[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QHVM8R9NGYD7AD9QF8293D":3,"skill-same:01M6QHVM8R9NGYD7AD9QF8293D":104},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":14,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M6QHVM8R9NGYD7AD9QF8293D","vaex",null,"Processes large tabular scientific datasets with Vaex expressions, filtered views, streamed statistics, binned visualizations, and file conversion. Use for larger-than-RAM HDF5, Arrow, CSV, or Parquet analysis, virtual feature engineering, or Vaex ML preprocessing; distinguishes these operations from estimators and conversions that materialize data.","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-vaex\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"read","remote","scientific","statistics","preprocessing","local","conversion","install","edit","write","workflows","virtual","access","Bash","credentials","analysis","data","network","feature engineering","2026-11-10 10:12:30",false,"---\nname: vaex\ndescription: Processes large tabular scientific datasets with Vaex expressions, filtered views, streamed statistics, binned visualizations, and file conversion. Use for larger-than-RAM HDF5, Arrow, CSV, or Parquet analysis, virtual feature engineering, or Vaex ML preprocessing; distinguishes these operations from estimators and conversions that materialize data.\nallowed-tools: Read Write Edit Bash Grep Glob\nlicense: MIT license\ncompatibility: Requires Python 3.9-3.12 for vaex-core 4.19.0; tested on Python 3.12. Install vaex-core plus vaex-hdf5, vaex-viz, or vaex-ml as needed. Package installation and remote data need network access; local workflows need no credentials.\nmetadata:\n  version: \"1.3\"\n  skill-author: K-Dense Inc.\n  last-reviewed: \"2026-10-01\"\ncategory: \"scientific-computing\"\n---\n\n# Vaex\n\n## When to use\n\nUse Vaex for columnar analysis on a single machine when data exceeds RAM, especially\nrepeated reductions and histograms over local Vaex HDF5 or Arrow files. Expressions\nand virtual columns defer computation; reductions normally execute immediately.\nOut-of-core storage does not make every operation memory bounded: sorting, joins,\nlarge group dictionaries, materialization, and many estimator fits need substantial RAM.\n\n## Installation and verified scope\n\nUse a separate environment; the repository's default Python is newer than this release supports:\n\n```bash\nuv venv --python 3.12 .venv-vaex\nuv pip install --python .venv-vaex\u002Fbin\u002Fpython \"vaex-core==4.19.0\" \"vaex-hdf5==0.15.0\" \"vaex-viz==0.6.0\"\n# Optional ML (also installs its declared estimator dependencies):\nuv pip install --python .venv-vaex\u002Fbin\u002Fpython \"vaex-ml==0.19.0\"\n```\n\nOn Windows use `.venv-vaex\\Scripts\\python.exe` as the interpreter path. The `vaex`\n4.19.0 metapackage installs more integrations; it is not needed for the core workflow.\nCore 4.19.0 declares Python `>=3.9,\u003C3.13`, pandas `\u003C3`, Dask `\u003C2024.9`, and NumPy\n`\u003C3`. Do not upgrade these constraints independently. Arrow support is in core;\nFITS needs `vaex-astro`. Compatible binary wheels determine platform availability;\ncompiling the optional `annoy` dependency requires a C++ toolchain, not just Python headers.\n\nNative checks used Python 3.12, core 4.19.0, HDF5 0.15.0, viz 0.6.0, ML 0.19.0,\nNumPy 2.5.3, pandas 2.3.3, PyArrow 25.0.1 and Matplotlib 3.11.2 on macOS ARM.\nSee [review and verification](references\u002Freview.md) for evidence and optional-integration limits.\nThese are correctness checks on small synthetic inputs, not performance benchmarks.\n\n## Workflow\n\n1. Establish row identity, units, schema, missing-value codes, and expected counts.\n   Inspect CSV raw headers before parsers rename duplicates; supply explicit types\n   for IDs and late-appearing values. Keep dates, time zones, and sampling cadence explicit.\n2. Open files with `vaex.open`. HDF5 must use a compatible table layout; arbitrary\n   HDF5 scientific arrays are not automatically a Vaex table. CSV opening performs\n   indexing\u002Fschema work; Parquet must decode compressed data. Neither is an instant,\n   zero-memory operation.\n3. Select needed columns and use expressions for derived values. A virtual column\n   avoids a full stored array but still needs expression metadata and evaluation buffers.\n4. Record filters\u002Fselections and missingness before reductions. Batch independent\n   statistics with `delay=True`, then `df.execute()` and each promise's `.get()`.\n5. Validate counts, units, join cardinality, and numerical results against a small\n   independently computed subset. Binned or approximate summaries need explicit limits\u002Fresolution.\n6. Plot aggregated grids or a bounded sample. A count heatmap and a mean heatmap\n   answer different questions; show coverage and avoid hiding rare\u002Fextreme observations silently.\n7. Export directly in chunks; exporting evaluates virtual columns without needing\n   `materialize()` first. Reopen and check counts\u002Fschema\u002Fvalues before replacing source data.\n\n## Small executable example\n\nRun in a writable working directory; output names must not refer to existing data.\n\n```python\nfrom pathlib import Path\nimport numpy as np\nimport vaex\n\nout = Path('vaex-example.hdf5')\nif out.exists():\n    raise FileExistsError(out)\ndf = vaex.from_arrays(\n    x=np.arange(1., 7.), y=np.arange(6.) ** 2,\n    category=np.array(['A', 'B', 'A', 'B', 'A', 'B']),\n)\ndf['energy'] = df.x ** 2 + df.y\nselected = df[df.x >= 3]\nmean_task = selected.energy.mean(delay=True)\ncount_task = selected.count(delay=True)\nselected.execute()\nassert count_task.get() == 4\nassert np.isclose(mean_task.get(), 35.0)\nsummary = df.groupby('category', agg={\n    'rows': vaex.agg.count(), 'energy_sum': vaex.agg.sum('energy'),\n})\nassert int(summary.rows.sum()) == len(df)\ndf.export_hdf5(str(out), chunk_size=2)\nreopened = vaex.open(str(out))\nassert reopened.get_column_names() == df.get_column_names()\nassert np.allclose(reopened.energy.to_numpy(), df.energy.to_numpy())\n```\n\nFor a large real input, replace the in-memory fixture with `vaex.open('input.hdf5')`.\nThe small `.to_numpy()` comparison above is a fixture check; do not apply it to a\nwhole larger-than-RAM dataset. Compare sampled rows and streamed summaries instead.\n\n## Reference map\n\n- [Core DataFrames](references\u002Fcore_dataframes.md): loaders, expression\u002Farray distinctions, inspection and schema.\n- [Data processing](references\u002Fdata_processing.md): filtering, missingness, strings\u002Fdates, grouped statistics and joins.\n- [Performance](references\u002Fperformance.md): delayed\u002Fasync execution, caching, buffers, materialization and profiling.\n- [Visualization](references\u002Fvisualization.md): supported `df.viz` methods, grid geometry, finite plotting limits and widgets.\n- [Machine learning](references\u002Fmachine_learning.md): train-only fitting, native transformers, estimator memory and state transfer.\n- [I\u002FO](references\u002Fio_operations.md): chunked CSV conversion, HDF5\u002FArrow\u002FParquet round trips and remote boundaries.\n\n## Failure checks\n\n- `df.x.mean()` returns a computed result; it is not a lazy expression.\n- Use `df.percentile_approx('x', percentage=50)` for approximate percentiles;\n  `Expression.quantile` is not a core 4.19.0 API.\n- Use explicit `vaex.agg` objects to name grouped outputs. Do not assume pandas\n  dictionary aggregation or arbitrary group callbacks have the same contract.\n- `join` defaults to left; declare `how`, validate keys, and extract filtered inputs\n  when the filter must define join membership. Joins accept one key expression per side.\n- `.values`, `.to_numpy()`, unchunked `.to_pandas_df()`, `.materialize()`, and\n  ordinary sklearn `Predictor.fit()` can allocate full arrays.\n- State files carry transformations and potentially serialized executable objects;\n  load only trusted artifacts. They do not carry the original dataset or prove its provenance.\n\n## Citing Scientific Agent Skills\n\nThis skill is part of Scientific Agent Skills by K-Dense. If it materially contributed to a\nmanuscript, report, presentation, or code release, add the paper to the references or\nsoftware section and tell the user you did so:\n\n> Kassis, T., Agarwal, V., He, Y., Patel, D., & Brueckner, A. M. (2026). Scientific Agent\n> Skills: A Library of Procedural Knowledge for Research Agents. arXiv:2609.00065.\n> https:\u002F\u002Fdoi.org\u002F10.48550\u002FarXiv.2609.00065\n\nAlways cite the current version. The DOI and https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.00065 resolve to the\nlatest arXiv version, so never append a version suffix such as `v1`. When network access is\navailable, fetch https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.00065 (or\nhttp:\u002F\u002Fexport.arxiv.org\u002Fapi\u002Fquery?id_list=2609.00065) before writing the reference and take\nthe author list, year, and version from that record. If the record lists a journal reference\nor publisher DOI, cite the published version instead.\n","# Vaex\n\n## When to use\n\nUse Vaex for columnar analysis on a single machine when data exceeds RAM, especially\nrepeated reductions and histograms over local Vaex HDF5 or Arrow files. Expressions\nand virtual columns defer computation; reductions normally execute immediately.\nOut-of-core storage does not make every operation memory bounded: sorting, joins,\nlarge group dictionaries, materialization, and many estimator fits need substantial RAM.\n\n## Installation and verified scope\n\nUse a separate environment; the repository's default Python is newer than this release supports:\n\n```bash\nuv venv --python 3.12 .venv-vaex\nuv pip install --python .venv-vaex\u002Fbin\u002Fpython \"vaex-core==4.19.0\" \"vaex-hdf5==0.15.0\" \"vaex-viz==0.6.0\"\n# Optional ML (also installs its declared estimator dependencies):\nuv pip install --python .venv-vaex\u002Fbin\u002Fpython \"vaex-ml==0.19.0\"\n```\n\nOn Windows use `.venv-vaex\\Scripts\\python.exe` as the interpreter path. The `vaex`\n4.19.0 metapackage installs more integrations; it is not needed for the core workflow.\nCore 4.19.0 declares Python `>=3.9,\u003C3.13`, pandas `\u003C3`, Dask `\u003C2024.9`, and NumPy\n`\u003C3`. Do not upgrade these constraints independently. Arrow support is in core;\nFITS needs `vaex-astro`. Compatible binary wheels determine platform availability;\ncompiling the optional `annoy` dependency requires a C++ toolchain, not just Python headers.\n\nNative checks used Python 3.12, core 4.19.0, HDF5 0.15.0, viz 0.6.0, ML 0.19.0,\nNumPy 2.5.3, pandas 2.3.3, PyArrow 25.0.1 and Matplotlib 3.11.2 on macOS ARM.\nSee [review and verification](references\u002Freview.md) for evidence and optional-integration limits.\nThese are correctness checks on small synthetic inputs, not performance benchmarks.\n\n## Workflow\n\n1. Establish row identity, units, schema, missing-value codes, and expected counts.\n   Inspect CSV raw headers before parsers rename duplicates; supply explicit types\n   for IDs and late-appearing values. Keep dates, time zones, and sampling cadence explicit.\n2. Open files with `vaex.open`. HDF5 must use a compatible table layout; arbitrary\n   HDF5 scientific arrays are not automatically a Vaex table. CSV opening performs\n   indexing\u002Fschema work; Parquet must decode compressed data. Neither is an instant,\n   zero-memory operation.\n3. Select needed columns and use expressions for derived values. A virtual column\n   avoids a full stored array but still needs expression metadata and evaluation buffers.\n4. Record filters\u002Fselections and missingness before reductions. Batch independent\n   statistics with `delay=True`, then `df.execute()` and each promise's `.get()`.\n5. Validate counts, units, join cardinality, and numerical results against a small\n   independently computed subset. Binned or approximate summaries need explicit limits\u002Fresolution.\n6. Plot aggregated grids or a bounded sample. A count heatmap and a mean heatmap\n   answer different questions; show coverage and avoid hiding rare\u002Fextreme observations silently.\n7. Export directly in chunks; exporting evaluates virtual columns without needing\n   `materialize()` first. Reopen and check counts\u002Fschema\u002Fvalues before replacing source data.\n\n## Small executable example\n\nRun in a writable working directory; output names must not refer to existing data.\n\n```python\nfrom pathlib import Path\nimport numpy as np\nimport vaex\n\nout = Path('vaex-example.hdf5')\nif out.exists():\n    raise FileExistsError(out)\ndf = vaex.from_arrays(\n    x=np.arange(1., 7.), y=np.arange(6.) ** 2,\n    category=np.array(['A', 'B', 'A', 'B', 'A', 'B']),\n)\ndf['energy'] = df.x ** 2 + df.y\nselected = df[df.x >= 3]\nmean_task = selected.energy.mean(delay=True)\ncount_task = selected.count(delay=True)\nselected.execute()\nassert count_task.get() == 4\nassert np.isclose(mean_task.get(), 35.0)\nsummary = df.groupby('category', agg={\n    'rows': vaex.agg.count(), 'energy_sum': vaex.agg.sum('energy'),\n})\nassert int(summary.rows.sum()) == len(df)\ndf.export_hdf5(str(out), chunk_size=2)\nreopened = vaex.open(str(out))\nassert reopened.get_column_names() == df.get_column_names()\nassert np.allclose(reopened.energy.to_numpy(), df.energy.to_numpy())\n```\n\nFor a large real input, replace the in-memory fixture with `vaex.open('input.hdf5')`.\nThe small `.to_numpy()` comparison above is a fixture check; do not apply it to a\nwhole larger-than-RAM dataset. Compare sampled rows and streamed summaries instead.\n\n## Reference map\n\n- [Core DataFrames](references\u002Fcore_dataframes.md): loaders, expression\u002Farray distinctions, inspection and schema.\n- [Data processing](references\u002Fdata_processing.md): filtering, missingness, strings\u002Fdates, grouped statistics and joins.\n- [Performance](references\u002Fperformance.md): delayed\u002Fasync execution, caching, buffers, materialization and profiling.\n- [Visualization](references\u002Fvisualization.md): supported `df.viz` methods, grid geometry, finite plotting limits and widgets.\n- [Machine learning](references\u002Fmachine_learning.md): train-only fitting, native transformers, estimator memory and state transfer.\n- [I\u002FO](references\u002Fio_operations.md): chunked CSV conversion, HDF5\u002FArrow\u002FParquet round trips and remote boundaries.\n\n## Failure checks\n\n- `df.x.mean()` returns a computed result; it is not a lazy expression.\n- Use `df.percentile_approx('x', percentage=50)` for approximate percentiles;\n  `Expression.quantile` is not a core 4.19.0 API.\n- Use explicit `vaex.agg` objects to name grouped outputs. Do not assume pandas\n  dictionary aggregation or arbitrary group callbacks have the same contract.\n- `join` defaults to left; declare `how`, validate keys, and extract filtered inputs\n  when the filter must define join membership. Joins accept one key expression per side.\n- `.values`, `.to_numpy()`, unchunked `.to_pandas_df()`, `.materialize()`, and\n  ordinary sklearn `Predictor.fit()` can allocate full arrays.\n- State files carry transformations and potentially serialized executable objects;\n  load only trusted artifacts. They do not carry the original dataset or prove its provenance.\n\n## Citing Scientific Agent Skills\n\nThis skill is part of Scientific Agent Skills by K-Dense. If it materially contributed to a\nmanuscript, report, presentation, or code release, add the paper to the references or\nsoftware section and tell the user you did so:\n\n> Kassis, T., Agarwal, V., He, Y., Patel, D., & Brueckner, A. M. (2026). Scientific Agent\n> Skills: A Library of Procedural Knowledge for Research Agents. arXiv:2609.00065.\n> https:\u002F\u002Fdoi.org\u002F10.48550\u002FarXiv.2609.00065\n\nAlways cite the current version. The DOI and https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.00065 resolve to the\nlatest arXiv version, so never append a version suffix such as `v1`. When network access is\navailable, fetch https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.00065 (or\nhttp:\u002F\u002Fexport.arxiv.org\u002Fapi\u002Fquery?id_list=2609.00065) before writing the reference and take\nthe author list, year, and version from that record. If the record lists a journal reference\nor publisher DOI, cite the published version instead.\n",{"name":5,"license":43,"category":44,"metadata":45,"description":7,"allowed-tools":49,"compatibility":50},"MIT license","scientific-computing",{"version":46,"skill-author":47,"last-reviewed":48},"1.3","K-Dense Inc.","2026-10-01","Read Write Edit Bash Grep Glob","Requires Python 3.9-3.12 for vaex-core 4.19.0; tested on Python 3.12. Install vaex-core plus vaex-hdf5, vaex-viz, or vaex-ml as needed. Package installation and remote data need network access; local workflows need no credentials.","main","0da4485785ee599388900be50db1635489d53056",".agents\u002Fskills\u002Fkd-vaex","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":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add Tashima-Tarsh\u002FDisha6.6 --skill vaex",{"tool":66,"command":67},"bunx","bunx skills add Tashima-Tarsh\u002FDisha6.6 --skill vaex",{"tool":69,"command":70},"pnpm","pnpm dlx skills add Tashima-Tarsh\u002FDisha6.6 --skill vaex","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-vaex\u002FSKILL.md",true,[74,80,84,88,92,96,100],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fcore_dataframes.md","REFERENCE","参考文档",4707,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-vaex\u002Freferences\u002Fcore_dataframes.md",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fdata_processing.md",7287,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-vaex\u002Freferences\u002Fdata_processing.md",{"path":85,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fio_operations.md",7742,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-vaex\u002Freferences\u002Fio_operations.md",{"path":89,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fmachine_learning.md",10023,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-vaex\u002Freferences\u002Fmachine_learning.md",{"path":93,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fperformance.md",5191,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-vaex\u002Freferences\u002Fperformance.md",{"path":97,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Freview.md",4620,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-vaex\u002Freferences\u002Freview.md",{"path":101,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fvisualization.md",5087,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-vaex\u002Freferences\u002Fvisualization.md",[105,136,160,187,212,235],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":116,"publishedAt":38},"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",[111],{"categoryNo":112,"categoryName":113,"taxonomyType":114,"taxonomyTypeDesc":115},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[117,118,119,120,121,122,35,123,124,125,126,127,128,129,130,131,132,133,134,135],"youtube full","youtube","full","transcript","search","monitoring","Video","Audio","list","files","do","get","age","trigger","URL","for","browsing","request","youtube transcripts",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":38},"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",[],[143,144,145,146,121,147,148,149,150,151,152,153,28,154,155,156,157,158,159,132],"twitter","x twitter growth","growth","research","content","engineering","plan","web search","competitors","analyze","engine","strategy","use","platform","grow","posting","competitive",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":169,"publishedAt":38},"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",[166],{"categoryNo":167,"categoryName":168,"taxonomyType":114,"taxonomyTypeDesc":115},"01JBSEEDCAT000000000000023","Skill与智能体开发",[170,28,171,172,173,174,175,176,155,177,178,51,179,180,181,182,183,184,185,186],"write a skill","github","create","https","productivity","matt pocock","direct","example","build","new skill","structure","new agent","resources","with","tree","progressive disclosure","author",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":193,"publishedAt":38},"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",[],[194,195,196,197,198,199,200,201,202,155,203,127,204,205,206,207,208,209,210,211],"wrap up","up","wrap","gemini","deployment","run","file","hardening","closeout","stop","upgrade","founder","close","companion","you","tables","directions","phase",{"skillNo":213,"name":214,"nameZh":6,"description":215,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":216,"categories":217,"keywords":219,"publishedAt":38},"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",[218],{"categoryNo":167,"categoryName":168,"taxonomyType":114,"taxonomyTypeDesc":115},[220,221,222,223,29,172,199,224,225,226,227,228,28,229,126,230,231,232,233,234],"workflow","workflow builder","builder","design","code","orchestrate","pipeline","loop","multi-agent","context","across","fresh","scripts","judge","claude code workflow",{"skillNo":236,"name":237,"nameZh":6,"description":238,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":239,"categories":240,"keywords":241,"publishedAt":38},"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",[],[242,243,244,245,246,247,248,249,250,227,251,252,253,254,255,256,128,257,258,211],"review","weekly review","weekly","deterministic scripts","reflect","feeds","inventory","open","team","projects","project-management","scanner","conversation","back","project","sprint","cadence"]