[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DF0WV14ZWXQKSS0MRY2XWY":3,"skill-same:01M7DF0WV14ZWXQKSS0MRY2XWY":130},{"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},"01M7DF0WV14ZWXQKSS0MRY2XWY","fmrigds",null,"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.","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\u002Ffmrigds\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: fmrigds\ndescription: \"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.\"\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# Group fMRI with fmrigds\n\nAccept existing subject estimates\u002Fmaps\u002Ftables or a first-level handoff; do not\nrequire BIDS or fmrireg. For an API question, read only [API](references\u002Fapi.md).\nFor a new analysis also read the [operating contract](references\u002Foperating-contract.md)\nand [inference decisions](references\u002Finference.md). Check [installed capabilities](references\u002Fcapabilities.md).\n\n## Establish the observation and estimand\n\nVerify subject identity\u002Forder, independent units, repeated sessions\u002Fconditions,\nspatial alignment, contrast semantics and units, masks, missingness, covariates,\nand the meaning of available assays. Follow the [handoff bridge](references\u002Fhandoff.md).\nFor subject NIfTI beta\u002FSE maps use the [NIfTI recipe](references\u002Fnifti-handoff.md),\nincluding explicit contrast order and coverage masks; import success does not\nverify every image's affine.\nAn SE is not a variance; a z\u002Fp map cannot uniquely supply an effect and its\nsampling variance. Effects without uncertainty can support a suitable unweighted\ngroup model; do not invent unit variance for precision weighting. Repeated runs\nare not independent subjects. A fixed-effects teaching example is not a default\npopulation model.\n\nAsk only material unresolved group decisions: estimand\u002Fmodel\u002Fcovariates,\nrepeated-measures structure, uncertainty assumptions, inclusion\u002Fmissingness,\nand correction family. Freeze the proposed model and contrast before inspecting\nits interesting outcomes. Fit neither an unsupported general mixed model nor\na whole-brain correction independently by chunk.\n\n## Build a lazy plan\n\nUse `gds()` or documented `as_gds()` inputs, keyed covariate attachment, explicit\n`reduce()` or appropriate public model helper, and `posthoc()` where justified.\nInspect `explain()` \u002F `preview()` \u002F `validate()` before approved `compute()`.\n`assets\u002Fgroup_template.R` constructs a lazy plan from explicit inputs; it does\nnot execute. `scripts\u002Fsmoke_group.R` checks a known fixed-effects arithmetic\nidentity on tiny synthetic data, not a production model choice.\n\nChoose public registered methods supported by the installed version. The reviewed\nLMM family is intentionally restricted: do not assume arbitrary lmer syntax,\nrandom effects, missing layouts, or covariance structures. Unsupported science\nrequires an explicit alternative adapter\u002Fmodel, not silent simplification.\n\n## Examine, correct, export\n\nUse `examine_group()` where supported to separate validity concerns, model\nsurprise, and influence. A review priority is not an exclusion rule. Record\nsensitivity analyses without redefining the primary cohort opportunistically.\nPreserve actual per-sample N, model\u002Fvariance diagnostics, convergence flags,\nheterogeneity where relevant, and missingness. Correct over the declared full\nfamily, accounting explicitly for mask, contrasts, sidedness, and post-selection.\nRetain unthresholded effects\u002Fstatistics, uncertainty, p\u002Fq and rejection masks.\n\nComplete the [artifact contract](references\u002Fartifact-contracts.md) with a frozen\ninference manifest. A reporting stage is optional; do not rerun a model just to\nmake maps look more impressive. A report renderer's cluster threshold is not a\nstatistical correction. Deliver outputs and limitations, including any failed\nsubjects\u002Fsamples, numerical approximations, or unsupported assumptions.\n","# Group fMRI with fmrigds\n\nAccept existing subject estimates\u002Fmaps\u002Ftables or a first-level handoff; do not\nrequire BIDS or fmrireg. For an API question, read only [API](references\u002Fapi.md).\nFor a new analysis also read the [operating contract](references\u002Foperating-contract.md)\nand [inference decisions](references\u002Finference.md). Check [installed capabilities](references\u002Fcapabilities.md).\n\n## Establish the observation and estimand\n\nVerify subject identity\u002Forder, independent units, repeated sessions\u002Fconditions,\nspatial alignment, contrast semantics and units, masks, missingness, covariates,\nand the meaning of available assays. Follow the [handoff bridge](references\u002Fhandoff.md).\nFor subject NIfTI beta\u002FSE maps use the [NIfTI recipe](references\u002Fnifti-handoff.md),\nincluding explicit contrast order and coverage masks; import success does not\nverify every image's affine.\nAn SE is not a variance; a z\u002Fp map cannot uniquely supply an effect and its\nsampling variance. Effects without uncertainty can support a suitable unweighted\ngroup model; do not invent unit variance for precision weighting. Repeated runs\nare not independent subjects. A fixed-effects teaching example is not a default\npopulation model.\n\nAsk only material unresolved group decisions: estimand\u002Fmodel\u002Fcovariates,\nrepeated-measures structure, uncertainty assumptions, inclusion\u002Fmissingness,\nand correction family. Freeze the proposed model and contrast before inspecting\nits interesting outcomes. Fit neither an unsupported general mixed model nor\na whole-brain correction independently by chunk.\n\n## Build a lazy plan\n\nUse `gds()` or documented `as_gds()` inputs, keyed covariate attachment, explicit\n`reduce()` or appropriate public model helper, and `posthoc()` where justified.\nInspect `explain()` \u002F `preview()` \u002F `validate()` before approved `compute()`.\n`assets\u002Fgroup_template.R` constructs a lazy plan from explicit inputs; it does\nnot execute. `scripts\u002Fsmoke_group.R` checks a known fixed-effects arithmetic\nidentity on tiny synthetic data, not a production model choice.\n\nChoose public registered methods supported by the installed version. The reviewed\nLMM family is intentionally restricted: do not assume arbitrary lmer syntax,\nrandom effects, missing layouts, or covariance structures. Unsupported science\nrequires an explicit alternative adapter\u002Fmodel, not silent simplification.\n\n## Examine, correct, export\n\nUse `examine_group()` where supported to separate validity concerns, model\nsurprise, and influence. A review priority is not an exclusion rule. Record\nsensitivity analyses without redefining the primary cohort opportunistically.\nPreserve actual per-sample N, model\u002Fvariance diagnostics, convergence flags,\nheterogeneity where relevant, and missingness. Correct over the declared full\nfamily, accounting explicitly for mask, contrasts, sidedness, and post-selection.\nRetain unthresholded effects\u002Fstatistics, uncertainty, p\u002Fq and rejection masks.\n\nComplete the [artifact contract](references\u002Fartifact-contracts.md) with a frozen\ninference manifest. A reporting stage is optional; do not rerun a model just to\nmake maps look more impressive. A report renderer's cluster threshold is not a\nstatistical correction. Deliver outputs and limitations, including any failed\nsubjects\u002Fsamples, numerical approximations, or unsupported assumptions.\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\u002Ffmrigds","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 fmrigds",{"tool":40,"command":41},"bunx","bunx skills add bbuchsbaum\u002Fbrbskills --skill fmrigds",{"tool":43,"command":44},"pnpm","pnpm dlx skills add bbuchsbaum\u002Fbrbskills --skill fmrigds","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002FSKILL.md",true,[48,54,60,64,68,72,76,80,84,88,92,96,100,104,108,112,116,122,126],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"agents\u002Fopenai.yaml","REFERENCE","参考文档",262,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002Fagents\u002Fopenai.yaml",{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"assets\u002Fgroup_template.R","ASSET","资产文件",1249,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002Fassets\u002Fgroup_template.R",{"path":61,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":15},"LICENSE","许可证",1084,{"path":65,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fapi.md",2817,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002Freferences\u002Fapi.md",{"path":69,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fartifact-contracts.md",3866,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002Freferences\u002Fartifact-contracts.md",{"path":73,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fcapabilities.md",2771,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002Freferences\u002Fcapabilities.md",{"path":77,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fevents-to-design.md",10124,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002Freferences\u002Fevents-to-design.md",{"path":81,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fhandoff.md",2498,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002Freferences\u002Fhandoff.md",{"path":85,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Finference.md",4137,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002Freferences\u002Finference.md",{"path":89,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fnifti-handoff.md",10171,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002Freferences\u002Fnifti-handoff.md",{"path":93,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Foperating-contract.md",5204,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002Freferences\u002Foperating-contract.md",{"path":97,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fsources.md",5607,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002Freferences\u002Fsources.md",{"path":101,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Ftrial-patterns-rsa.md",5062,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002Freferences\u002Ftrial-patterns-rsa.md",{"path":105,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":106,"sourceHtmlUrl":107},"schemas\u002Finventory.schema.json",1077,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002Fschemas\u002Finventory.schema.json",{"path":109,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":110,"sourceHtmlUrl":111},"schemas\u002Fplan.schema.json",3962,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002Fschemas\u002Fplan.schema.json",{"path":113,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":114,"sourceHtmlUrl":115},"schemas\u002Fpreferences.schema.json",1394,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002Fschemas\u002Fpreferences.schema.json",{"path":117,"resourceType":118,"resourceTypeDesc":119,"sizeBytes":120,"sourceHtmlUrl":121},"scripts\u002Fprobe_capabilities.R","SCRIPT","脚本",2814,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002Fscripts\u002Fprobe_capabilities.R",{"path":123,"resourceType":118,"resourceTypeDesc":119,"sizeBytes":124,"sourceHtmlUrl":125},"scripts\u002Fsmoke_group.R",1969,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002Fscripts\u002Fsmoke_group.R",{"path":127,"resourceType":118,"resourceTypeDesc":119,"sizeBytes":128,"sourceHtmlUrl":129},"scripts\u002Fworkbench.py",21343,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fcollections\u002Ffmri-workbench\u002Fskills\u002Ffmrigds\u002Fscripts\u002Fworkbench.py",[131,139,147,155,163,169],{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":135,"sourceHtmlUrl":136,"categories":137,"keywords":138,"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":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":143,"sourceHtmlUrl":144,"categories":145,"keywords":146,"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":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":151,"sourceHtmlUrl":152,"categories":153,"keywords":154,"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":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":159,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":19},"01M7DF0N2CZ4SNNMZDSPK5X3JH","fmri-bids","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.","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",[],[],{"skillNo":164,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":165,"sourceHtmlUrl":166,"categories":167,"keywords":168,"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":170,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":171,"sourceHtmlUrl":172,"categories":173,"keywords":174,"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",[],[]]