[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7913R7Z3K8G8MTA4PAMADR3":3,"skill-same:01M7913R7Z3K8G8MTA4PAMADR3":63},{"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":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M7913R7Z3K8G8MTA4PAMADR3","taxonomy-helper",null,"Use the optional gimme_taxa workflow to resolve taxon names or parent TaxIDs into descendant TaxIDs or taxon metadata for ncbi-genome-download.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fncbi-genome-download\u002Fsub-skills\u002Ftaxonomy-helper\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: taxonomy-helper\ndescription: \"Use the optional gimme_taxa workflow to resolve taxon names or\n  parent TaxIDs into descendant TaxIDs or taxon metadata for\n  ncbi-genome-download.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Taxonomy helper\n\n`gimme_taxa.py` is an optional, experimental contributed workflow. It uses\nETE3's `NCBITaxa` interface and a local NCBI taxonomy database to resolve each\ncomma-separated positional input (a taxon name, a numeric TaxID, or both) and\nthen either emit descendants or describe the supplied taxa. It is a separate\npreparation step; it is not part of the main download CLI.\n\nUse the bundled helper at [`scripts\u002Fgimme_taxa.py`](scripts\u002Fgimme_taxa.py), not\nan original source checkout. The helper's parser preserves the public spellings\n`-v\u002F--verbose`, `-d\u002F--database`, `-u\u002F--update`, `-j\u002F--just-taxids`,\n`-i\u002F--taxon-info`, and `-o\u002F--outfile`.\n\n## Choose an output mode\n\n- **Download input (`-j` \u002F `--just-taxids`)**: write one descendant TaxID per\n  line, with no header. This is the only output mode intended for direct use as\n  an `ncbi-genome-download --taxids` input file. See\n  [`..\u002Fdownload-and-filter\u002FSKILL.md`](..\u002Fdownload-and-filter\u002FSKILL.md) for the\n  consuming download command and its filters.\n- **Default descendant report**: write a header followed by tab-separated rows\n  with `parent_taxid`, `descendent_taxid`, and `descendent_name`. This is for\n  inspection, not direct `--taxids` consumption.\n- **Taxon metadata (`-i` \u002F `--taxon-info`)**: write a header followed by\n  tab-separated `name`, `taxid`, `rank`, and `lineage` columns for the supplied\n  taxa. If `-i` and `-j` are both supplied, the source's `taxon-info` branch\n  takes precedence.\n\nThe source spelling `descendent` in the default header is intentional. Do not\nsilently deduplicate or reorder rows: the helper emits the returned ETE3\nsequence once for each supplied parent. The actual names and descendants are\nproperties of the local taxonomy database and were not live-queried during\nverification.\n\n## Safety boundary\n\nA lookup can have network and filesystem side effects. Constructing\n`NCBITaxa` may create or download a local taxonomy SQLite database when no\nusable database exists. `--update` (`-u`) explicitly asks ETE3 to refresh that\ndatabase and can take several minutes and require network access. Prefer an\nexplicit, writable `--database` path in a controlled workspace, record that\npath, and use the same path on later runs. Do not enable `--update` merely to\nproduce help or to test parsing.\n\nThe helper requires a Python environment in which ETE3 and its expected\nruntime dependencies `six` and `numpy` are installed. Installation and\ndatabase acquisition are deliberately outside the download skill's normal\nverification: no live taxonomy database query was run. First run `--help`,\nthen make a deliberate decision about dependency installation, database\nlocation, and network access before querying.\n\nFor checksums, file existence, and downstream output validation, follow\n[`..\u002Foutput-and-integrity\u002FSKILL.md`](..\u002Foutput-and-integrity\u002FSKILL.md). Treat the\nTaxID file as generated input: inspect its headerless, one-ID-per-line format\nbefore passing it onward.\n\n## Minimal handoff pattern\n\n```bash\n# Set this to the generated skill directory; the commands below are portable.\nexport SKILL_ROOT=\"${SKILL_ROOT:?Set SKILL_ROOT to the generated skill directory}\"\nWORKDIR=\"$(mktemp -d)\"\n\n# Parser-only check; this does not instantiate ETE3 or access the network.\npython \"$SKILL_ROOT\u002Fsub-skills\u002Ftaxonomy-helper\u002Fscripts\u002Fgimme_taxa.py\" --help\n\n# Deliberate lookup: choose a writable database and output file first.\npython \"$SKILL_ROOT\u002Fsub-skills\u002Ftaxonomy-helper\u002Fscripts\u002Fgimme_taxa.py\" \\\n  --database \"$WORKDIR\u002Ftaxonomy.sqlite\" \\\n  --just-taxids \\\n  --outfile \"$WORKDIR\u002Fdescendant-taxids.txt\" \\\n  Escherichia\n\n# Consume only after inspecting the generated file.\nncbi-genome-download --taxids \"$WORKDIR\u002Fdescendant-taxids.txt\" bacteria\n```\n\nThe lookup command may download\u002Fcreate the database. Add `--update` only when\nrefreshing it is intended, and use `-v` or `-vv` when diagnostic output is\nneeded. Keep helper diagnostics on stderr and the data file on `--outfile` (or\nstdout when `--outfile` is omitted) so shell redirection cannot accidentally\nmix status text into the TaxID file.\n","# Taxonomy helper\n\n`gimme_taxa.py` is an optional, experimental contributed workflow. It uses\nETE3's `NCBITaxa` interface and a local NCBI taxonomy database to resolve each\ncomma-separated positional input (a taxon name, a numeric TaxID, or both) and\nthen either emit descendants or describe the supplied taxa. It is a separate\npreparation step; it is not part of the main download CLI.\n\nUse the bundled helper at [`scripts\u002Fgimme_taxa.py`](scripts\u002Fgimme_taxa.py), not\nan original source checkout. The helper's parser preserves the public spellings\n`-v\u002F--verbose`, `-d\u002F--database`, `-u\u002F--update`, `-j\u002F--just-taxids`,\n`-i\u002F--taxon-info`, and `-o\u002F--outfile`.\n\n## Choose an output mode\n\n- **Download input (`-j` \u002F `--just-taxids`)**: write one descendant TaxID per\n  line, with no header. This is the only output mode intended for direct use as\n  an `ncbi-genome-download --taxids` input file. See\n  [`..\u002Fdownload-and-filter\u002FSKILL.md`](..\u002Fdownload-and-filter\u002FSKILL.md) for the\n  consuming download command and its filters.\n- **Default descendant report**: write a header followed by tab-separated rows\n  with `parent_taxid`, `descendent_taxid`, and `descendent_name`. This is for\n  inspection, not direct `--taxids` consumption.\n- **Taxon metadata (`-i` \u002F `--taxon-info`)**: write a header followed by\n  tab-separated `name`, `taxid`, `rank`, and `lineage` columns for the supplied\n  taxa. If `-i` and `-j` are both supplied, the source's `taxon-info` branch\n  takes precedence.\n\nThe source spelling `descendent` in the default header is intentional. Do not\nsilently deduplicate or reorder rows: the helper emits the returned ETE3\nsequence once for each supplied parent. The actual names and descendants are\nproperties of the local taxonomy database and were not live-queried during\nverification.\n\n## Safety boundary\n\nA lookup can have network and filesystem side effects. Constructing\n`NCBITaxa` may create or download a local taxonomy SQLite database when no\nusable database exists. `--update` (`-u`) explicitly asks ETE3 to refresh that\ndatabase and can take several minutes and require network access. Prefer an\nexplicit, writable `--database` path in a controlled workspace, record that\npath, and use the same path on later runs. Do not enable `--update` merely to\nproduce help or to test parsing.\n\nThe helper requires a Python environment in which ETE3 and its expected\nruntime dependencies `six` and `numpy` are installed. Installation and\ndatabase acquisition are deliberately outside the download skill's normal\nverification: no live taxonomy database query was run. First run `--help`,\nthen make a deliberate decision about dependency installation, database\nlocation, and network access before querying.\n\nFor checksums, file existence, and downstream output validation, follow\n[`..\u002Foutput-and-integrity\u002FSKILL.md`](..\u002Foutput-and-integrity\u002FSKILL.md). Treat the\nTaxID file as generated input: inspect its headerless, one-ID-per-line format\nbefore passing it onward.\n\n## Minimal handoff pattern\n\n```bash\n# Set this to the generated skill directory; the commands below are portable.\nexport SKILL_ROOT=\"${SKILL_ROOT:?Set SKILL_ROOT to the generated skill directory}\"\nWORKDIR=\"$(mktemp -d)\"\n\n# Parser-only check; this does not instantiate ETE3 or access the network.\npython \"$SKILL_ROOT\u002Fsub-skills\u002Ftaxonomy-helper\u002Fscripts\u002Fgimme_taxa.py\" --help\n\n# Deliberate lookup: choose a writable database and output file first.\npython \"$SKILL_ROOT\u002Fsub-skills\u002Ftaxonomy-helper\u002Fscripts\u002Fgimme_taxa.py\" \\\n  --database \"$WORKDIR\u002Ftaxonomy.sqlite\" \\\n  --just-taxids \\\n  --outfile \"$WORKDIR\u002Fdescendant-taxids.txt\" \\\n  Escherichia\n\n# Consume only after inspecting the generated file.\nncbi-genome-download --taxids \"$WORKDIR\u002Fdescendant-taxids.txt\" bacteria\n```\n\nThe lookup command may download\u002Fcreate the database. Add `--update` only when\nrefreshing it is intended, and use `-v` or `-vv` when diagnostic output is\nneeded. Keep helper diagnostics on stderr and the data file on `--outfile` (or\nstdout when `--outfile` is omitted) so shell redirection cannot accidentally\nmix status text into the TaxID file.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fncbi-genome-download\u002Fsub-skills\u002Ftaxonomy-helper",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill taxonomy-helper",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill taxonomy-helper",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill taxonomy-helper","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fncbi-genome-download\u002Fsub-skills\u002Ftaxonomy-helper\u002FSKILL.md",[47,53,57],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fdependencies-and-troubleshooting.md","REFERENCE","参考文档",5740,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fncbi-genome-download\u002Fsub-skills\u002Ftaxonomy-helper\u002Freferences\u002Fdependencies-and-troubleshooting.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fworkflow.md",5430,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fncbi-genome-download\u002Fsub-skills\u002Ftaxonomy-helper\u002Freferences\u002Fworkflow.md",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Fgimme_taxa.py","SCRIPT","脚本",7068,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fncbi-genome-download\u002Fsub-skills\u002Ftaxonomy-helper\u002Fscripts\u002Fgimme_taxa.py",[64,71,78,85,92,99],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]