[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792T2DGC4C3MM4ABHCDWGWF":3,"skill-same:01M792T2DGC4C3MM4ABHCDWGWF":57},{"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},"01M792T2DGC4C3MM4ABHCDWGWF","dashboard",null,"Route Plexe's dashboard and workdir inspection workflow.","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\u002Fplexe\u002Fsub-skills\u002Fdashboard\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dashboard\ndescription: \"Route Plexe's dashboard and workdir inspection workflow.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# dashboard\n\nUse this sub-skill for Plexe's Streamlit dashboard and saved-run inspection workflow.\nIt is the right route when the user wants to browse experiment history, checkpoints,\nsearch trees, evaluation reports, or packaged model files.\n\n## Typical triggers\n\n- \"Open the Plexe dashboard\"\n- \"What does this workdir contain?\"\n- \"Why isn't my saved run showing up?\"\n- \"Inspect the checkpoints or model package for this experiment\"\n- \"How does Plexe discover experiments in `workdir\u002F`?\"\n\n## What belongs here\n\n- `python -m plexe.viz --work-dir ...`\n- `plexe.viz.main`\n- `plexe.utils.dashboard.app`\n- experiment discovery and metadata extraction\n- checkpoint and report loading\n- dashboard tabs and model package presentation\n- workdir structure assumptions for saved runs\n\n## What stays out\n\n- Training, retraining, Spark setup, and packaging decisions belong in\n  [model-building](..\u002Fmodel-building\u002FSKILL.md).\n- Repository maintenance and release automation stay outside this skill.\n\n## Read these references first when needed\n\n- [`references\u002Fdashboard-workflow.md`](references\u002Fdashboard-workflow.md) for the launch command,\n  environment variables, experiment discovery, tabs, and workdir layout.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for missing workdirs,\n  empty dashboards, malformed checkpoints, and dependency problems.\n- [`..\u002F..\u002Fscripts\u002Finspect_workdir.py`](..\u002F..\u002Fscripts\u002Finspect_workdir.py) when you need a\n  quick read-only summary without opening the Streamlit UI.\n\n## How to work this route\n\n1. Confirm the workdir path and whether the user wants the dashboard or a text summary.\n2. Check that the run has checkpoints and a packaged model before blaming the UI.\n3. Use the dashboard reference to map a question to the correct tab or file.\n4. Use the troubleshooting reference when the workdir is empty, corrupt, or incomplete.\n\n## What the dashboard expects\n\n- Saved experiment directories grouped by dataset name and timestamp.\n- `checkpoints\u002F*.json` files for phase progress and search state.\n- `.build\u002Freports\u002F*.yaml` files for generated reports.\n- `model\u002F` and `model.tar.gz` for packaged model inspection.\n- `model\u002Fmodel.yaml` plus `schemas\u002F` and `src\u002F` files for the package tab.\n\nIf those files are missing, the dashboard may still open but will show warnings or empty panes.\n\n## Common questions this route answers\n\n- Which phase did the run reach?\n- Why is a run marked failed, paused, or running?\n- What did the best search node look like?\n- Did the package get written and what files does it contain?\n- Which saved runs exist for a given dataset?\n\n## Decision points\n\n- If the path exists but no experiments appear, check the depth and naming convention first.\n- If the run exists but a tab is empty, inspect whether the corresponding checkpoint or report file was written.\n- If the package tab is missing fields, confirm the final packaging phase completed.\n- If you only need a text summary, use the bundled workdir inspector instead of opening Streamlit.\n\n## Bundle ownership\n\nThis sub-skill owns the dashboard workflow reference and its troubleshooting notes.\nThe root skill should only route here, not duplicate the tab-by-tab behavior.\n","# dashboard\n\nUse this sub-skill for Plexe's Streamlit dashboard and saved-run inspection workflow.\nIt is the right route when the user wants to browse experiment history, checkpoints,\nsearch trees, evaluation reports, or packaged model files.\n\n## Typical triggers\n\n- \"Open the Plexe dashboard\"\n- \"What does this workdir contain?\"\n- \"Why isn't my saved run showing up?\"\n- \"Inspect the checkpoints or model package for this experiment\"\n- \"How does Plexe discover experiments in `workdir\u002F`?\"\n\n## What belongs here\n\n- `python -m plexe.viz --work-dir ...`\n- `plexe.viz.main`\n- `plexe.utils.dashboard.app`\n- experiment discovery and metadata extraction\n- checkpoint and report loading\n- dashboard tabs and model package presentation\n- workdir structure assumptions for saved runs\n\n## What stays out\n\n- Training, retraining, Spark setup, and packaging decisions belong in\n  [model-building](..\u002Fmodel-building\u002FSKILL.md).\n- Repository maintenance and release automation stay outside this skill.\n\n## Read these references first when needed\n\n- [`references\u002Fdashboard-workflow.md`](references\u002Fdashboard-workflow.md) for the launch command,\n  environment variables, experiment discovery, tabs, and workdir layout.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for missing workdirs,\n  empty dashboards, malformed checkpoints, and dependency problems.\n- [`..\u002F..\u002Fscripts\u002Finspect_workdir.py`](..\u002F..\u002Fscripts\u002Finspect_workdir.py) when you need a\n  quick read-only summary without opening the Streamlit UI.\n\n## How to work this route\n\n1. Confirm the workdir path and whether the user wants the dashboard or a text summary.\n2. Check that the run has checkpoints and a packaged model before blaming the UI.\n3. Use the dashboard reference to map a question to the correct tab or file.\n4. Use the troubleshooting reference when the workdir is empty, corrupt, or incomplete.\n\n## What the dashboard expects\n\n- Saved experiment directories grouped by dataset name and timestamp.\n- `checkpoints\u002F*.json` files for phase progress and search state.\n- `.build\u002Freports\u002F*.yaml` files for generated reports.\n- `model\u002F` and `model.tar.gz` for packaged model inspection.\n- `model\u002Fmodel.yaml` plus `schemas\u002F` and `src\u002F` files for the package tab.\n\nIf those files are missing, the dashboard may still open but will show warnings or empty panes.\n\n## Common questions this route answers\n\n- Which phase did the run reach?\n- Why is a run marked failed, paused, or running?\n- What did the best search node look like?\n- Did the package get written and what files does it contain?\n- Which saved runs exist for a given dataset?\n\n## Decision points\n\n- If the path exists but no experiments appear, check the depth and naming convention first.\n- If the run exists but a tab is empty, inspect whether the corresponding checkpoint or report file was written.\n- If the package tab is missing fields, confirm the final packaging phase completed.\n- If you only need a text summary, use the bundled workdir inspector instead of opening Streamlit.\n\n## Bundle ownership\n\nThis sub-skill owns the dashboard workflow reference and its troubleshooting notes.\nThe root skill should only route here, not duplicate the tab-by-tab behavior.\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\u002Fplexe\u002Fsub-skills\u002Fdashboard",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 dashboard",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill dashboard",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill dashboard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fplexe\u002Fsub-skills\u002Fdashboard\u002FSKILL.md",[47,53],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fdashboard-workflow.md","REFERENCE","参考文档",2628,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fplexe\u002Fsub-skills\u002Fdashboard\u002Freferences\u002Fdashboard-workflow.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",2521,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fplexe\u002Fsub-skills\u002Fdashboard\u002Freferences\u002Ftroubleshooting.md",[58,65,72,79,86,93],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"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":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"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":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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",[],[]]