[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78WE2D3CJ32EBGVSEV86Y0P":3,"skill-same:01M78WE2D3CJ32EBGVSEV86Y0P":125},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M78WE2D3CJ32EBGVSEV86Y0P","synthdog",null,"Generate synthetic OCR-free document datasets with SynthDoG, render language-specific configs, and adapt the template for custom corpora.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: synthdog\ndescription: \"Generate synthetic OCR-free document datasets with SynthDoG,\n  render language-specific configs, and adapt the template for custom corpora.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# SynthDoG\n\nUse this sub-skill when a user wants to generate synthetic document samples, make OCR-free document data, swap between the English\u002FJapanese\u002FKorean\u002FChinese template configs, or adapt SynthDoG to a new corpus.\n\n## Route first\n\n- Read [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for the render-then-run flow, tiny-fixture smoke, split layout, and metadata layout.\n- Read [`references\u002Fconfiguration.md`](references\u002Fconfiguration.md) for the config knobs, language bundle mapping, and custom-corpus adaptation.\n- Read [`references\u002Fresource-layout.md`](references\u002Fresource-layout.md) for the background\u002Fpaper\u002Fcorpus\u002Ffont directory contract and the asset bundling decision.\n- Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) when `synthtiger`, `pytweening`, NumPy, OpenCV, fonts, corpora, or output paths fail.\n- Use [`scripts\u002Frender_config.py`](scripts\u002Frender_config.py) when you need to turn the bundled placeholder configs into a runnable config that points at external resource directories.\n- For shared install\u002Fimport issues with the broader Donut stack, check the parent-tree troubleshooting file at [`..\u002F..\u002Freferences\u002Ftroubleshooting.md`](..\u002F..\u002Freferences\u002Ftroubleshooting.md) once it exists.\n- If the user is actually trying to fine-tune on generated data, hand off to [`..\u002Ftraining\u002FSKILL.md`](..\u002Ftraining\u002FSKILL.md).\n\n## Boundaries\n\n- Include: template behavior, background\u002Fdocument\u002Fcontent\u002Flayout helper modules, language configs, resource requirements, CLI invocation through `synthtiger`, output directory and metadata layout, tiny-fixture generation.\n- Exclude: Donut training, inference, and evaluation metrics.\n\n## Quick checks\n\n- `python scripts\u002Frender_config.py --help`\n- `synthtiger --help` if SynthDoG is installed in the active environment\n- `python -m py_compile scripts\u002Frender_config.py scripts\u002Ftemplate.py scripts\u002Felements\u002F*.py scripts\u002Flayouts\u002F*.py`\n\n## What to do\n\n1. Choose the language bundle and resource root.\n2. Render a config with `scripts\u002Frender_config.py`.\n3. Run `synthtiger` from this sub-skill root with `scripts\u002Ftemplate.py`, the `SynthDoG` template class name, and the rendered config.\n4. Inspect the split directories and `metadata.jsonl` files that `template.py` writes.\n5. If the user later wants model training on the generated data, route the dataset to the training sub-skill.\n","# SynthDoG\n\nUse this sub-skill when a user wants to generate synthetic document samples, make OCR-free document data, swap between the English\u002FJapanese\u002FKorean\u002FChinese template configs, or adapt SynthDoG to a new corpus.\n\n## Route first\n\n- Read [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for the render-then-run flow, tiny-fixture smoke, split layout, and metadata layout.\n- Read [`references\u002Fconfiguration.md`](references\u002Fconfiguration.md) for the config knobs, language bundle mapping, and custom-corpus adaptation.\n- Read [`references\u002Fresource-layout.md`](references\u002Fresource-layout.md) for the background\u002Fpaper\u002Fcorpus\u002Ffont directory contract and the asset bundling decision.\n- Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) when `synthtiger`, `pytweening`, NumPy, OpenCV, fonts, corpora, or output paths fail.\n- Use [`scripts\u002Frender_config.py`](scripts\u002Frender_config.py) when you need to turn the bundled placeholder configs into a runnable config that points at external resource directories.\n- For shared install\u002Fimport issues with the broader Donut stack, check the parent-tree troubleshooting file at [`..\u002F..\u002Freferences\u002Ftroubleshooting.md`](..\u002F..\u002Freferences\u002Ftroubleshooting.md) once it exists.\n- If the user is actually trying to fine-tune on generated data, hand off to [`..\u002Ftraining\u002FSKILL.md`](..\u002Ftraining\u002FSKILL.md).\n\n## Boundaries\n\n- Include: template behavior, background\u002Fdocument\u002Fcontent\u002Flayout helper modules, language configs, resource requirements, CLI invocation through `synthtiger`, output directory and metadata layout, tiny-fixture generation.\n- Exclude: Donut training, inference, and evaluation metrics.\n\n## Quick checks\n\n- `python scripts\u002Frender_config.py --help`\n- `synthtiger --help` if SynthDoG is installed in the active environment\n- `python -m py_compile scripts\u002Frender_config.py scripts\u002Ftemplate.py scripts\u002Felements\u002F*.py scripts\u002Flayouts\u002F*.py`\n\n## What to do\n\n1. Choose the language bundle and resource root.\n2. Render a config with `scripts\u002Frender_config.py`.\n3. Run `synthtiger` from this sub-skill root with `scripts\u002Ftemplate.py`, the `SynthDoG` template class name, and the rendered config.\n4. Inspect the split directories and `metadata.jsonl` files that `template.py` writes.\n5. If the user later wants model training on the generated data, route the dataset to the training sub-skill.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill synthdog",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill synthdog",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill synthdog","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002FSKILL.md",[46,52,56,60,63,67,71,75,79,85,89,93,97,101,105,109,113,117,121],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fconfigs\u002Fconfig_en.yaml","REFERENCE","参考文档",2627,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Freferences\u002Fconfigs\u002Fconfig_en.yaml",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fconfigs\u002Fconfig_ja.yaml",2628,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Freferences\u002Fconfigs\u002Fconfig_ja.yaml",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fconfigs\u002Fconfig_ko.yaml",2626,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Freferences\u002Fconfigs\u002Fconfig_ko.yaml",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":62},"references\u002Fconfigs\u002Fconfig_zh.yaml","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Freferences\u002Fconfigs\u002Fconfig_zh.yaml",{"path":64,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fconfiguration.md",3944,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Freferences\u002Fconfiguration.md",{"path":68,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fresource-layout.md",2031,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Freferences\u002Fresource-layout.md",{"path":72,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Ftroubleshooting.md",3421,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Freferences\u002Ftroubleshooting.md",{"path":76,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fworkflows.md",2839,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Freferences\u002Fworkflows.md",{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"scripts\u002Felements\u002F__init__.py","SCRIPT","脚本",323,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Fscripts\u002Felements\u002F__init__.py",{"path":86,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":87,"sourceHtmlUrl":88},"scripts\u002Felements\u002Fbackground.py",608,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Fscripts\u002Felements\u002Fbackground.py",{"path":90,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":91,"sourceHtmlUrl":92},"scripts\u002Felements\u002Fcontent.py",3555,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Fscripts\u002Felements\u002Fcontent.py",{"path":94,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":95,"sourceHtmlUrl":96},"scripts\u002Felements\u002Fdocument.py",2418,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Fscripts\u002Felements\u002Fdocument.py",{"path":98,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":99,"sourceHtmlUrl":100},"scripts\u002Felements\u002Fpaper.py",391,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Fscripts\u002Felements\u002Fpaper.py",{"path":102,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":103,"sourceHtmlUrl":104},"scripts\u002Felements\u002Ftextbox.py",1154,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Fscripts\u002Felements\u002Ftextbox.py",{"path":106,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":107,"sourceHtmlUrl":108},"scripts\u002Flayouts\u002F__init__.py",169,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Fscripts\u002Flayouts\u002F__init__.py",{"path":110,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":111,"sourceHtmlUrl":112},"scripts\u002Flayouts\u002Fgrid_stack.py",2506,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Fscripts\u002Flayouts\u002Fgrid_stack.py",{"path":114,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":115,"sourceHtmlUrl":116},"scripts\u002Flayouts\u002Fgrid.py",2329,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Fscripts\u002Flayouts\u002Fgrid.py",{"path":118,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":119,"sourceHtmlUrl":120},"scripts\u002Frender_config.py",6718,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Fscripts\u002Frender_config.py",{"path":122,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":123,"sourceHtmlUrl":124},"scripts\u002Ftemplate.py",5095,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdonut\u002Fsub-skills\u002Fsynthdog\u002Fscripts\u002Ftemplate.py",[126,134,141,148,155,162],{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":130,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"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.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":130,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"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":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":130,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"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":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":130,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"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":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":130,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"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":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":130,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":168,"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",[],[]]