[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QH3R7SECEWG190H1APNFFD":3,"skill-same:01M6QH3R7SECEWG190H1APNFFD":98},{"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":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":14,"repositoryHtmlUrl":56,"repositoryHomepageUrl":57,"ownerHtmlUrl":58,"ownerBlogUrl":59,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M6QH3R7SECEWG190H1APNFFD","nwb-conversion",null,"Converts neuroscience acquisition data to Neurodata Without Borders files with NeuroConv and PyNWB, preserves metadata and timebases, checks evidence-based clock alignment, and produces schema validation, NWB Inspector findings and round-trip checks. Use for NWB conversion and synchronization of planar single-channel two-photon TIFF imaging plus timestamped behavioral position CSV; this skill does not perform spike sorting or claim tested support for arbitrary acquisition formats.","Tashima-Tarsh\u002FDisha6.6","Tashima-Tarsh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269906498?v=4","01M6PBH98X03XERH0HFT4PFB1P","NITISH KUMAR","01M6PBH9DA0M6KM3Z12P848F0K",0,"MIT","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-nwb-conversion\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"nwb conversion","conversion","alignment","formats","imaging","sorting","scientific","neuroscience","local","claim","files","file access","only","acquisition","synchronization","access","credentials","data","network","support","2026-11-10 10:12:30",false,"---\nname: nwb-conversion\ndescription: Converts neuroscience acquisition data to Neurodata Without Borders files with NeuroConv and PyNWB, preserves metadata and timebases, checks evidence-based clock alignment, and produces schema validation, NWB Inspector findings and round-trip checks. Use for NWB conversion and synchronization of planar single-channel two-photon TIFF imaging plus timestamped behavioral position CSV; this skill does not perform spike sorting or claim tested support for arbitrary acquisition formats.\nlicense: MIT\ncompatibility: Requires Python 3.12 with neuroconv[tiff] 0.10.2, PyNWB 4.2.0, NWB Inspector 0.7.2, roiextractors 0.10.0, tifffile 2026.9.20, zarr 2.18.7 and hdmf-zarr 0.11.3. Local HDF5 file access is required. Network is needed only for installation; no credentials.\nmetadata:\n  version: \"1.1\"\n  skill-author: K-Dense Inc.\n  last-reviewed: \"2026-10-01\"\n  upstream-neuroconv: \"0.10.2\"\n  upstream-pynwb: \"4.2.0\"\n  upstream-nwbinspector: \"0.7.2\"\ncategory: \"scientific-computing\"\n---\n\n# Validated NWB conversion\n\n## Supported streams\n\nThe executable workflow covers two explicit input streams in one session:\n\n| Input | NWB representation | Tested constraints |\n| --- | --- | --- |\n| Two-photon grayscale multi-page TIFF + frame timestamps CSV | Acquisition `TwoPhotonSeries` named `Imaging` through NeuroConv | One channel, one plane, one 2D image per page, fixed shape and dtype |\n| Calibrated position CSV (`time_s,x,y`) | Behavior `Position` \u002F `SpatialSeries` through PyNWB | Coordinates in m, cm or mm; converted to meters without temporal resampling |\n\nOther acquisition readers require their own format-specific tests. In particular, this helper does\nnot decode SpikeGLX, Open Ephys, multichannel TIFF, volumetric TIFF, compressed video, or pixel-to-world\ncalibration. Do not rename an arbitrary numeric table to a supported stream.\n\n## Install the tested environment\n\n```bash\nuv venv --python 3.12 nwb-env\nuv pip install --python nwb-env\u002Fbin\u002Fpython 'neuroconv[tiff]==0.10.2' pynwb==4.2.0 \\\n  nwbinspector==0.7.2 roiextractors==0.10.0 tifffile==2026.9.20 \\\n  zarr==2.18.7 hdmf-zarr==0.11.3\n```\n\nKeep both Zarr pins even for an HDF5-only conversion: NeuroConv 0.10.2 imports its backend\nconfiguration modules at startup, and the tested unconstrained Zarr 3.4.0 installation failed on\n`zarr.codec_registry`. The pinned environment ran the real conversion, PyNWB validation and\nInspector successfully on macOS ARM64. The dependency resolver supplies NumPy and HDF5 support.\nThese are compatibility pins, not claims that Zarr 2 and hdmf-zarr 0.11.3 are the latest releases.\nCurrent interface checks and the tested dependency exception are recorded in\n[references\u002Fupstream-review.md](references\u002Fupstream-review.md).\n\n## Workflow\n\n1. Inventory the actual inputs and acquisition metadata. Identify image plane\u002Fchannel, optical\n   settings, subject\u002Fsession identifiers, timezone, behavior coordinate system, units and the\n   timestamp clock for every stream. Preserve originals. Do not replace missing metadata with\n   plausible defaults from a sample config.\n2. Copy [assets\u002Fsession-template.json](assets\u002Fsession-template.json) beside the raw data and\n   replace the explicitly synthetic values. Paths resolve from that JSON file. Read\n   [references\u002Finput-contract.md](references\u002Finput-contract.md) for the exact CSV and metadata\n   contract and the pulse-pair variant. TIFF pixels are retained as acquired; a raw arbitrary-unit\n   intensity does not become a photon count merely by changing its unit label.\n3. Establish the common timebase from acquisition evidence. Frame timestamps must already be\n   reference-clock seconds since the timezone-aware session start. For position, provide either\n   a documented shared clock or matched synchronization pulses. The helper fits one affine clock\n   transform, checks its residual against a specified tolerance, and refuses extrapolation beyond\n   the pulse range. It never estimates synchronization from coincident-looking neural\u002Fbehavioral\n   signals. Clock resets or nonlinear drift require an explicitly validated piecewise mapping.\n4. Execute the converter. Inputs must have finite, strictly increasing timestamps and matching\n   image\u002Ftimestamp counts. Explicitly declare one channel and one plane; known TIFF channel\u002Fplane\n   metadata must agree. Grayscale pages alone cannot exclude undocumented interleaving.\n   The acquisition samples stay intact; only coordinate units and, when\n   evidenced, behavior timestamps are transformed.\n5. Read the `.validation.json` alongside the NWB file. Schema compliance, Inspector findings and\n   data equality answer different questions. The script exits with an error for schema failures\n   and flags critical Inspector findings for review in the report. Review all findings in context;\n   successful validation cannot establish that anatomical labels, pulse pairing or calibration\n   supplied by the user are correct.\n6. Deliver the NWB, validation JSON, original conversion config and an explanation of remaining\n   metadata gaps or Inspector findings. No upload or archive submission is part of this workflow.\n\n## Execute\n\nRun the following from the skill directory, with paths to the actual analysis files:\n\n```bash\nnwb-env\u002Fbin\u002Fpython scripts\u002Fconvert_session.py \u002Fpath\u002Fto\u002Fsession.json --output \u002Fpath\u002Fto\u002Fsession.nwb\n```\n\n`nwb-env` must point to the environment created above; the absolute example input paths are\nillustrative. The command requires a `.nwb` output and refuses to overwrite an existing NWB or\nvalidation report. Output contains source and converter checksums,\npackage versions, full supplied metadata, units and clock-fit provenance in both a scratch record\nand the validation report. When adapting this command for large data, TIFF writes are iterative\nand equality checking loads one frame at a time; position CSV currently loads into memory.\nRound-trip checks also verify dtype, unit scaling, optical-channel links, subject metadata,\nposition reference frame, common time origin and embedded provenance. Inspector findings requiring\nreview appear in the CLI summary; exit zero alone does not mean the file is scientifically correct.\nAn exception during writing or round-trip checks can leave an incomplete NWB without a report;\nretain the error and use a fresh output path after correcting the cause.\n\nThe real-library test converts eight non-square uint16 images with irregular frame timing plus\nfour position samples, asserts exact pixel and timestamp round trips, and checks centimeter-to-meter\nconversion. A second integration test recovers a known 1000-ppm clock drift and 50-ms offset from\nthree matched pulses. Duplicate timestamps, mismatched frame counts, absent clock evidence,\nnonlinear pulse disagreement and missing timezone are rejection cases. The mapping is\nTIFF `(time,y,x)` to NWB `(time,x,y)`, explicitly checked against every transposed source page. NWB Inspector flags the short fixture\nwith a critical orientation heuristic because width exceeds frame count; the report retains that\nfinding and adds the exact frame\u002Ftimestamp equality evidence. No transpose is performed merely to\nsatisfy a longest-axis heuristic.\n\n## Primary references\n\n- [NeuroConv TIFF conversion](https:\u002F\u002Fneuroconv.readthedocs.io\u002Fen\u002Fstable\u002Fconversion_examples_gallery\u002Fimaging\u002Ftiff.html)\n- [NeuroConv temporal alignment](https:\u002F\u002Fneuroconv.readthedocs.io\u002Fen\u002Fstable\u002Fuser_guide\u002Ftemporal_alignment.html)\n- [PyNWB](https:\u002F\u002Fgithub.com\u002FNeurodataWithoutBorders\u002Fpynwb)\n- [NWB Inspector and its relation to schema validation](https:\u002F\u002Fgithub.com\u002FNeurodataWithoutBorders\u002Fnwbinspector)\n","# Validated NWB conversion\n\n## Supported streams\n\nThe executable workflow covers two explicit input streams in one session:\n\n| Input | NWB representation | Tested constraints |\n| --- | --- | --- |\n| Two-photon grayscale multi-page TIFF + frame timestamps CSV | Acquisition `TwoPhotonSeries` named `Imaging` through NeuroConv | One channel, one plane, one 2D image per page, fixed shape and dtype |\n| Calibrated position CSV (`time_s,x,y`) | Behavior `Position` \u002F `SpatialSeries` through PyNWB | Coordinates in m, cm or mm; converted to meters without temporal resampling |\n\nOther acquisition readers require their own format-specific tests. In particular, this helper does\nnot decode SpikeGLX, Open Ephys, multichannel TIFF, volumetric TIFF, compressed video, or pixel-to-world\ncalibration. Do not rename an arbitrary numeric table to a supported stream.\n\n## Install the tested environment\n\n```bash\nuv venv --python 3.12 nwb-env\nuv pip install --python nwb-env\u002Fbin\u002Fpython 'neuroconv[tiff]==0.10.2' pynwb==4.2.0 \\\n  nwbinspector==0.7.2 roiextractors==0.10.0 tifffile==2026.9.20 \\\n  zarr==2.18.7 hdmf-zarr==0.11.3\n```\n\nKeep both Zarr pins even for an HDF5-only conversion: NeuroConv 0.10.2 imports its backend\nconfiguration modules at startup, and the tested unconstrained Zarr 3.4.0 installation failed on\n`zarr.codec_registry`. The pinned environment ran the real conversion, PyNWB validation and\nInspector successfully on macOS ARM64. The dependency resolver supplies NumPy and HDF5 support.\nThese are compatibility pins, not claims that Zarr 2 and hdmf-zarr 0.11.3 are the latest releases.\nCurrent interface checks and the tested dependency exception are recorded in\n[references\u002Fupstream-review.md](references\u002Fupstream-review.md).\n\n## Workflow\n\n1. Inventory the actual inputs and acquisition metadata. Identify image plane\u002Fchannel, optical\n   settings, subject\u002Fsession identifiers, timezone, behavior coordinate system, units and the\n   timestamp clock for every stream. Preserve originals. Do not replace missing metadata with\n   plausible defaults from a sample config.\n2. Copy [assets\u002Fsession-template.json](assets\u002Fsession-template.json) beside the raw data and\n   replace the explicitly synthetic values. Paths resolve from that JSON file. Read\n   [references\u002Finput-contract.md](references\u002Finput-contract.md) for the exact CSV and metadata\n   contract and the pulse-pair variant. TIFF pixels are retained as acquired; a raw arbitrary-unit\n   intensity does not become a photon count merely by changing its unit label.\n3. Establish the common timebase from acquisition evidence. Frame timestamps must already be\n   reference-clock seconds since the timezone-aware session start. For position, provide either\n   a documented shared clock or matched synchronization pulses. The helper fits one affine clock\n   transform, checks its residual against a specified tolerance, and refuses extrapolation beyond\n   the pulse range. It never estimates synchronization from coincident-looking neural\u002Fbehavioral\n   signals. Clock resets or nonlinear drift require an explicitly validated piecewise mapping.\n4. Execute the converter. Inputs must have finite, strictly increasing timestamps and matching\n   image\u002Ftimestamp counts. Explicitly declare one channel and one plane; known TIFF channel\u002Fplane\n   metadata must agree. Grayscale pages alone cannot exclude undocumented interleaving.\n   The acquisition samples stay intact; only coordinate units and, when\n   evidenced, behavior timestamps are transformed.\n5. Read the `.validation.json` alongside the NWB file. Schema compliance, Inspector findings and\n   data equality answer different questions. The script exits with an error for schema failures\n   and flags critical Inspector findings for review in the report. Review all findings in context;\n   successful validation cannot establish that anatomical labels, pulse pairing or calibration\n   supplied by the user are correct.\n6. Deliver the NWB, validation JSON, original conversion config and an explanation of remaining\n   metadata gaps or Inspector findings. No upload or archive submission is part of this workflow.\n\n## Execute\n\nRun the following from the skill directory, with paths to the actual analysis files:\n\n```bash\nnwb-env\u002Fbin\u002Fpython scripts\u002Fconvert_session.py \u002Fpath\u002Fto\u002Fsession.json --output \u002Fpath\u002Fto\u002Fsession.nwb\n```\n\n`nwb-env` must point to the environment created above; the absolute example input paths are\nillustrative. The command requires a `.nwb` output and refuses to overwrite an existing NWB or\nvalidation report. Output contains source and converter checksums,\npackage versions, full supplied metadata, units and clock-fit provenance in both a scratch record\nand the validation report. When adapting this command for large data, TIFF writes are iterative\nand equality checking loads one frame at a time; position CSV currently loads into memory.\nRound-trip checks also verify dtype, unit scaling, optical-channel links, subject metadata,\nposition reference frame, common time origin and embedded provenance. Inspector findings requiring\nreview appear in the CLI summary; exit zero alone does not mean the file is scientifically correct.\nAn exception during writing or round-trip checks can leave an incomplete NWB without a report;\nretain the error and use a fresh output path after correcting the cause.\n\nThe real-library test converts eight non-square uint16 images with irregular frame timing plus\nfour position samples, asserts exact pixel and timestamp round trips, and checks centimeter-to-meter\nconversion. A second integration test recovers a known 1000-ppm clock drift and 50-ms offset from\nthree matched pulses. Duplicate timestamps, mismatched frame counts, absent clock evidence,\nnonlinear pulse disagreement and missing timezone are rejection cases. The mapping is\nTIFF `(time,y,x)` to NWB `(time,x,y)`, explicitly checked against every transposed source page. NWB Inspector flags the short fixture\nwith a critical orientation heuristic because width exceeds frame count; the report retains that\nfinding and adds the exact frame\u002Ftimestamp equality evidence. No transpose is performed merely to\nsatisfy a longest-axis heuristic.\n\n## Primary references\n\n- [NeuroConv TIFF conversion](https:\u002F\u002Fneuroconv.readthedocs.io\u002Fen\u002Fstable\u002Fconversion_examples_gallery\u002Fimaging\u002Ftiff.html)\n- [NeuroConv temporal alignment](https:\u002F\u002Fneuroconv.readthedocs.io\u002Fen\u002Fstable\u002Fuser_guide\u002Ftemporal_alignment.html)\n- [PyNWB](https:\u002F\u002Fgithub.com\u002FNeurodataWithoutBorders\u002Fpynwb)\n- [NWB Inspector and its relation to schema validation](https:\u002F\u002Fgithub.com\u002FNeurodataWithoutBorders\u002Fnwbinspector)\n",{"name":5,"license":15,"category":44,"metadata":45,"description":7,"compatibility":52},"scientific-computing",{"version":46,"skill-author":47,"last-reviewed":48,"upstream-pynwb":49,"upstream-neuroconv":50,"upstream-nwbinspector":51},"1.1","K-Dense Inc.","2026-10-01","4.2.0","0.10.2","0.7.2","Requires Python 3.12 with neuroconv[tiff] 0.10.2, PyNWB 4.2.0, NWB Inspector 0.7.2, roiextractors 0.10.0, tifffile 2026.9.20, zarr 2.18.7 and hdmf-zarr 0.11.3. Local HDF5 file access is required. Network is needed only for installation; no credentials.","main","0da4485785ee599388900be50db1635489d53056",".agents\u002Fskills\u002Fkd-nwb-conversion","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6","https:\u002F\u002Fdisha6.6.thenitishkr.in\u002F","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh","www.thenitishkr","thenitishkr | AI • Cyber-security • Research\r\n","2026-11-08 03:33:25",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add Tashima-Tarsh\u002FDisha6.6 --skill nwb-conversion",{"tool":68,"command":69},"bunx","bunx skills add Tashima-Tarsh\u002FDisha6.6 --skill nwb-conversion",{"tool":71,"command":72},"pnpm","pnpm dlx skills add Tashima-Tarsh\u002FDisha6.6 --skill nwb-conversion","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-nwb-conversion\u002FSKILL.md",true,[76,82,88,92],{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"assets\u002Fsession-template.json","ASSET","资产文件",1340,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-nwb-conversion\u002Fassets\u002Fsession-template.json",{"path":83,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Finput-contract.md","REFERENCE","参考文档",4842,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-nwb-conversion\u002Freferences\u002Finput-contract.md",{"path":89,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fupstream-review.md",4023,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-nwb-conversion\u002Freferences\u002Fupstream-review.md",{"path":93,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":96,"sourceHtmlUrl":97},"scripts\u002Fconvert_session.py","SCRIPT","脚本",16098,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-nwb-conversion\u002Fscripts\u002Fconvert_session.py",[99,129,154,181,206,230],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":110,"publishedAt":39},"01M6QRD07D4TGNDK6VJ4EHF8BV","youtube-full","Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private\u002Fage-restricted videos.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fyoutube-full\u002FSKILL.md",[105],{"categoryNo":106,"categoryName":107,"taxonomyType":108,"taxonomyTypeDesc":109},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[111,112,113,114,115,116,36,117,118,119,29,120,121,122,123,124,125,126,127,128],"youtube full","youtube","full","transcript","search","monitoring","Video","Audio","list","do","get","age","trigger","URL","for","browsing","request","youtube transcripts",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":39},"01M6QRCJ3112VYPA97YG7KGMC2","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[136,137,138,139,115,140,141,142,143,144,145,146,147,148,149,150,151,152,153,125],"twitter","x twitter growth","growth","research","content","engineering","plan","web search","competitors","analyze","engine","write","strategy","use","platform","grow","posting","competitive",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":163,"publishedAt":39},"01M6QRBN3EHQNJY42RERP7A149","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",[160],{"categoryNo":161,"categoryName":162,"taxonomyType":108,"taxonomyTypeDesc":109},"01JBSEEDCAT000000000000023","Skill与智能体开发",[164,147,165,166,167,168,169,170,149,171,172,53,173,174,175,176,177,178,179,180],"write a skill","github","create","https","productivity","matt pocock","direct","example","build","new skill","structure","new agent","resources","with","tree","progressive disclosure","author",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":187,"publishedAt":39},"01M6QRB6G8P33PNGAF9Y69EJ9T","wrap-up","Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says \"wrap up\", \"close this out\", \"what do I own now\", \"give me the summary\", \"recap the agent\", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained .\u002Fmy-agent\u002Fagent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrap-up\u002FSKILL.md",[],[188,189,190,191,192,193,194,195,196,149,197,120,198,199,200,201,202,203,204,205],"wrap up","up","wrap","gemini","deployment","run","file","hardening","closeout","stop","upgrade","founder","close","companion","you","tables","directions","phase",{"skillNo":207,"name":208,"nameZh":6,"description":209,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":210,"categories":211,"keywords":213,"publishedAt":39},"01M6QRA5AYC1RBFZ39GTWGS3N8","workflow-builder","Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworkflow-builder\u002FSKILL.md",[212],{"categoryNo":161,"categoryName":162,"taxonomyType":108,"taxonomyTypeDesc":109},[214,215,216,217,218,166,193,219,220,221,222,223,147,224,29,225,226,227,228,229],"workflow","workflow builder","builder","design","workflows","code","orchestrate","pipeline","loop","multi-agent","context","across","fresh","scripts","judge","claude code workflow",{"skillNo":231,"name":232,"nameZh":6,"description":233,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":234,"categories":235,"keywords":236,"publishedAt":39},"01M6QR7QMCZESKQA0ERW1E657M","weekly-review","Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says \"\u002Fcs:weekly-review\". Walks David Allen's three-phase loop — GET CLEAR, GET CURRENT, GET CREATIVE — with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweekly-review\u002FSKILL.md",[],[237,238,239,240,241,242,243,244,245,222,246,247,248,249,250,251,121,252,253,205],"review","weekly review","weekly","deterministic scripts","reflect","feeds","inventory","open","team","projects","project-management","scanner","conversation","back","project","sprint","cadence"]