[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792FTGAXTK5WR021JWA7H7S":3,"skill-same:01M792FTGAXTK5WR021JWA7H7S":75},{"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},"01M792FTGAXTK5WR021JWA7H7S","reporting",null,"Create and troubleshoot paperai 2.6.0 YAML reports in Markdown, CSV, or optional PDF annotation format, including generated columns and safe configuration validation.","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\u002Fpaperai\u002Fsub-skills\u002Freporting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: reporting\ndescription: \"Create and troubleshoot paperai 2.6.0 YAML reports in Markdown,\n  CSV, or optional PDF annotation format, including generated columns and safe\n  configuration validation.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Reporting\n\nUse this route to turn an existing paperai corpus\u002Findex into a bounded report.\nStart with [configuration](references\u002Fconfiguration.md) for YAML and column\nsemantics, [workflows](references\u002Fworkflows.md) for staged runs,\n[api-reference](references\u002Fapi-reference.md) for Python calls, and\n[cli-reference](references\u002Fcli-reference.md) for the positional module CLI.\nUse [troubleshooting](references\u002Ftroubleshooting.md) before changing a model,\ncorpus, or report definition.\n\n## Scope and routing\n\n- **Owns:** `Task.load`, `Task.queries`, one-level `Task.flatten`, report YAML,\n  standard\u002Fconstant\u002Fgenerated columns, `Execute.options`\u002F`create`\u002F`run`,\n  Markdown (`md`), CSV (`csv`), optional PDF annotation (`ant`), output naming,\n  `topn`, `threshold`, `indir`, `allsections`, `section`, `surround`,\n  `matches`, `snippet`, and column conversion helpers.\n- **Requires:** a model directory containing `articles.sqlite` and a compatible\n  saved txtai embeddings index. Use [indexing](..\u002Findexing\u002FSKILL.md) for corpus\n  schema, index construction, vector configuration, and compatibility.\n- **Delegates:** search syntax, score filtering, grouping, and highlight\n  internals to [querying](..\u002Fquerying\u002FSKILL.md). Do not use this route to repair\n  SQLite, build embeddings, or ingest source PDFs.\n\n## Safe route\n\n1. Copy the minimal, standard-column YAML in [configuration](references\u002Fconfiguration.md)\n   and replace every placeholder. Run the bundled\n   [the safe validator](scripts\u002Fvalidate_report_config.py) before loading a\n   model; it parses YAML and checks shape only, without importing paperai,\n   opening SQLite, or touching models.\n2. Confirm the model directory and database\u002Findex prerequisites. For `ant`,\n   also confirm a readable source directory and exact source basenames.\n3. Run one narrow query with explicit `topn` and `md`. Add one generated field,\n   then `dtype`\u002Fcontext controls, then switch to CSV or annotation.\n4. Inspect output files with a Markdown\u002FCSV parser and plan a fresh output\n   directory or unique names: paperai opens outputs in write mode and does not\n   prompt before replacement.\n\n## Fast facts\n\n- Renderer values are exactly `md`, `csv`, and `ant`; missing render resolves\n  to Markdown, while another value raises `ValueError`.\n- A task path writes beside the YAML. Its root `name` is the Markdown\u002Fmaster\n  output stem. Markdown is `\u003Cname>.md`; CSV creates one `\u003Cquery-name>.csv` per\n  top-level query and removes its temporary `\u003Cname>.csv`; annotation writes\n  `annotations\u002F\u003CSource>` and removes its temporary `\u003Cname>.ant`.\n- Standard columns are `Id`, `Date`, `Study`, `Study Link`, `Journal`, `Source`,\n  `Entry`, and `Matches`. A `constant` column performs no model call. A\n  generated column has `query` and optional `question`\u002Fcontrols.\n- `query: \"*\"` enumerates all articles and can make `topn` ineffective. The\n  query layer uses a default threshold of 0.25 when threshold is absent.\n  Pass `topn` explicitly: in 2.6.0 `Execute.options` stores a missing value as\n  `None`, which can defeat the nominal `Report.build` fallback of 50.\n- `section: true` expands a match to the full same-named subsection; positive\n  `surround: N` expands to nearby stored section rows. `section` wins if both\n  are set. `matches` controls context snippets per generated field, not article\n  count.\n- `qa` is an `Execute`\u002FCLI parameter but verified 2.6.0 filters it before RAG\n  construction; set YAML `options.llm` for the effective RAG model selector.\n  `ant` additionally requires `txtmarker`, PDFs, and matching `Source` names.\n\nKeep long schemas, renderer details, workflows, and failure matrices in the\nlinked references rather than expanding this router.\n","# Reporting\n\nUse this route to turn an existing paperai corpus\u002Findex into a bounded report.\nStart with [configuration](references\u002Fconfiguration.md) for YAML and column\nsemantics, [workflows](references\u002Fworkflows.md) for staged runs,\n[api-reference](references\u002Fapi-reference.md) for Python calls, and\n[cli-reference](references\u002Fcli-reference.md) for the positional module CLI.\nUse [troubleshooting](references\u002Ftroubleshooting.md) before changing a model,\ncorpus, or report definition.\n\n## Scope and routing\n\n- **Owns:** `Task.load`, `Task.queries`, one-level `Task.flatten`, report YAML,\n  standard\u002Fconstant\u002Fgenerated columns, `Execute.options`\u002F`create`\u002F`run`,\n  Markdown (`md`), CSV (`csv`), optional PDF annotation (`ant`), output naming,\n  `topn`, `threshold`, `indir`, `allsections`, `section`, `surround`,\n  `matches`, `snippet`, and column conversion helpers.\n- **Requires:** a model directory containing `articles.sqlite` and a compatible\n  saved txtai embeddings index. Use [indexing](..\u002Findexing\u002FSKILL.md) for corpus\n  schema, index construction, vector configuration, and compatibility.\n- **Delegates:** search syntax, score filtering, grouping, and highlight\n  internals to [querying](..\u002Fquerying\u002FSKILL.md). Do not use this route to repair\n  SQLite, build embeddings, or ingest source PDFs.\n\n## Safe route\n\n1. Copy the minimal, standard-column YAML in [configuration](references\u002Fconfiguration.md)\n   and replace every placeholder. Run the bundled\n   [the safe validator](scripts\u002Fvalidate_report_config.py) before loading a\n   model; it parses YAML and checks shape only, without importing paperai,\n   opening SQLite, or touching models.\n2. Confirm the model directory and database\u002Findex prerequisites. For `ant`,\n   also confirm a readable source directory and exact source basenames.\n3. Run one narrow query with explicit `topn` and `md`. Add one generated field,\n   then `dtype`\u002Fcontext controls, then switch to CSV or annotation.\n4. Inspect output files with a Markdown\u002FCSV parser and plan a fresh output\n   directory or unique names: paperai opens outputs in write mode and does not\n   prompt before replacement.\n\n## Fast facts\n\n- Renderer values are exactly `md`, `csv`, and `ant`; missing render resolves\n  to Markdown, while another value raises `ValueError`.\n- A task path writes beside the YAML. Its root `name` is the Markdown\u002Fmaster\n  output stem. Markdown is `\u003Cname>.md`; CSV creates one `\u003Cquery-name>.csv` per\n  top-level query and removes its temporary `\u003Cname>.csv`; annotation writes\n  `annotations\u002F\u003CSource>` and removes its temporary `\u003Cname>.ant`.\n- Standard columns are `Id`, `Date`, `Study`, `Study Link`, `Journal`, `Source`,\n  `Entry`, and `Matches`. A `constant` column performs no model call. A\n  generated column has `query` and optional `question`\u002Fcontrols.\n- `query: \"*\"` enumerates all articles and can make `topn` ineffective. The\n  query layer uses a default threshold of 0.25 when threshold is absent.\n  Pass `topn` explicitly: in 2.6.0 `Execute.options` stores a missing value as\n  `None`, which can defeat the nominal `Report.build` fallback of 50.\n- `section: true` expands a match to the full same-named subsection; positive\n  `surround: N` expands to nearby stored section rows. `section` wins if both\n  are set. `matches` controls context snippets per generated field, not article\n  count.\n- `qa` is an `Execute`\u002FCLI parameter but verified 2.6.0 filters it before RAG\n  construction; set YAML `options.llm` for the effective RAG model selector.\n  `ant` additionally requires `txtmarker`, PDFs, and matching `Source` names.\n\nKeep long schemas, renderer details, workflows, and failure matrices in the\nlinked references rather than expanding this router.\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\u002Fpaperai\u002Fsub-skills\u002Freporting",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 reporting",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill reporting",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill reporting","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaperai\u002Fsub-skills\u002Freporting\u002FSKILL.md",[47,53,57,61,65,69],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",4760,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaperai\u002Fsub-skills\u002Freporting\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fcli-reference.md",3087,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaperai\u002Fsub-skills\u002Freporting\u002Freferences\u002Fcli-reference.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fconfiguration.md",7679,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaperai\u002Fsub-skills\u002Freporting\u002Freferences\u002Fconfiguration.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",7373,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaperai\u002Fsub-skills\u002Freporting\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fworkflows.md",5811,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaperai\u002Fsub-skills\u002Freporting\u002Freferences\u002Fworkflows.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fvalidate_report_config.py","SCRIPT","脚本",6926,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaperai\u002Fsub-skills\u002Freporting\u002Fscripts\u002Fvalidate_report_config.py",[76,83,90,97,104,111],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]