[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QHF20QQ68HK2JSG02FSVEA":3,"skill-same:01M6QHF20QQ68HK2JSG02FSVEA":86},{"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":51,"commitSha":52,"skillDirectory":53,"forksCount":14,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M6QHF20QQ68HK2JSG02FSVEA","qiime2-amplicon",null,"Processes paired-end 16S amplicon reads into QIIME 2 ASVs and taxonomy with retained artifact provenance. Checks paired FASTQ manifests, primer orientation diagnostics, predicted post-trimming overlap, sample IDs, runtime versions and read retention, and guides selection of compatible taxonomic classifiers.","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-qiime2-amplicon\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"qiime2 amplicon","distribution","manifests","types","scientific","retention","primer","guides","conda","end","official","sample","artifact","selection","classifier","install","read","ids","network","library","2026-11-10 10:12:30",false,"---\nname: qiime2-amplicon\ndescription: Processes paired-end 16S amplicon reads into QIIME 2 ASVs and taxonomy with retained artifact provenance. Checks paired FASTQ manifests, primer orientation diagnostics, predicted post-trimming overlap, sample IDs, runtime versions and read retention, and guides selection of compatible taxonomic classifiers.\nlicense: MIT\ncompatibility: Python 3.10+ for the standard-library validation helper; QIIME 2 2026.7 distribution with cutadapt, dada2, demux, feature-table, feature-classifier, taxa and types plugins for execution. Install through the official conda\u002Fcontainer distribution, not PyPI. Requires a compatible trusted classifier and network for installation\u002Freference downloads.\nmetadata:\n  version: \"1.1\"\n  skill-author: K-Dense Inc.\n  upstream-version: \"2026.7\"\n  last-reviewed: \"2026-10-01\"\ncategory: \"scientific-computing\"\n---\n\n# QIIME 2 paired-end 16S amplicons\n\nUse for a demultiplexed, paired-end 16S assay with known primers, quality encoding, expected insert\nlength, and sample metadata. This bounded workflow imports reads, removes 5′ primers, denoises with\nDADA2, classifies ASVs using an explicitly supplied classifier, and retains `.qza`\u002F`.qzv` provenance.\nDo not treat read counts as absolute cell counts or taxonomy assignments as strain identification.\n\n## Establish the assay before running\n\n- Confirm Phred+33, read orientation, primer sequences **as sequenced** in forward\u002Freverse reads,\n  and whether primers have already been removed. The bundled runner requires primers still\n  present at the 5′ ends; it anchors Cutadapt matching and discards untrimmed pairs. Already\n  trimmed reads need a direct import → DADA2 workflow with that omission recorded in provenance.\n- Choose truncation positions from actual per-base quality and error profiles. `trunc-f\u002Fr` are\n  positions **after primer removal**. The expected maximum insert length also excludes primers.\n  Require `trunc_f + trunc_r - maximum_insert_length >= 12`; use a margin for length variation.\n  The check predicts geometrical overlap, not successful biological merging.\n- Choose a classifier whose reference database, taxonomic coverage, orientation and training\n  approach fit the assay. Full-length classifiers are supported; primer-region-specific training\n  is not mandatory. Match its scikit-learn version exactly to the installed environment\n  (the official 2026.7 distribution pins 1.7.1). Record source URL, database version and checksum.\n  QIIME's current data-resources page links externally hosted classifiers for 2026.4 and later;\n  its older downloads are not automatically compatible. Do not automatically fetch\n  an arbitrary “latest” classifier or reuse an incompatible serialized sklearn model. Load sklearn\n  classifier artifacts only from trusted sources: QZA format validation does not make an\n  untrusted serialized model safe.\n- Include extraction blanks, PCR negatives, and a mock community where available. The runner\n  rejects empty FASTQs; preserve empty-control IDs separately and report them rather than silently\n  deleting control evidence. Assess contamination before ecological interpretation.\n\n## Input files\n\nManifest is a **tab-separated** `PairedEndFastqManifestPhred33V2` file with exactly these headers:\n\n```text\nsample-id\tforward-absolute-filepath\treverse-absolute-filepath\nsample1\t\u002Fdata\u002Fsample1_R1.fastq.gz\t\u002Fdata\u002Fsample1_R2.fastq.gz\n```\n\nThis is the helper's deliberately narrow manifest profile. Use actual tab characters, literal\nabsolute paths visible to the runtime (expand environment variables before calling this helper),\nand one row per sample; no comment\u002Fdirective rows or additional columns in this manifest.\nDo not reverse-complement R2 files. Sample metadata is a tab-separated file with first column\n`sample-id`, unique IDs matching the manifest, and optional `#q2:types` annotation. Include\ncovariates and biological replicate IDs needed downstream.\nThe helper checks metadata IDs and row structure; QIIME performs full metadata typing\u002Fdirective\nvalidation during execution. Metadata used by actions persists in artifact provenance, so use\nde-identified biological replicate IDs.\n\n## Execute\n\nThe helper lives at [scripts\u002Famplicon_workflow.py](scripts\u002Famplicon_workflow.py). Commands below\nassume the skill directory is the working directory. First validate\nwithout QIIME. These example primers and lengths are **illustrative**, not universal assay settings:\n\n```bash\npython scripts\u002Famplicon_workflow.py validate \\\n  --manifest manifest.tsv --metadata sample-metadata.tsv \\\n  --primer-f GTGYCAGCMGCCGCGGTAA --primer-r GGACTACNVGGGTWTCTAAT \\\n  --trunc-f 220 --trunc-r 200 --amplicon-max 300\n```\n\nThen run in the QIIME 2 2026.7 environment with a compatible classifier. This study-specific\ninvocation is illustrative; choose lengths using a preceding quality inspection or pilot:\n\n```bash\npython scripts\u002Famplicon_workflow.py run \\\n  --manifest manifest.tsv --metadata sample-metadata.tsv \\\n  --primer-f GTGYCAGCMGCCGCGGTAA --primer-r GGACTACNVGGGTWTCTAAT \\\n  --trunc-f 220 --trunc-r 200 --amplicon-max 300 \\\n  --classifier compatible-classifier.qza --threads 4 --output run01\n```\n\n`run` executes immediately, writes only to a fresh output directory, and stops on a failing QIIME\ncommand. It streams through every paired FASTQ record to catch mismatched IDs\u002Forder\u002Fcounts,\nchecks sequence\u002Fquality consistency and sample alignment, and profiles the first 1,000 read pairs\nfor exact IUPAC primer matches. Low exact-match rates are warnings: Cutadapt allows mismatches,\nbut a low rate can also indicate incorrect orientation, adapters, or already-trimmed data.\nAt least one complete pair per sample must meet nominal post-primer truncation lengths.\nThese length estimates subtract the stated primer lengths; they do not simulate Cutadapt indels\nor quality filtering, and do not establish that any pair will actually merge.\n\nThe runner uses `--output-dir` for plugin methods with evolving output sets, preserving Cutadapt\nstatistics and DADA2 base-transition artifacts when supplied by the release. The 2026.7 table\nsummary also produces `feature-frequencies.qza` and `sample-frequencies.qza` beside `table.qzv`.\nIt records\n`qiime-info.txt`, `commands.json`, `workflow.log`, input QC, classifier checksum and output artifact\nchecksums. It runs maximum-level QIIME artifact validation before reporting completion.\nSee [references\u002Fruntime-and-interpretation.md](references\u002Fruntime-and-interpretation.md) for the\nrelease-pinned runtime, actual validation scope, restart handling and scientific interpretation.\n\n## Inspect results before analysis\n\nOpen `trimmed.qzv`, `table.qzv`, and `taxa.qzv` in a local QIIME visualization environment or\n[QIIME 2 View](https:\u002F\u002Fview.qiime2.org\u002F) as appropriate for the data. Examine quality\u002Flength profiles,\nper-sample depth and dominant taxa. Retain original artifacts rather than replacing them with\nCSV\u002FBIOM exports: exports do not retain the original provenance graph.\n\n`retention-qc.json` compares raw pairs with DADA2 input and non-chimeric reads, so trimming losses\nremain visible. A \u003C50% retained fraction is a review heuristic, not a universal rejection rule.\nInspect the individual stages in `stats\u002Fstats.tsv`: filtering loss suggests quality\u002Fexpected-error\nsettings; loss after forward denoising includes reverse-denoising and merging failures; chimera loss warrants reviewing library\nquality and parameters. Investigate missing\u002Fzero samples and control behavior before rarefaction,\ndiversity, or differential abundance. Those downstream analyses need a separate design decision;\nthis skill does not choose a rarefaction depth automatically.\nThe standalone `retention stats.tsv` subcommand knows only DADA2 input counts: it reports\n`raw_pairs: null` and names that denominator explicitly. It supports merged-only paired DADA2\nstatistics, as produced by this runner; it rejects retained-unmerged\u002Fconcatenated-read statistics.\n\n## Primary references\n\n- [Current installation entry point](https:\u002F\u002Flibrary.qiime2.org\u002Fquickstart\u002Fqiime2) and\n  [amplicon documentation](https:\u002F\u002Famplicon-docs.qiime2.org\u002Fen\u002Flatest\u002F).\n- [Import formats](https:\u002F\u002Famplicon-docs.qiime2.org\u002Fen\u002Flatest\u002Fhow-to-guides\u002Fhow-to-import\u002F).\n- [Cutadapt actions](https:\u002F\u002Famplicon-docs.qiime2.org\u002Fen\u002Flatest\u002Freferences\u002Fplugins\u002Fcutadapt\u002F) and\n  [DADA2 actions](https:\u002F\u002Famplicon-docs.qiime2.org\u002Fen\u002Flatest\u002Freferences\u002Fplugins\u002Fdada2\u002F).\n- [Classifier data resources](https:\u002F\u002Flibrary.qiime2.org\u002Fdata-resources).\n\nThe rolling documentation may describe a development release. Inspect `qiime info` and action\n`--help` in the exact installed environment before adapting the pinned runner to a later release.\n","# QIIME 2 paired-end 16S amplicons\n\nUse for a demultiplexed, paired-end 16S assay with known primers, quality encoding, expected insert\nlength, and sample metadata. This bounded workflow imports reads, removes 5′ primers, denoises with\nDADA2, classifies ASVs using an explicitly supplied classifier, and retains `.qza`\u002F`.qzv` provenance.\nDo not treat read counts as absolute cell counts or taxonomy assignments as strain identification.\n\n## Establish the assay before running\n\n- Confirm Phred+33, read orientation, primer sequences **as sequenced** in forward\u002Freverse reads,\n  and whether primers have already been removed. The bundled runner requires primers still\n  present at the 5′ ends; it anchors Cutadapt matching and discards untrimmed pairs. Already\n  trimmed reads need a direct import → DADA2 workflow with that omission recorded in provenance.\n- Choose truncation positions from actual per-base quality and error profiles. `trunc-f\u002Fr` are\n  positions **after primer removal**. The expected maximum insert length also excludes primers.\n  Require `trunc_f + trunc_r - maximum_insert_length >= 12`; use a margin for length variation.\n  The check predicts geometrical overlap, not successful biological merging.\n- Choose a classifier whose reference database, taxonomic coverage, orientation and training\n  approach fit the assay. Full-length classifiers are supported; primer-region-specific training\n  is not mandatory. Match its scikit-learn version exactly to the installed environment\n  (the official 2026.7 distribution pins 1.7.1). Record source URL, database version and checksum.\n  QIIME's current data-resources page links externally hosted classifiers for 2026.4 and later;\n  its older downloads are not automatically compatible. Do not automatically fetch\n  an arbitrary “latest” classifier or reuse an incompatible serialized sklearn model. Load sklearn\n  classifier artifacts only from trusted sources: QZA format validation does not make an\n  untrusted serialized model safe.\n- Include extraction blanks, PCR negatives, and a mock community where available. The runner\n  rejects empty FASTQs; preserve empty-control IDs separately and report them rather than silently\n  deleting control evidence. Assess contamination before ecological interpretation.\n\n## Input files\n\nManifest is a **tab-separated** `PairedEndFastqManifestPhred33V2` file with exactly these headers:\n\n```text\nsample-id\tforward-absolute-filepath\treverse-absolute-filepath\nsample1\t\u002Fdata\u002Fsample1_R1.fastq.gz\t\u002Fdata\u002Fsample1_R2.fastq.gz\n```\n\nThis is the helper's deliberately narrow manifest profile. Use actual tab characters, literal\nabsolute paths visible to the runtime (expand environment variables before calling this helper),\nand one row per sample; no comment\u002Fdirective rows or additional columns in this manifest.\nDo not reverse-complement R2 files. Sample metadata is a tab-separated file with first column\n`sample-id`, unique IDs matching the manifest, and optional `#q2:types` annotation. Include\ncovariates and biological replicate IDs needed downstream.\nThe helper checks metadata IDs and row structure; QIIME performs full metadata typing\u002Fdirective\nvalidation during execution. Metadata used by actions persists in artifact provenance, so use\nde-identified biological replicate IDs.\n\n## Execute\n\nThe helper lives at [scripts\u002Famplicon_workflow.py](scripts\u002Famplicon_workflow.py). Commands below\nassume the skill directory is the working directory. First validate\nwithout QIIME. These example primers and lengths are **illustrative**, not universal assay settings:\n\n```bash\npython scripts\u002Famplicon_workflow.py validate \\\n  --manifest manifest.tsv --metadata sample-metadata.tsv \\\n  --primer-f GTGYCAGCMGCCGCGGTAA --primer-r GGACTACNVGGGTWTCTAAT \\\n  --trunc-f 220 --trunc-r 200 --amplicon-max 300\n```\n\nThen run in the QIIME 2 2026.7 environment with a compatible classifier. This study-specific\ninvocation is illustrative; choose lengths using a preceding quality inspection or pilot:\n\n```bash\npython scripts\u002Famplicon_workflow.py run \\\n  --manifest manifest.tsv --metadata sample-metadata.tsv \\\n  --primer-f GTGYCAGCMGCCGCGGTAA --primer-r GGACTACNVGGGTWTCTAAT \\\n  --trunc-f 220 --trunc-r 200 --amplicon-max 300 \\\n  --classifier compatible-classifier.qza --threads 4 --output run01\n```\n\n`run` executes immediately, writes only to a fresh output directory, and stops on a failing QIIME\ncommand. It streams through every paired FASTQ record to catch mismatched IDs\u002Forder\u002Fcounts,\nchecks sequence\u002Fquality consistency and sample alignment, and profiles the first 1,000 read pairs\nfor exact IUPAC primer matches. Low exact-match rates are warnings: Cutadapt allows mismatches,\nbut a low rate can also indicate incorrect orientation, adapters, or already-trimmed data.\nAt least one complete pair per sample must meet nominal post-primer truncation lengths.\nThese length estimates subtract the stated primer lengths; they do not simulate Cutadapt indels\nor quality filtering, and do not establish that any pair will actually merge.\n\nThe runner uses `--output-dir` for plugin methods with evolving output sets, preserving Cutadapt\nstatistics and DADA2 base-transition artifacts when supplied by the release. The 2026.7 table\nsummary also produces `feature-frequencies.qza` and `sample-frequencies.qza` beside `table.qzv`.\nIt records\n`qiime-info.txt`, `commands.json`, `workflow.log`, input QC, classifier checksum and output artifact\nchecksums. It runs maximum-level QIIME artifact validation before reporting completion.\nSee [references\u002Fruntime-and-interpretation.md](references\u002Fruntime-and-interpretation.md) for the\nrelease-pinned runtime, actual validation scope, restart handling and scientific interpretation.\n\n## Inspect results before analysis\n\nOpen `trimmed.qzv`, `table.qzv`, and `taxa.qzv` in a local QIIME visualization environment or\n[QIIME 2 View](https:\u002F\u002Fview.qiime2.org\u002F) as appropriate for the data. Examine quality\u002Flength profiles,\nper-sample depth and dominant taxa. Retain original artifacts rather than replacing them with\nCSV\u002FBIOM exports: exports do not retain the original provenance graph.\n\n`retention-qc.json` compares raw pairs with DADA2 input and non-chimeric reads, so trimming losses\nremain visible. A \u003C50% retained fraction is a review heuristic, not a universal rejection rule.\nInspect the individual stages in `stats\u002Fstats.tsv`: filtering loss suggests quality\u002Fexpected-error\nsettings; loss after forward denoising includes reverse-denoising and merging failures; chimera loss warrants reviewing library\nquality and parameters. Investigate missing\u002Fzero samples and control behavior before rarefaction,\ndiversity, or differential abundance. Those downstream analyses need a separate design decision;\nthis skill does not choose a rarefaction depth automatically.\nThe standalone `retention stats.tsv` subcommand knows only DADA2 input counts: it reports\n`raw_pairs: null` and names that denominator explicitly. It supports merged-only paired DADA2\nstatistics, as produced by this runner; it rejects retained-unmerged\u002Fconcatenated-read statistics.\n\n## Primary references\n\n- [Current installation entry point](https:\u002F\u002Flibrary.qiime2.org\u002Fquickstart\u002Fqiime2) and\n  [amplicon documentation](https:\u002F\u002Famplicon-docs.qiime2.org\u002Fen\u002Flatest\u002F).\n- [Import formats](https:\u002F\u002Famplicon-docs.qiime2.org\u002Fen\u002Flatest\u002Fhow-to-guides\u002Fhow-to-import\u002F).\n- [Cutadapt actions](https:\u002F\u002Famplicon-docs.qiime2.org\u002Fen\u002Flatest\u002Freferences\u002Fplugins\u002Fcutadapt\u002F) and\n  [DADA2 actions](https:\u002F\u002Famplicon-docs.qiime2.org\u002Fen\u002Flatest\u002Freferences\u002Fplugins\u002Fdada2\u002F).\n- [Classifier data resources](https:\u002F\u002Flibrary.qiime2.org\u002Fdata-resources).\n\nThe rolling documentation may describe a development release. Inspect `qiime info` and action\n`--help` in the exact installed environment before adapting the pinned runner to a later release.\n",{"name":5,"license":15,"category":44,"metadata":45,"description":7,"compatibility":50},"scientific-computing",{"version":46,"skill-author":47,"last-reviewed":48,"upstream-version":49},"1.1","K-Dense Inc.","2026-10-01","2026.7","Python 3.10+ for the standard-library validation helper; QIIME 2 2026.7 distribution with cutadapt, dada2, demux, feature-table, feature-classifier, taxa and types plugins for execution. Install through the official conda\u002Fcontainer distribution, not PyPI. Requires a compatible trusted classifier and network for installation\u002Freference downloads.","main","0da4485785ee599388900be50db1635489d53056",".agents\u002Fskills\u002Fkd-qiime2-amplicon","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 qiime2-amplicon",{"tool":66,"command":67},"bunx","bunx skills add Tashima-Tarsh\u002FDisha6.6 --skill qiime2-amplicon",{"tool":69,"command":70},"pnpm","pnpm dlx skills add Tashima-Tarsh\u002FDisha6.6 --skill qiime2-amplicon","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-qiime2-amplicon\u002FSKILL.md",true,[74,80],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fruntime-and-interpretation.md","REFERENCE","参考文档",13632,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-qiime2-amplicon\u002Freferences\u002Fruntime-and-interpretation.md",{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"scripts\u002Famplicon_workflow.py","SCRIPT","脚本",15621,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-qiime2-amplicon\u002Fscripts\u002Famplicon_workflow.py",[87,119,144,171,196,220],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":98,"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",[93],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118],"youtube full","youtube","full","transcript","search","monitoring","data","Video","Audio","list","files","do","get","age","trigger","URL","for","browsing","request","youtube transcripts",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"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",[],[126,127,128,129,103,130,131,132,133,134,135,136,137,138,139,140,141,142,143,115],"twitter","x twitter growth","growth","research","content","engineering","plan","web search","competitors","analyze","engine","write","strategy","use","platform","grow","posting","competitive",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":153,"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",[150],{"categoryNo":151,"categoryName":152,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000023","Skill与智能体开发",[154,137,155,156,157,158,159,160,139,161,162,51,163,164,165,166,167,168,169,170],"write a skill","github","create","https","productivity","matt pocock","direct","example","build","new skill","structure","new agent","resources","with","tree","progressive disclosure","author",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":177,"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",[],[178,179,180,181,182,183,184,185,186,139,187,110,188,189,190,191,192,193,194,195],"wrap up","up","wrap","gemini","deployment","run","file","hardening","closeout","stop","upgrade","founder","close","companion","you","tables","directions","phase",{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":200,"categories":201,"keywords":203,"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",[202],{"categoryNo":151,"categoryName":152,"taxonomyType":96,"taxonomyTypeDesc":97},[204,205,206,207,208,156,183,209,210,211,212,213,137,214,109,215,216,217,218,219],"workflow","workflow builder","builder","design","workflows","code","orchestrate","pipeline","loop","multi-agent","context","across","fresh","scripts","judge","claude code workflow",{"skillNo":221,"name":222,"nameZh":6,"description":223,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":224,"categories":225,"keywords":226,"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",[],[227,228,229,230,231,232,233,234,235,212,236,237,238,239,240,241,111,242,243,195],"review","weekly review","weekly","deterministic scripts","reflect","feeds","inventory","open","team","projects","project-management","scanner","conversation","back","project","sprint","cadence"]