[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78VZBD14HM3X70SWG694QDZ":3,"skill-same:01M78VZBD14HM3X70SWG694QDZ":66},{"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},"01M78VZBD14HM3X70SWG694QDZ","deepxiv-sdk",null,"Use the DeepXiv SDK for citation-aware academic and web research through its Python Reader, deepxiv CLI, progressive paper APIs, optional local LangGraph agent, PMC, bioRxiv\u002FmedRxiv, and trending workflows.","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\u002Fdeepxiv-sdk\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: deepxiv-sdk\ndescription: \"Use the DeepXiv SDK for citation-aware academic and web research\n  through its Python Reader, deepxiv CLI, progressive paper APIs, optional local\n  LangGraph agent, PMC, bioRxiv\u002FmedRxiv, and trending workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# DeepXiv SDK\n\nUse this repo skill when a task needs DeepXiv's hosted literature service or\nits optional local research agent. It teaches a later Researcher how to choose\nbetween the Python SDK and CLI, preserve citations and evidence strength, and\navoid credential, quota, truncation, and stale-API mistakes.\n\n## Start here\n\n1. Confirm the installed package and CLI are the expected 1.0.x surface:\n   `python -c \"import deepxiv_sdk; print(deepxiv_sdk.__version__)\"` and\n   `deepxiv --help`. If the executable lists an older command set, repair the\n   installation before using route-specific flags.\n2. Install the base package with `python -m pip install deepxiv-sdk`. For the\n   optional local OpenAI-compatible LangGraph agent use\n   `python -m pip install \"deepxiv-sdk[agent]\"` (or `[all]`) and install\n   `tiktoken` separately if the optional-import probe reports it missing.\n3. Keep DeepXiv and model-provider credentials outside prompts, source files,\n   logs, and commits. Ordinary retrieval uses a DeepXiv token; hosted `ask`\n   requires a registered account key and has a separate agentic quota.\n4. Run the no-network [installation check](scripts\u002Fcheck_install.py) before\n   diagnosing package or optional-dependency problems.\n\n## Route by task\n\n- **Python literature research:** Read\n  [reader-and-paper-research](sub-skills\u002Freader-and-paper-research\u002FSKILL.md)\n  for `Reader`, hosted agentic search, source\u002Fcitation handling, progressive\n  reading, biomedical sources, PMC, and trending signals.\n- **Shell commands and operations:** Read\n  [cli-and-operations](sub-skills\u002Fcli-and-operations\u002FSKILL.md) for command\n  selection, flag partitions, JSON\u002Ftext output, stdout\u002Fstderr, token setup,\n  health\u002Fdebug, and CLI recovery.\n- **Local model-driven research loop:** Read\n  [optional-local-agent](sub-skills\u002Foptional-local-agent\u002FSKILL.md) for the\n  optional `Agent`, LangGraph tools, provider options, persistent paper context,\n  budgets, and circuit-breaker behavior.\n\n## Shared operating rules\n\n- Prefer the narrowest evidence operation: search or `brief` first, then\n  `head`, one or two sections, or `preview`; avoid `raw`\u002F`json` for routine\n  screening.\n- Hosted `agent_search` and `agent_search_stream` distinguish arXiv and web\n  flags. Preserve arXiv IDs or URLs, separate retrieved sources from sources\n  cited in the answer, and reject `answer_truncated` or streamed `error` output\n  as complete evidence.\n- The SDK retries ordinary GET timeouts\u002Fconnections with exponential backoff,\n  but hosted agentic calls deliberately do not auto-retry because each call can\n  spend quota. Correct the query or wait rather than hammering the endpoint.\n- Network, registered credentials, remote LLM keys, and live service results\n  are runtime prerequisites; this skill does not claim them from import or\n  help checks. Read [cross-cutting troubleshooting](references\u002Ftroubleshooting.md)\n  and the [provenance baseline](references\u002Frepo-provenance.md) when a mismatch\n  or stale checkout is suspected.\n","# DeepXiv SDK\n\nUse this repo skill when a task needs DeepXiv's hosted literature service or\nits optional local research agent. It teaches a later Researcher how to choose\nbetween the Python SDK and CLI, preserve citations and evidence strength, and\navoid credential, quota, truncation, and stale-API mistakes.\n\n## Start here\n\n1. Confirm the installed package and CLI are the expected 1.0.x surface:\n   `python -c \"import deepxiv_sdk; print(deepxiv_sdk.__version__)\"` and\n   `deepxiv --help`. If the executable lists an older command set, repair the\n   installation before using route-specific flags.\n2. Install the base package with `python -m pip install deepxiv-sdk`. For the\n   optional local OpenAI-compatible LangGraph agent use\n   `python -m pip install \"deepxiv-sdk[agent]\"` (or `[all]`) and install\n   `tiktoken` separately if the optional-import probe reports it missing.\n3. Keep DeepXiv and model-provider credentials outside prompts, source files,\n   logs, and commits. Ordinary retrieval uses a DeepXiv token; hosted `ask`\n   requires a registered account key and has a separate agentic quota.\n4. Run the no-network [installation check](scripts\u002Fcheck_install.py) before\n   diagnosing package or optional-dependency problems.\n\n## Route by task\n\n- **Python literature research:** Read\n  [reader-and-paper-research](sub-skills\u002Freader-and-paper-research\u002FSKILL.md)\n  for `Reader`, hosted agentic search, source\u002Fcitation handling, progressive\n  reading, biomedical sources, PMC, and trending signals.\n- **Shell commands and operations:** Read\n  [cli-and-operations](sub-skills\u002Fcli-and-operations\u002FSKILL.md) for command\n  selection, flag partitions, JSON\u002Ftext output, stdout\u002Fstderr, token setup,\n  health\u002Fdebug, and CLI recovery.\n- **Local model-driven research loop:** Read\n  [optional-local-agent](sub-skills\u002Foptional-local-agent\u002FSKILL.md) for the\n  optional `Agent`, LangGraph tools, provider options, persistent paper context,\n  budgets, and circuit-breaker behavior.\n\n## Shared operating rules\n\n- Prefer the narrowest evidence operation: search or `brief` first, then\n  `head`, one or two sections, or `preview`; avoid `raw`\u002F`json` for routine\n  screening.\n- Hosted `agent_search` and `agent_search_stream` distinguish arXiv and web\n  flags. Preserve arXiv IDs or URLs, separate retrieved sources from sources\n  cited in the answer, and reject `answer_truncated` or streamed `error` output\n  as complete evidence.\n- The SDK retries ordinary GET timeouts\u002Fconnections with exponential backoff,\n  but hosted agentic calls deliberately do not auto-retry because each call can\n  spend quota. Correct the query or wait rather than hammering the endpoint.\n- Network, registered credentials, remote LLM keys, and live service results\n  are runtime prerequisites; this skill does not claim them from import or\n  help checks. Read [cross-cutting troubleshooting](references\u002Ftroubleshooting.md)\n  and the [provenance baseline](references\u002Frepo-provenance.md) when a mismatch\n  or stale checkout is suspected.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fdeepxiv-sdk",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 deepxiv-sdk",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill deepxiv-sdk",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill deepxiv-sdk","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeepxiv-sdk\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Frepo-provenance.md","REFERENCE","参考文档",1739,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeepxiv-sdk\u002Freferences\u002Frepo-provenance.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-routing-metadata.json",769,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeepxiv-sdk\u002Freferences\u002Frepo-routing-metadata.json",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",4062,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeepxiv-sdk\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fcheck_install.py","SCRIPT","脚本",2938,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdeepxiv-sdk\u002Fscripts\u002Fcheck_install.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]