[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EPDY43JMXCKGDPWSJKCPV2":3,"skill-same:01M7EPDY43JMXCKGDPWSJKCPV2":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},"01M7EPDY43JMXCKGDPWSJKCPV2","paperai",null,"Guides paperai workflows for indexing paper corpora, querying scientific articles, and generating RAG-backed Markdown, CSV, or PDF-annotation reports.","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\u002F04-安全渗透\u002Fpaperai\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: paperai\ndescription: \"Guides paperai workflows for indexing paper corpora, querying\n  scientific articles, and generating RAG-backed Markdown, CSV, or\n  PDF-annotation reports.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# paperai\n\n`paperai` is a Python application for searching and analyzing scientific and\nmedical paper corpora. It combines a paperetl-style SQLite database with a\ntxtai embeddings index and optional LLM\u002FRAG pipelines. Use this skill when a\ntask asks to build a paperai index, search indexed articles, expose enriched\nsearch results, or generate repeatable reports.\n\n## Install and inspect\n\nUse Python 3.10+ and install the public package:\n\n```bash\npython -m pip install \"paperai==2.6.0\"\npython -m pip check\n# from the generated paperai skill directory\npython scripts\u002Fcheck_install.py\n```\n\nThe last command is a bundled, no-download import check; it does not load model\nweights or validate a corpus. Read [references\u002Finstall.md](references\u002Finstall.md)\nfor dependency and runtime boundaries, and [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md)\nfor cross-cutting failures.\n\n## Route by task\n\n- **Build or inspect an index, validate `articles.sqlite`, train static vectors,\n  or export section text:** read\n  [indexing](sub-skills\u002Findexing\u002FSKILL.md).\n- **Run one-shot searches, use `paperai` shell, integrate the enriched API, or\n  make a search UI:** read [querying](sub-skills\u002Fquerying\u002FSKILL.md).\n- **Define YAML tasks and produce Markdown\u002FCSV\u002FPDF-annotation reports:** read\n  [reporting](sub-skills\u002Freporting\u002FSKILL.md).\n\nA normal end-to-end handoff is `indexing → querying` or\n`indexing → reporting`. The generated skill contains the needed API details and\nsafe helpers; do not reopen the original repository's source, examples, tests,\nor checkout-specific paths.\n\n## Shared model-directory contract\n\nMost workflows receive one directory containing `articles.sqlite` and saved\ntxtai artifacts (`config` or `config.json` plus model\u002Findex files). The database\nis normally produced by paperetl and is not created by paperai. Validate its\ntables and columns before model construction. Model identifiers can trigger\nnetwork downloads and optional GPU use; state the cache, device, data, and\nruntime constraints before starting a large operation.\n\n## Verification boundary\n\nA successful import proves package plumbing only. Validate actual model loading,\nSQLite schema compatibility, retrieval quality, report rendering, and optional\nPDF annotation separately. Keep `maxsize`, `toprank`, `topn`, and report context\nbounded for smoke runs. Markdown\u002FCSV are the portable default; `ant` annotation\nrequires original PDFs and additional runtime support.\n\nRead [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before using\nthis skill with a changed checkout. If the commit, package version, or evidence\npaths differ, refresh the repo skill instead of assuming the guidance is current.\n","# paperai\n\n`paperai` is a Python application for searching and analyzing scientific and\nmedical paper corpora. It combines a paperetl-style SQLite database with a\ntxtai embeddings index and optional LLM\u002FRAG pipelines. Use this skill when a\ntask asks to build a paperai index, search indexed articles, expose enriched\nsearch results, or generate repeatable reports.\n\n## Install and inspect\n\nUse Python 3.10+ and install the public package:\n\n```bash\npython -m pip install \"paperai==2.6.0\"\npython -m pip check\n# from the generated paperai skill directory\npython scripts\u002Fcheck_install.py\n```\n\nThe last command is a bundled, no-download import check; it does not load model\nweights or validate a corpus. Read [references\u002Finstall.md](references\u002Finstall.md)\nfor dependency and runtime boundaries, and [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md)\nfor cross-cutting failures.\n\n## Route by task\n\n- **Build or inspect an index, validate `articles.sqlite`, train static vectors,\n  or export section text:** read\n  [indexing](sub-skills\u002Findexing\u002FSKILL.md).\n- **Run one-shot searches, use `paperai` shell, integrate the enriched API, or\n  make a search UI:** read [querying](sub-skills\u002Fquerying\u002FSKILL.md).\n- **Define YAML tasks and produce Markdown\u002FCSV\u002FPDF-annotation reports:** read\n  [reporting](sub-skills\u002Freporting\u002FSKILL.md).\n\nA normal end-to-end handoff is `indexing → querying` or\n`indexing → reporting`. The generated skill contains the needed API details and\nsafe helpers; do not reopen the original repository's source, examples, tests,\nor checkout-specific paths.\n\n## Shared model-directory contract\n\nMost workflows receive one directory containing `articles.sqlite` and saved\ntxtai artifacts (`config` or `config.json` plus model\u002Findex files). The database\nis normally produced by paperetl and is not created by paperai. Validate its\ntables and columns before model construction. Model identifiers can trigger\nnetwork downloads and optional GPU use; state the cache, device, data, and\nruntime constraints before starting a large operation.\n\n## Verification boundary\n\nA successful import proves package plumbing only. Validate actual model loading,\nSQLite schema compatibility, retrieval quality, report rendering, and optional\nPDF annotation separately. Keep `maxsize`, `toprank`, `topn`, and report context\nbounded for smoke runs. Markdown\u002FCSV are the portable default; `ant` annotation\nrequires original PDFs and additional runtime support.\n\nRead [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before using\nthis skill with a changed checkout. If the commit, package version, or evidence\npaths differ, refresh the repo skill instead of assuming the guidance is current.\n",{"name":5,"license":24,"metadata":25,"description":7,"disable-model-invocation":27},"Apache 2.0",{"disco-role":26},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Fpaperai",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 paperai",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill paperai",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill paperai","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpaperai\u002FSKILL.md",[49,55,59,63],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Finstall.md","REFERENCE","参考文档",1706,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpaperai\u002Freferences\u002Finstall.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Frepo-provenance.md",1359,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpaperai\u002Freferences\u002Frepo-provenance.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Frepo-routing-metadata.json",492,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpaperai\u002Freferences\u002Frepo-routing-metadata.json",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Ftroubleshooting.md",2263,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fpaperai\u002Freferences\u002Ftroubleshooting.md",[68,77,82,89,96,103],{"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":76},"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",[],[],"2026-11-16 10:05:34",{"skillNo":78,"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":79,"categories":80,"keywords":81,"publishedAt":76},"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":76},"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":76},"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":76},"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":76},"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",[],[]]