[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F7TQFDFSAXAY7S1Q7XD2HX":3,"skill-same:01M7F7TQFDFSAXAY7S1Q7XD2HX":67},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":48},"01M7F7TQFDFSAXAY7S1Q7XD2HX","bertviz",null,"Route BertViz Transformer attention visualization, neuron-view, notebook, and HTML export workflows.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fbertviz\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: bertviz\ndescription: \"Route BertViz Transformer attention visualization, neuron-view,\n  notebook, and HTML export workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# BertViz\n\nUse this repo skill when a task involves BertViz, Transformer attention\nvisualization, head\u002Fmodel view rendering, neuron-level query\u002Fkey inspection, or\nsaving BertViz notebook visualizations as HTML.\n\n## Install and quick check\n\nFor ordinary use:\n\n```bash\npip install bertviz\n```\n\nFor interactive notebooks also install and enable a notebook frontend such as\nJupyterLab plus widgets:\n\n```bash\npip install jupyterlab ipywidgets\n```\n\nMinimal package\u002FAPI check:\n\n```bash\npython - \u003C\u003C'PY'\nfrom bertviz import head_view, model_view\nfrom bertviz.neuron_view import get_attention\nprint(\"bertviz import ok\", head_view.__name__, model_view.__name__, get_attention.__name__)\nPY\n```\n\nFor a stronger no-network check, run [`scripts\u002Fcheck_bertviz_environment.py`](scripts\u002Fcheck_bertviz_environment.py).\n\n## Route by task\n\n| User need | Read next |\n| --- | --- |\n| Visualize standard self-attention tensors from Hugging Face or another Transformer model. | [`sub-skills\u002Fattention-views\u002FSKILL.md`](sub-skills\u002Fattention-views\u002FSKILL.md) |\n| Render sentence-pair head\u002Fmodel views with `sentence_b_start`. | [`sub-skills\u002Fattention-views\u002FSKILL.md`](sub-skills\u002Fattention-views\u002FSKILL.md) |\n| Render encoder, decoder, or cross-attention for sequence-to-sequence models. | [`sub-skills\u002Fattention-views\u002FSKILL.md`](sub-skills\u002Fattention-views\u002FSKILL.md) |\n| Save BertViz output as standalone HTML or use it outside a notebook display call. | [`sub-skills\u002Fattention-views\u002FSKILL.md`](sub-skills\u002Fattention-views\u002FSKILL.md), or [`sub-skills\u002Fneuron-view\u002FSKILL.md`](sub-skills\u002Fneuron-view\u002FSKILL.md) for neuron view |\n| Inspect query\u002Fkey neuron contributions using BertViz's modified model classes. | [`sub-skills\u002Fneuron-view\u002FSKILL.md`](sub-skills\u002Fneuron-view\u002FSKILL.md) |\n| Diagnose package installation, notebook display, PyTorch\u002FIPython dependency, or JS asset issues. | [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) |\n| Check whether this skill matches the current BertViz checkout\u002Fversion. | [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md) |\n\n## Core distinctions\n\n- `head_view` and `model_view` consume attention tensors. They are the right\n  choice when the model can return Hugging Face-style attention weights with\n  `output_attentions=True`.\n- `neuron_view.show` computes a visualization payload from BertViz's modified\n  BERT\u002FGPT-2\u002FRoBERTa\u002FXLNet classes because neuron view needs query and key\n  vectors, not only attention probabilities.\n- BertViz is a visualization tool, not a model explanation guarantee. It helps\n  inspect attention patterns but should not be presented as proving causal\n  feature attribution.\n\n## Repo-level references and scripts\n\n- [`references\u002Fenvironment-and-install.md`](references\u002Fenvironment-and-install.md)\n  explains dependencies, notebook frontend expectations, backend assumptions,\n  and offline validation strategy.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) covers\n  cross-cutting install\u002Fimport\u002Fdisplay\u002Fruntime symptoms.\n- [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md) records the\n  source snapshot and evidence paths used to build this skill.\n- [`scripts\u002Fcheck_bertviz_environment.py`](scripts\u002Fcheck_bertviz_environment.py)\n  checks imports, function signatures, packaged JavaScript assets, and optional\n  neuron-view imports without downloading models.\n\n## Safety defaults\n\n- Do not run public notebooks or `from_pretrained(...)` examples automatically\n  when network\u002Fmodel downloads are not explicitly allowed.\n- Prefer bundled no-network helpers for validation: the root environment check,\n  `attention-views\u002Fscripts\u002Frender_synthetic_attention.py`, and\n  `neuron-view\u002Fscripts\u002Fvalidate_toy_bert_attention.py`.\n- Keep generated outputs and saved HTML in user-chosen working directories;\n  BertViz does not require modifying its installed package files.\n","# BertViz\n\nUse this repo skill when a task involves BertViz, Transformer attention\nvisualization, head\u002Fmodel view rendering, neuron-level query\u002Fkey inspection, or\nsaving BertViz notebook visualizations as HTML.\n\n## Install and quick check\n\nFor ordinary use:\n\n```bash\npip install bertviz\n```\n\nFor interactive notebooks also install and enable a notebook frontend such as\nJupyterLab plus widgets:\n\n```bash\npip install jupyterlab ipywidgets\n```\n\nMinimal package\u002FAPI check:\n\n```bash\npython - \u003C\u003C'PY'\nfrom bertviz import head_view, model_view\nfrom bertviz.neuron_view import get_attention\nprint(\"bertviz import ok\", head_view.__name__, model_view.__name__, get_attention.__name__)\nPY\n```\n\nFor a stronger no-network check, run [`scripts\u002Fcheck_bertviz_environment.py`](scripts\u002Fcheck_bertviz_environment.py).\n\n## Route by task\n\n| User need | Read next |\n| --- | --- |\n| Visualize standard self-attention tensors from Hugging Face or another Transformer model. | [`sub-skills\u002Fattention-views\u002FSKILL.md`](sub-skills\u002Fattention-views\u002FSKILL.md) |\n| Render sentence-pair head\u002Fmodel views with `sentence_b_start`. | [`sub-skills\u002Fattention-views\u002FSKILL.md`](sub-skills\u002Fattention-views\u002FSKILL.md) |\n| Render encoder, decoder, or cross-attention for sequence-to-sequence models. | [`sub-skills\u002Fattention-views\u002FSKILL.md`](sub-skills\u002Fattention-views\u002FSKILL.md) |\n| Save BertViz output as standalone HTML or use it outside a notebook display call. | [`sub-skills\u002Fattention-views\u002FSKILL.md`](sub-skills\u002Fattention-views\u002FSKILL.md), or [`sub-skills\u002Fneuron-view\u002FSKILL.md`](sub-skills\u002Fneuron-view\u002FSKILL.md) for neuron view |\n| Inspect query\u002Fkey neuron contributions using BertViz's modified model classes. | [`sub-skills\u002Fneuron-view\u002FSKILL.md`](sub-skills\u002Fneuron-view\u002FSKILL.md) |\n| Diagnose package installation, notebook display, PyTorch\u002FIPython dependency, or JS asset issues. | [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) |\n| Check whether this skill matches the current BertViz checkout\u002Fversion. | [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md) |\n\n## Core distinctions\n\n- `head_view` and `model_view` consume attention tensors. They are the right\n  choice when the model can return Hugging Face-style attention weights with\n  `output_attentions=True`.\n- `neuron_view.show` computes a visualization payload from BertViz's modified\n  BERT\u002FGPT-2\u002FRoBERTa\u002FXLNet classes because neuron view needs query and key\n  vectors, not only attention probabilities.\n- BertViz is a visualization tool, not a model explanation guarantee. It helps\n  inspect attention patterns but should not be presented as proving causal\n  feature attribution.\n\n## Repo-level references and scripts\n\n- [`references\u002Fenvironment-and-install.md`](references\u002Fenvironment-and-install.md)\n  explains dependencies, notebook frontend expectations, backend assumptions,\n  and offline validation strategy.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) covers\n  cross-cutting install\u002Fimport\u002Fdisplay\u002Fruntime symptoms.\n- [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md) records the\n  source snapshot and evidence paths used to build this skill.\n- [`scripts\u002Fcheck_bertviz_environment.py`](scripts\u002Fcheck_bertviz_environment.py)\n  checks imports, function signatures, packaged JavaScript assets, and optional\n  neuron-view imports without downloading models.\n\n## Safety defaults\n\n- Do not run public notebooks or `from_pretrained(...)` examples automatically\n  when network\u002Fmodel downloads are not explicitly allowed.\n- Prefer bundled no-network helpers for validation: the root environment check,\n  `attention-views\u002Fscripts\u002Frender_synthetic_attention.py`, and\n  `neuron-view\u002Fscripts\u002Fvalidate_toy_bert_attention.py`.\n- Keep generated outputs and saved HTML in user-chosen working directories;\n  BertViz does not require modifying its installed package files.\n",{"name":5,"license":24,"metadata":25,"description":7,"disable-model-invocation":27},"Apache 2.0",{"disco-role":26},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fbertviz",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":27},[38,41,44],{"tool":39,"command":40},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill bertviz",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill bertviz",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill bertviz","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fbertviz\u002FSKILL.md",[49,55,59,63],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fenvironment-and-install.md","REFERENCE","参考文档",2683,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fbertviz\u002Freferences\u002Fenvironment-and-install.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Frepo-provenance.md",2167,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fbertviz\u002Freferences\u002Frepo-provenance.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Frepo-routing-metadata.json",312,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fbertviz\u002Freferences\u002Frepo-routing-metadata.json",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Ftroubleshooting.md",2664,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fbertviz\u002Freferences\u002Ftroubleshooting.md",[68,76,81,88,95,102],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":77,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]