[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79769X5J4P9DFF1XR1QNFSK":3,"skill-same:01M79769X5J4P9DFF1XR1QNFSK":85},{"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":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":35,"install":36,"resources":48},"01M79769X5J4P9DFF1XR1QNFSK","vizro",null,"Use Vizro to build, validate, debug, extend, and maintain dashboards across vizro-core, Vizro-MCP, deprecated Vizro-AI, experimental chat, and Vizro Dash Components.","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\u002Fvizro\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: vizro\ndescription: \"Use Vizro to build, validate, debug, extend, and maintain\n  dashboards across vizro-core, Vizro-MCP, deprecated Vizro-AI, experimental\n  chat, and Vizro Dash Components.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\n  source-repo: mckinsey\u002Fvizro\n  source-commit: 99634b8e837d371f0d25c53692278b39236594e6\nlicense: Apache 2.0\n---\n\n# Vizro\n\nUse this skill when a task involves the Vizro monorepo or the installed Vizro packages: dashboard authoring, model\u002FYAML validation, charts\u002Ftables\u002Flayouts\u002Factions, MCP-assisted dashboard generation, the deprecated `vizro-ai` chart agent, experimental chat\u002Fpopup components, or `vizro-dash-components` custom Dash components.\n\n## Start Here\n\n1. Read `references\u002Frepo-provenance.md` to confirm the source snapshot, evidence scope, and freshness limits.\n2. Read `references\u002Fpackage-map.md` to identify the relevant package, public API surface, and known version-specific facts.\n3. Read `references\u002Fenvironment.md` before installing packages, building `vizro-dash-components`, running tests, using browser-backed examples, or touching provider-backed LLM features.\n4. Run `python scripts\u002Fprobe_vizro_environment.py` in the target environment for a quick installed-package smoke check.\n5. Use the route map below. Each sub-skill owns task-specific workflows and near references.\n6. When modifying this repository, also route to `sub-skills\u002Frepo-development-testing\u002FSKILL.md` for package-specific commands, backend-classified tests, and AGENTS constraints.\n\n## Route Map\n\n| User task | Use sub-skill | Why |\n| --- | --- | --- |\n| Build\u002Frun a Vizro dashboard in Python or YAML; validate `Dashboard`\u002F`Page`\u002Flayout basics | `sub-skills\u002Fcore-dashboard-build\u002FSKILL.md` | Owns `Vizro().build()`, `Vizro().run()`, dashboard\u002Fpage models, Python\u002FYAML authoring, layout-first debug patterns. |\n| Add or debug cards, graphs, tables, filters, selectors, data sources, custom components, or actions | `sub-skills\u002Fcore-components-data-actions\u002FSKILL.md` | Owns Vizro model composition, `data_manager`, action wiring, controls, table\u002Fgrid behavior, and validation failures. |\n| Choose or author charts\u002Ffigures\u002Ftables with Plotly\u002FVizro conventions | `sub-skills\u002Fcharts-and-figures\u002FSKILL.md` | Owns `vizro.plotly.express`, custom chart callables, visual-vocabulary guidance, and figure model pitfalls. |\n| Use or change Vizro-MCP agent\u002Fserver workflows | `sub-skills\u002Fmcp-agent-workflows\u002FSKILL.md` | Owns FastMCP server tools\u002Fresources, dashboard creation\u002Fvalidation helpers, schema extraction, and PyCafe workflows. |\n| Inspect or maintain the deprecated `vizro-ai` chart agent | `sub-skills\u002Flegacy-ai-chart-agent\u002FSKILL.md` | Owns `chart_agent`, response models, safeguard behavior, and deprecation-safe routing. |\n| Use or modify `vizro-experimental` chat component or floating popup | `sub-skills\u002Fexperimental-chat-popup\u002FSKILL.md` | Owns `Chat`, `add_chat_popup`, lazy agent helpers, BYO callback mode, and security constraints. |\n| Use\u002Fmaintain `vizro-dash-components` Cascader\u002FMarkdown components or generated wrappers | `sub-skills\u002Fdash-components-build\u002FSKILL.md` | Owns TypeScript source-of-truth, npm\u002Fwebpack\u002Fdash-generate-components pipeline, props, and browser-test constraints. |\n| Change repository code, docs, tests, build config, or package metadata | `sub-skills\u002Frepo-development-testing\u002FSKILL.md` | Owns monorepo layout, Hatch commands, package-local test commands, changelog, and backend-classified verification. |\n\n## Public Package Facts\n\n- `vizro-core` installs the public distribution `vizro`. Public Python examples typically use:\n\n  ```python\n  import vizro.models as vm\n  from vizro import Vizro\n\n  dashboard = vm.Dashboard(pages=[vm.Page(title=\"Home\", components=[vm.Card(text=\"Hello\")])])\n  app = Vizro().build(dashboard)   # returns the Vizro wrapper, not the raw Dash app\n  app.run()\n  ```\n\n  The underlying Dash app is `app.dash` after build.\n- `vizro.plotly.express` provides Vizro-oriented wrappers around Plotly Express; use it when authoring standard Vizro charts unless the task requires custom Plotly code.\n- `vizro-mcp` is the preferred maintained agent-assistance path for new AI\u002Fdashboard workflows.\n- `vizro-ai` is deprecated in this checkout. Maintain existing chart-agent behavior when requested, but do not recommend it for greenfield workflows when Vizro-MCP\u002Fe2e-flow is a better fit.\n- `vizro-experimental` APIs may change or graduate into `vizro-core`; state that caveat in user-facing solutions.\n- `vizro-dash-components` source of truth is TypeScript\u002FReact under `src\u002Fts`. Python files and JS bundles under `vizro_dash_components\u002F` are generated; do not hand-edit them.\n\n## Safety Defaults\n\n- Do not run live LLM provider calls unless the user explicitly supplies\u002Fauthorizes credentials and network use. Prefer import, schema, or BYO callback checks.\n- Do not require browser-backed `dash_duo`\u002FSelenium\u002Fe2e tests on hosts without Chrome\u002FChromium. Treat them as optional backend-specific gates and document the missing backend.\n- Do not run full monorepo test suites first. Start with package-local focused tests for the touched behavior; then broaden if needed.\n- Do not edit generated `vizro_dash_components\u002F*.py` or JS bundles directly. Edit TypeScript in `vizro-dash-components\u002Fsrc\u002Fts` and regenerate.\n- For repo edits, obey package-local `AGENTS.md`\u002F`CLAUDE.md`: Hatch commands run from the specific package directory; `vizro-e2e-flow` is a Claude plugin and its guide says no Hatch commands.\n\n## Bundled Helpers\n\n- `scripts\u002Fprobe_vizro_environment.py` checks imports and small CPU-only smoke behavior across Vizro packages.\n- `scripts\u002Finspect_vizro_schema.py` summarizes public Vizro model fields\u002Fschemas for dashboard-writing tasks.\n- `scripts\u002Fvalidate_vizro_dashboard.py` validates a small Python or YAML dashboard path when the installed package and PyYAML are available.\n\n## Common First Moves\n\n- User wants a dashboard: route to `core-dashboard-build`, then to `charts-and-figures` and `core-components-data-actions` as components\u002Fcharts\u002Factions\u002Fdata appear.\n- User wants AI-generated or agent-validated dashboards: route to `mcp-agent-workflows`; only use `legacy-ai-chart-agent` if the task explicitly mentions `vizro-ai` or existing chart-agent code.\n- User wants chat in a dashboard: route to `experimental-chat-popup`; prefer BYO `generate_response` for credential-free examples.\n- User touches custom Dash components: route to `dash-components-build` and `repo-development-testing`.\n- User touches repository code: load the relevant feature subskill plus `repo-development-testing`, then run focused tests with the package-local working directory.\n","# Vizro\n\nUse this skill when a task involves the Vizro monorepo or the installed Vizro packages: dashboard authoring, model\u002FYAML validation, charts\u002Ftables\u002Flayouts\u002Factions, MCP-assisted dashboard generation, the deprecated `vizro-ai` chart agent, experimental chat\u002Fpopup components, or `vizro-dash-components` custom Dash components.\n\n## Start Here\n\n1. Read `references\u002Frepo-provenance.md` to confirm the source snapshot, evidence scope, and freshness limits.\n2. Read `references\u002Fpackage-map.md` to identify the relevant package, public API surface, and known version-specific facts.\n3. Read `references\u002Fenvironment.md` before installing packages, building `vizro-dash-components`, running tests, using browser-backed examples, or touching provider-backed LLM features.\n4. Run `python scripts\u002Fprobe_vizro_environment.py` in the target environment for a quick installed-package smoke check.\n5. Use the route map below. Each sub-skill owns task-specific workflows and near references.\n6. When modifying this repository, also route to `sub-skills\u002Frepo-development-testing\u002FSKILL.md` for package-specific commands, backend-classified tests, and AGENTS constraints.\n\n## Route Map\n\n| User task | Use sub-skill | Why |\n| --- | --- | --- |\n| Build\u002Frun a Vizro dashboard in Python or YAML; validate `Dashboard`\u002F`Page`\u002Flayout basics | `sub-skills\u002Fcore-dashboard-build\u002FSKILL.md` | Owns `Vizro().build()`, `Vizro().run()`, dashboard\u002Fpage models, Python\u002FYAML authoring, layout-first debug patterns. |\n| Add or debug cards, graphs, tables, filters, selectors, data sources, custom components, or actions | `sub-skills\u002Fcore-components-data-actions\u002FSKILL.md` | Owns Vizro model composition, `data_manager`, action wiring, controls, table\u002Fgrid behavior, and validation failures. |\n| Choose or author charts\u002Ffigures\u002Ftables with Plotly\u002FVizro conventions | `sub-skills\u002Fcharts-and-figures\u002FSKILL.md` | Owns `vizro.plotly.express`, custom chart callables, visual-vocabulary guidance, and figure model pitfalls. |\n| Use or change Vizro-MCP agent\u002Fserver workflows | `sub-skills\u002Fmcp-agent-workflows\u002FSKILL.md` | Owns FastMCP server tools\u002Fresources, dashboard creation\u002Fvalidation helpers, schema extraction, and PyCafe workflows. |\n| Inspect or maintain the deprecated `vizro-ai` chart agent | `sub-skills\u002Flegacy-ai-chart-agent\u002FSKILL.md` | Owns `chart_agent`, response models, safeguard behavior, and deprecation-safe routing. |\n| Use or modify `vizro-experimental` chat component or floating popup | `sub-skills\u002Fexperimental-chat-popup\u002FSKILL.md` | Owns `Chat`, `add_chat_popup`, lazy agent helpers, BYO callback mode, and security constraints. |\n| Use\u002Fmaintain `vizro-dash-components` Cascader\u002FMarkdown components or generated wrappers | `sub-skills\u002Fdash-components-build\u002FSKILL.md` | Owns TypeScript source-of-truth, npm\u002Fwebpack\u002Fdash-generate-components pipeline, props, and browser-test constraints. |\n| Change repository code, docs, tests, build config, or package metadata | `sub-skills\u002Frepo-development-testing\u002FSKILL.md` | Owns monorepo layout, Hatch commands, package-local test commands, changelog, and backend-classified verification. |\n\n## Public Package Facts\n\n- `vizro-core` installs the public distribution `vizro`. Public Python examples typically use:\n\n  ```python\n  import vizro.models as vm\n  from vizro import Vizro\n\n  dashboard = vm.Dashboard(pages=[vm.Page(title=\"Home\", components=[vm.Card(text=\"Hello\")])])\n  app = Vizro().build(dashboard)   # returns the Vizro wrapper, not the raw Dash app\n  app.run()\n  ```\n\n  The underlying Dash app is `app.dash` after build.\n- `vizro.plotly.express` provides Vizro-oriented wrappers around Plotly Express; use it when authoring standard Vizro charts unless the task requires custom Plotly code.\n- `vizro-mcp` is the preferred maintained agent-assistance path for new AI\u002Fdashboard workflows.\n- `vizro-ai` is deprecated in this checkout. Maintain existing chart-agent behavior when requested, but do not recommend it for greenfield workflows when Vizro-MCP\u002Fe2e-flow is a better fit.\n- `vizro-experimental` APIs may change or graduate into `vizro-core`; state that caveat in user-facing solutions.\n- `vizro-dash-components` source of truth is TypeScript\u002FReact under `src\u002Fts`. Python files and JS bundles under `vizro_dash_components\u002F` are generated; do not hand-edit them.\n\n## Safety Defaults\n\n- Do not run live LLM provider calls unless the user explicitly supplies\u002Fauthorizes credentials and network use. Prefer import, schema, or BYO callback checks.\n- Do not require browser-backed `dash_duo`\u002FSelenium\u002Fe2e tests on hosts without Chrome\u002FChromium. Treat them as optional backend-specific gates and document the missing backend.\n- Do not run full monorepo test suites first. Start with package-local focused tests for the touched behavior; then broaden if needed.\n- Do not edit generated `vizro_dash_components\u002F*.py` or JS bundles directly. Edit TypeScript in `vizro-dash-components\u002Fsrc\u002Fts` and regenerate.\n- For repo edits, obey package-local `AGENTS.md`\u002F`CLAUDE.md`: Hatch commands run from the specific package directory; `vizro-e2e-flow` is a Claude plugin and its guide says no Hatch commands.\n\n## Bundled Helpers\n\n- `scripts\u002Fprobe_vizro_environment.py` checks imports and small CPU-only smoke behavior across Vizro packages.\n- `scripts\u002Finspect_vizro_schema.py` summarizes public Vizro model fields\u002Fschemas for dashboard-writing tasks.\n- `scripts\u002Fvalidate_vizro_dashboard.py` validates a small Python or YAML dashboard path when the installed package and PyYAML are available.\n\n## Common First Moves\n\n- User wants a dashboard: route to `core-dashboard-build`, then to `charts-and-figures` and `core-components-data-actions` as components\u002Fcharts\u002Factions\u002Fdata appear.\n- User wants AI-generated or agent-validated dashboards: route to `mcp-agent-workflows`; only use `legacy-ai-chart-agent` if the task explicitly mentions `vizro-ai` or existing chart-agent code.\n- User wants chat in a dashboard: route to `experimental-chat-popup`; prefer BYO `generate_response` for credential-free examples.\n- User touches custom Dash components: route to `dash-components-build` and `repo-development-testing`.\n- User touches repository code: load the relevant feature subskill plus `repo-development-testing`, then run focused tests with the package-local working directory.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":28},"Apache 2.0",{"disco-role":25,"source-repo":26,"source-commit":27},"operating","mckinsey\u002Fvizro","99634b8e837d371f0d25c53692278b39236594e6",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fvizro",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":28},[38,41,44],{"tool":39,"command":40},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill vizro",{"tool":42,"command":43},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill vizro",{"tool":45,"command":46},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill vizro","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvizro\u002FSKILL.md",[49,55,59,63,67,71,77,81],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fenvironment.md","REFERENCE","参考文档",4638,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvizro\u002Freferences\u002Fenvironment.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fpackage-map.md",5007,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvizro\u002Freferences\u002Fpackage-map.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Frepo-provenance.md",2827,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvizro\u002Freferences\u002Frepo-provenance.md",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Frepo-routing-metadata.json",398,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvizro\u002Freferences\u002Frepo-routing-metadata.json",{"path":68,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fverification.md",4292,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvizro\u002Freferences\u002Fverification.md",{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"scripts\u002Finspect_vizro_schema.py","SCRIPT","脚本",2146,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvizro\u002Fscripts\u002Finspect_vizro_schema.py",{"path":78,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":79,"sourceHtmlUrl":80},"scripts\u002Fprobe_vizro_environment.py",4665,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvizro\u002Fscripts\u002Fprobe_vizro_environment.py",{"path":82,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":83,"sourceHtmlUrl":84},"scripts\u002Fvalidate_vizro_dashboard.py",2272,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvizro\u002Fscripts\u002Fvalidate_vizro_dashboard.py",[86,93,100,107,114,121],{"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},"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":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},"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"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":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"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",[],[]]