitimately serve several echoes; several BOLD representations\nmust not become extra runs or subjects. Check cardinalities and exclusions.\nA mask and a space label are insufficient without grid\u002Faffine compatibility.\nReport unsupported CIFTI\u002Fsurface, nonuniform timing, or other adapter limits rather\nthan coercing data to a different representation without approval.\n\nFor the source-reviewed fmrireg importer, `from_bids()` is a convenience path,\nnot a universal discovery oracle: it orders by numeric run, selects the first TR,\nand uses a single supplied mask. Certify its preconditions or create explicit\nbindings through `as_manifest()` downstream. Do not send session\u002Fecho filters in\n`...` and assume they filter scans; those arguments go to confounds.\n\n## Handoff\n\nWrite inventory\u002Fprovenance, validation states, exact selections, unresolved\nscientific questions, and a concise dataset card. Use the [artifact contract](references\u002Fartifact-contracts.md).\nRun the official BIDS validator locally when available and authorized; preserve\nversion and structured findings. Missing validator or unchecked header\u002Fjoins\nmust remain \"not checked\". File discovery alone never certifies readiness.\nOnly ask about gaps that affect the requested scope. Read only the applicable\npreference fields; do not save new preferences without explicit consent.\n",{"name":5,"license":14,"metadata":24,"description":7,"compatibility":27},{"version":25,"reviewed":26},"0.1.0","2026-09-27","Requires local filesystem access; R for package execution and Python 3.10+ for optional helpers.","main","a5bd39077217516e1456ede5fa15cefb7670d28c","collections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum","2026-11-11 02:55:31",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add bbuchsbaum\u002Fbrbskills --skill fmri-bids",{"tool":40,"command":41},"bunx","bunx skills add bbuchsbaum\u002Fbrbskills --skill fmri-bids",{"tool":43,"command":44},"pnpm","pnpm dlx skills add bbuchsbaum\u002Fbrbskills --skill fmri-bids","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002FSKILL.md",true,[48,54,58,62,66,70,74,78,82,86,89,93,97,101,105,111,115,119],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"agents\u002Fopenai.yaml","REFERENCE","参考文档",266,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002Fagents\u002Fopenai.yaml",{"path":55,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":15},"LICENSE","许可证",1084,{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fartifact-contracts.md",3866,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002Freferences\u002Fartifact-contracts.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fcapabilities.md",2771,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002Freferences\u002Fcapabilities.md",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fdiscovery.md",4551,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002Freferences\u002Fdiscovery.md",{"path":71,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fevents-to-design.md",10124,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002Freferences\u002Fevents-to-design.md",{"path":75,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fnifti-handoff.md",10171,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002Freferences\u002Fnifti-handoff.md",{"path":79,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Foperating-contract.md",5204,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002Freferences\u002Foperating-contract.md",{"path":83,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fsources.md",5607,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002Freferences\u002Fsources.md",{"path":87,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":88},"references\u002Ftiming-and-joins.md","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002Freferences\u002Ftiming-and-joins.md",{"path":90,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Ftrial-patterns-rsa.md",5062,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002Freferences\u002Ftrial-patterns-rsa.md",{"path":94,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":95,"sourceHtmlUrl":96},"schemas\u002Finventory.schema.json",1077,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002Fschemas\u002Finventory.schema.json",{"path":98,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":99,"sourceHtmlUrl":100},"schemas\u002Fplan.schema.json",3962,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002Fschemas\u002Fplan.schema.json",{"path":102,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":103,"sourceHtmlUrl":104},"schemas\u002Fpreferences.schema.json",1394,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002Fschemas\u002Fpreferences.schema.json",{"path":106,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":109,"sourceHtmlUrl":110},"scripts\u002Fdiscover_bids.R","SCRIPT","脚本",5645,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002Fscripts\u002Fdiscover_bids.R",{"path":112,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":113,"sourceHtmlUrl":114},"scripts\u002Fprobe_capabilities.R",2814,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002Fscripts\u002Fprobe_capabilities.R",{"path":116,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":117,"sourceHtmlUrl":118},"scripts\u002Fprofile_table.py",3309,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002Fscripts\u002Fprofile_table.py",{"path":120,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":121,"sourceHtmlUrl":122},"scripts\u002Fworkbench.py",21343,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri-bids\u002Fscripts\u002Fworkbench.py",[124,132,140,148,156,162],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":128,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":19},"01M7DF15136MDRBYSTDHQ2JFSM","neuromosaic","Create neuromosaic fMRI map montages, atlas-annotated cluster reports, or interactive explorers from existing statistical outputs. Use without refitting analyses; distinguish display thresholds from statistical inference.","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Fneuromosaic\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Fneuromosaic\u002FSKILL.md",[],[],{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":136,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":19},"01M7DF10YY163FFFPBSVFT0YDQ","fmrireg","Specify, diagnose, fit, or export first-level task-fMRI GLMs with fmrireg, including HRFs, nuisance baselines, contrasts, and native batch jobs. Use independently of group analysis and reports; not for preprocessing.","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrireg\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrireg\u002FSKILL.md",[],[],{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":144,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":19},"01M7DF0WV14ZWXQKSS0MRY2XWY","fmrigds","Build and validate group-level fMRI analyses with fmrigds from existing effect\u002Fstatistic maps or tables: covariates, uncertainty, repeated measures, corrections, and cohort examination. Does not require first-level refitting.","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002FSKILL.md",[],[],{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":152,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":19},"01M7DF0RNZYSF5DQ8HZ86MCZ20","fmri","Coordinate end-to-end task-fMRI analyses across BIDS discovery, fmrireg models, fmrigds group inference, and neuromosaic reports. Use for multi-stage analysis plans or execution, not a single-package question.","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmri\u002FSKILL.md",[],[],{"skillNo":157,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":158,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":19},"01M7DEZD9H20TPS57Z509SWSRN","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcodex\u002Fneuromosaic\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcodex\u002Fneuromosaic\u002FSKILL.md",[],[],{"skillNo":163,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":164,"sourceHtmlUrl":165,"categories":166,"keywords":167,"publishedAt":19},"01M7DEYXMWRWFGPZNFYR9MMB6C","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcodex\u002Ffmrireg\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcodex\u002Ffmrireg\u002FSKILL.md",[],[]]