[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DETZNH0FSKFZYBY3144DBM":3,"skill-same:01M7DETZNH0FSKFZYBY3144DBM":122},{"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},"01M7DETZNH0FSKFZYBY3144DBM","fmri",null,"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.","bbuchsbaum\u002Fbrbskills","bbuchsbaum","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F53819?v=4","01M7DEQDWCB5Q14MV6V9QK719R","01M7DEQDX2QYX57H9RFJGRH22C",0,"MIT","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: fmri\ndescription: \"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.\"\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# fMRI workbench\n\nTurn the user's scientific question into an inspectable, executable analysis.\nCoordinate stages; do not replace their package APIs or load every reference.\nFor an isolated task, route directly to `fmri-bids`, `fmrireg`, `fmrigds`, or\n`neuromosaic` and stop coordinating. Each is independently installable.\n\n## Start with evidence\n\nRead the [operating contract](references\u002Foperating-contract.md) when creating or\nchanging an analysis. Reuse approved state and preferences before asking anything.\nDiscover which requested stages already have valid inputs. For datasets, use\n`fmri-bids` to inspect local BIDS metadata first. Raw-only data can be inventoried\nbut these four packages do not implement a preprocessing pipeline. If the\nindependent `fmriprep` skill is installed and preprocessing is requested, use it\nfor that stage and record its downstream handoff manifest as\n`fingerprints.preprocessing_handoff` (`path`, `sha256`) in `plan.json`; fit only\nruns it lists as QC-passed. Otherwise record the\npreprocessing handoff and missing capability; never fit raw BOLD or install a\npreprocessor implicitly. Do not assume fMRIPrep completion means analysis readiness.\n\nWhen the question is open, use [events to candidate designs](references\u002Fevents-to-design.md)\nto infer plausible models from event tables and task documentation. Present a few\nsupported candidates and their unresolved meanings before the interview.\nFor trialwise patterns or representational comparisons, read the conditional\n[trial-pattern\u002FRSA guide](references\u002Ftrial-patterns-rsa.md) and verify the required\nspecialist capabilities before planning execution.\n\nPresent a compact **observed \u002F proposed \u002F needs your decision** summary. Resolve\nthe scientific question, estimand, meaningful condition labels, cohort, and\nmaterial ambiguities. Use the [adaptive interview](references\u002Finterview.md).\nDefault to a standard review, no more than two rounds \u002F six material questions\nwhen possible. Do not ask again for facts or choices already supplied. Interaction\nbudget never licenses fabricated metadata or unapproved scientific decisions.\n\n## Plan, test, then execute\n\nSave a plan envelope plus editable native R code. The [execution protocol](references\u002Fexecution.md)\nlinks plan approval to code, inputs, environment and limits. Let package-native\nobjects carry implementation detail: fmrireg templates\u002Fjobs and fmrigds lazy plans.\nUse [artifact contracts](references\u002Fartifact-contracts.md) for handoffs. Persist\nwhat is known, proposed, confirmed, unresolved, or blocked; do not rely on chat\nhistory for resumption. `scripts\u002Fworkbench.py --help` exposes deterministic\nstate, audit, and preference helpers; it is not an analysis engine.\n\nRead and invoke only the next relevant installed stage. Do not assume automatic\ncross-skill dependency installation. If a needed stage is absent, report the\nmissing component; already available standalone work may still proceed. Keep\nparallelization subordinate to scientific dependencies. Run design checks and a\nsmall representative pilot before approved cohort execution. Review new scientific\nissues, not every reversible coding detail. Preserve partial failures.\n\n## Remember only with consent\n\nUse [preferences](references\u002Fpreferences.md) for conditional user\u002Fproject profiles.\nA preference such as motion24 is not an instruction to silently omit unavailable\ncolumns. A B-spline baseline is not a B-spline HRF. Offer to save repeated choices,\nbut write only after explicit consent. Protocol conflicts need an amendment.\n\n## Finish\n\nDeliver the requested outputs, a readable methods\u002Fdecision summary, QC\u002Ffailure\nledger, reproducibility information, and exact remaining limitations. Distinguish\nsource review, executed numerical tests, and real-data validation. Do not present\nuncorrected display clusters as corrected findings or automatically exclude\ninfluential subjects. Keep report sharing and embedded voxel disclosure explicit.\nFor environment differences, load [capabilities](references\u002Fcapabilities.md).\n","# fMRI workbench\n\nTurn the user's scientific question into an inspectable, executable analysis.\nCoordinate stages; do not replace their package APIs or load every reference.\nFor an isolated task, route directly to `fmri-bids`, `fmrireg`, `fmrigds`, or\n`neuromosaic` and stop coordinating. Each is independently installable.\n\n## Start with evidence\n\nRead the [operating contract](references\u002Foperating-contract.md) when creating or\nchanging an analysis. Reuse approved state and preferences before asking anything.\nDiscover which requested stages already have valid inputs. For datasets, use\n`fmri-bids` to inspect local BIDS metadata first. Raw-only data can be inventoried\nbut these four packages do not implement a preprocessing pipeline. If the\nindependent `fmriprep` skill is installed and preprocessing is requested, use it\nfor that stage and record its downstream handoff manifest as\n`fingerprints.preprocessing_handoff` (`path`, `sha256`) in `plan.json`; fit only\nruns it lists as QC-passed. Otherwise record the\npreprocessing handoff and missing capability; never fit raw BOLD or install a\npreprocessor implicitly. Do not assume fMRIPrep completion means analysis readiness.\n\nWhen the question is open, use [events to candidate designs](references\u002Fevents-to-design.md)\nto infer plausible models from event tables and task documentation. Present a few\nsupported candidates and their unresolved meanings before the interview.\nFor trialwise patterns or representational comparisons, read the conditional\n[trial-pattern\u002FRSA guide](references\u002Ftrial-patterns-rsa.md) and verify the required\nspecialist capabilities before planning execution.\n\nPresent a compact **observed \u002F proposed \u002F needs your decision** summary. Resolve\nthe scientific question, estimand, meaningful condition labels, cohort, and\nmaterial ambiguities. Use the [adaptive interview](references\u002Finterview.md).\nDefault to a standard review, no more than two rounds \u002F six material questions\nwhen possible. Do not ask again for facts or choices already supplied. Interaction\nbudget never licenses fabricated metadata or unapproved scientific decisions.\n\n## Plan, test, then execute\n\nSave a plan envelope plus editable native R code. The [execution protocol](references\u002Fexecution.md)\nlinks plan approval to code, inputs, environment and limits. Let package-native\nobjects carry implementation detail: fmrireg templates\u002Fjobs and fmrigds lazy plans.\nUse [artifact contracts](references\u002Fartifact-contracts.md) for handoffs. Persist\nwhat is known, proposed, confirmed, unresolved, or blocked; do not rely on chat\nhistory for resumption. `scripts\u002Fworkbench.py --help` exposes deterministic\nstate, audit, and preference helpers; it is not an analysis engine.\n\nRead and invoke only the next relevant installed stage. Do not assume automatic\ncross-skill dependency installation. If a needed stage is absent, report the\nmissing component; already available standalone work may still proceed. Keep\nparallelization subordinate to scientific dependencies. Run design checks and a\nsmall representative pilot before approved cohort execution. Review new scientific\nissues, not every reversible coding detail. Preserve partial failures.\n\n## Remember only with consent\n\nUse [preferences](references\u002Fpreferences.md) for conditional user\u002Fproject profiles.\nA preference such as motion24 is not an instruction to silently omit unavailable\ncolumns. A B-spline baseline is not a B-spline HRF. Offer to save repeated choices,\nbut write only after explicit consent. Protocol conflicts need an amendment.\n\n## Finish\n\nDeliver the requested outputs, a readable methods\u002Fdecision summary, QC\u002Ffailure\nledger, reproducibility information, and exact remaining limitations. Distinguish\nsource review, executed numerical tests, and real-data validation. Do not present\nuncorrected display clusters as corrected findings or automatically exclude\ninfluential subjects. Keep report sharing and embedded voxel disclosure explicit.\nFor environment differences, load [capabilities](references\u002Fcapabilities.md).\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","claude\u002Ffmri","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",{"tool":40,"command":41},"bunx","bunx skills add bbuchsbaum\u002Fbrbskills --skill fmri",{"tool":43,"command":44},"pnpm","pnpm dlx skills add bbuchsbaum\u002Fbrbskills --skill fmri","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002FSKILL.md",true,[48,52,58,62,66,70,74,78,82,86,90,94,98,102,106,112,116],{"path":49,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":15},"LICENSE","许可证",1084,{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fartifact-contracts.md","REFERENCE","参考文档",3866,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002Freferences\u002Fartifact-contracts.md",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fcapabilities.md",2771,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002Freferences\u002Fcapabilities.md",{"path":63,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fevents-to-design.md",10124,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002Freferences\u002Fevents-to-design.md",{"path":67,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fexecution.md",3785,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002Freferences\u002Fexecution.md",{"path":71,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Finterview.md",4437,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002Freferences\u002Finterview.md",{"path":75,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fnifti-handoff.md",10171,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002Freferences\u002Fnifti-handoff.md",{"path":79,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Foperating-contract.md",5204,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002Freferences\u002Foperating-contract.md",{"path":83,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fpreferences.md",3632,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002Freferences\u002Fpreferences.md",{"path":87,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fsources.md",5607,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002Freferences\u002Fsources.md",{"path":91,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Ftrial-patterns-rsa.md",5062,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002Freferences\u002Ftrial-patterns-rsa.md",{"path":95,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":96,"sourceHtmlUrl":97},"schemas\u002Finventory.schema.json",1077,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002Fschemas\u002Finventory.schema.json",{"path":99,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":100,"sourceHtmlUrl":101},"schemas\u002Fplan.schema.json",3962,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002Fschemas\u002Fplan.schema.json",{"path":103,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":104,"sourceHtmlUrl":105},"schemas\u002Fpreferences.schema.json",1394,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002Fschemas\u002Fpreferences.schema.json",{"path":107,"resourceType":108,"resourceTypeDesc":109,"sizeBytes":110,"sourceHtmlUrl":111},"scripts\u002Fprobe_capabilities.R","SCRIPT","脚本",2814,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002Fscripts\u002Fprobe_capabilities.R",{"path":113,"resourceType":108,"resourceTypeDesc":109,"sizeBytes":114,"sourceHtmlUrl":115},"scripts\u002Fworkbench.py",21343,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002Fscripts\u002Fworkbench.py",{"path":117,"resourceType":118,"resourceTypeDesc":119,"sizeBytes":120,"sourceHtmlUrl":121},"SHA256SUMS","OTHER","其他",1557,"https:\u002F\u002Fgithub.com\u002Fbbuchsbaum\u002Fbrbskills\u002Fblob\u002Fmain\u002Fclaude\u002Ffmri\u002FSHA256SUMS",[123,131,139,147,153,161],{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":127,"sourceHtmlUrl":128,"categories":129,"keywords":130,"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":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},"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":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},"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":148,"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":149,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":19},"01M7DF0RNZYSF5DQ8HZ86MCZ20","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":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":157,"sourceHtmlUrl":158,"categories":159,"keywords":160,"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":162,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":163,"sourceHtmlUrl":164,"categories":165,"keywords":166,"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",[],[]]