[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7976ZA4CSDCMWNX8GP35HT6":3,"skill-same:01M7976ZA4CSDCMWNX8GP35HT6":47},{"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},"01M7976ZA4CSDCMWNX8GP35HT6","mcp-agent-workflows",null,"Use and maintain Vizro-MCP FastMCP server workflows for dashboard creation, validation, schemas, and PyCafe sharing.","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\u002Fsub-skills\u002Fmcp-agent-workflows\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: mcp-agent-workflows\ndescription: \"Use and maintain Vizro-MCP FastMCP server workflows for dashboard\n  creation, validation, schemas, and PyCafe sharing.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# MCP Agent Workflows\n\nUse this sub-skill when the task involves `vizro-mcp`, MCP server setup, agent-assisted dashboard generation, dashboard validation, schema extraction, PyCafe links, or repository changes under `vizro-mcp\u002F`.\n\nRoute elsewhere when the task is mainly about:\n- Hand-writing a dashboard without MCP: `..\u002Fcore-dashboard-build\u002FSKILL.md`.\n- Chart semantics inside a generated dashboard: `..\u002Fcharts-and-figures\u002FSKILL.md`.\n- Deprecated `vizro-ai`: `..\u002Flegacy-ai-chart-agent\u002FSKILL.md`.\n\n## Package facts\n\n- Import package: `vizro_mcp`.\n- Main evidence file: `vizro-mcp\u002Fsrc\u002Fvizro_mcp\u002Fserver.py`.\n- The installed `vizro_mcp.server` exposes `mcp`, `create_dashboard`, `validate_dashboard_config`, schema\u002Fresult models, and PyCafe helper functions in this snapshot.\n- `vizro-mcp` depends on `mcp`, `httpx`, `click`, `pandas[html,parquet,excel]`, `pydantic-settings`, and `vizro`.\n\n## Safe first moves\n\nFor a user asking to use MCP with Vizro:\n\n1. Explain that Vizro-MCP is the maintained agent-assistance route in this monorepo.\n2. Check installed package importability before launching a server:\n\n   ```bash\n   python - \u003C\u003C'PY'\n   import vizro_mcp.server as s\n   print(hasattr(s, 'mcp'), hasattr(s, 'create_dashboard'), hasattr(s, 'validate_dashboard_config'))\n   PY\n   ```\n\n3. Inspect `vizro-mcp\u002FREADME.md` for current server\u002FCLI setup expected by the repository.\n4. Use validation helpers\u002Fschema output before generating or sharing external artifacts.\n\n## Dashboard generation\u002Fvalidation principles\n\n- Treat generated dashboard code\u002Fconfig as untrusted until validated by Vizro models and, when feasible, built with `Vizro().build()`.\n- Validate data paths and external URLs before embedding them in dashboards.\n- Avoid writing files outside a user-approved output directory.\n- Prefer deterministic local validation over agent\u002Fmodel calls when debugging generated code.\n- If PyCafe sharing is requested, confirm whether network upload\u002Flink creation is allowed.\n\n## Schema work\n\nWhen the task asks for schema\u002Fmodel JSON or LLM-facing dashboard instructions:\n\n- Use `vizro_mcp.server` schema helpers and schema models as the source of truth.\n- Cross-check with `vizro-core` model fields using `scripts\u002Finspect_vizro_schema.py` when changes involve core model definitions.\n- Keep schema output free of local absolute paths and secrets.\n\n## Repository edits\n\nFor changes under `vizro-mcp\u002F`:\n\n```bash\ncd vizro-mcp\nhatch run lint\nhatch run test-unit tests\u002Funit\u002Fvizro_mcp\u002Ftest_server.py\n```\n\nIf Hatch is unavailable, use the prepared installed-package environment and run focused `pytest` from `vizro-mcp\u002F`, but preserve the package working directory.\n\n## Common failures\n\n- `validate_dashboard_config` errors usually mean the generated dashboard does not match current `vizro.models` schemas. Inspect the model fields and fix the config, not the validator.\n- Missing Excel\u002Fparquet\u002Fhtml dependencies: install\u002Fverify `pandas[html,parquet,excel]` extras.\n- MCP server launch issues: separate import errors from transport\u002Fserver configuration errors.\n- PyCafe URL issues: check network permission and the helper in `tools\u002Fpycafe\u002Fcreate_pycafe_links_comments.py`.\n\n## Evidence anchors\n\n- `vizro-mcp\u002FREADME.md`\n- `vizro-mcp\u002Fsrc\u002Fvizro_mcp\u002Fserver.py`\n- `vizro-mcp\u002Fsrc\u002Fvizro_mcp\u002F_schemas\u002Fschemas.py`\n- `vizro-mcp\u002Ftests\u002Funit\u002Fvizro_mcp\u002Ftest_server.py`\n- `tools\u002Fpycafe\u002Fcreate_pycafe_links_comments.py`\n","# MCP Agent Workflows\n\nUse this sub-skill when the task involves `vizro-mcp`, MCP server setup, agent-assisted dashboard generation, dashboard validation, schema extraction, PyCafe links, or repository changes under `vizro-mcp\u002F`.\n\nRoute elsewhere when the task is mainly about:\n- Hand-writing a dashboard without MCP: `..\u002Fcore-dashboard-build\u002FSKILL.md`.\n- Chart semantics inside a generated dashboard: `..\u002Fcharts-and-figures\u002FSKILL.md`.\n- Deprecated `vizro-ai`: `..\u002Flegacy-ai-chart-agent\u002FSKILL.md`.\n\n## Package facts\n\n- Import package: `vizro_mcp`.\n- Main evidence file: `vizro-mcp\u002Fsrc\u002Fvizro_mcp\u002Fserver.py`.\n- The installed `vizro_mcp.server` exposes `mcp`, `create_dashboard`, `validate_dashboard_config`, schema\u002Fresult models, and PyCafe helper functions in this snapshot.\n- `vizro-mcp` depends on `mcp`, `httpx`, `click`, `pandas[html,parquet,excel]`, `pydantic-settings`, and `vizro`.\n\n## Safe first moves\n\nFor a user asking to use MCP with Vizro:\n\n1. Explain that Vizro-MCP is the maintained agent-assistance route in this monorepo.\n2. Check installed package importability before launching a server:\n\n   ```bash\n   python - \u003C\u003C'PY'\n   import vizro_mcp.server as s\n   print(hasattr(s, 'mcp'), hasattr(s, 'create_dashboard'), hasattr(s, 'validate_dashboard_config'))\n   PY\n   ```\n\n3. Inspect `vizro-mcp\u002FREADME.md` for current server\u002FCLI setup expected by the repository.\n4. Use validation helpers\u002Fschema output before generating or sharing external artifacts.\n\n## Dashboard generation\u002Fvalidation principles\n\n- Treat generated dashboard code\u002Fconfig as untrusted until validated by Vizro models and, when feasible, built with `Vizro().build()`.\n- Validate data paths and external URLs before embedding them in dashboards.\n- Avoid writing files outside a user-approved output directory.\n- Prefer deterministic local validation over agent\u002Fmodel calls when debugging generated code.\n- If PyCafe sharing is requested, confirm whether network upload\u002Flink creation is allowed.\n\n## Schema work\n\nWhen the task asks for schema\u002Fmodel JSON or LLM-facing dashboard instructions:\n\n- Use `vizro_mcp.server` schema helpers and schema models as the source of truth.\n- Cross-check with `vizro-core` model fields using `scripts\u002Finspect_vizro_schema.py` when changes involve core model definitions.\n- Keep schema output free of local absolute paths and secrets.\n\n## Repository edits\n\nFor changes under `vizro-mcp\u002F`:\n\n```bash\ncd vizro-mcp\nhatch run lint\nhatch run test-unit tests\u002Funit\u002Fvizro_mcp\u002Ftest_server.py\n```\n\nIf Hatch is unavailable, use the prepared installed-package environment and run focused `pytest` from `vizro-mcp\u002F`, but preserve the package working directory.\n\n## Common failures\n\n- `validate_dashboard_config` errors usually mean the generated dashboard does not match current `vizro.models` schemas. Inspect the model fields and fix the config, not the validator.\n- Missing Excel\u002Fparquet\u002Fhtml dependencies: install\u002Fverify `pandas[html,parquet,excel]` extras.\n- MCP server launch issues: separate import errors from transport\u002Fserver configuration errors.\n- PyCafe URL issues: check network permission and the helper in `tools\u002Fpycafe\u002Fcreate_pycafe_links_comments.py`.\n\n## Evidence anchors\n\n- `vizro-mcp\u002FREADME.md`\n- `vizro-mcp\u002Fsrc\u002Fvizro_mcp\u002Fserver.py`\n- `vizro-mcp\u002Fsrc\u002Fvizro_mcp\u002F_schemas\u002Fschemas.py`\n- `vizro-mcp\u002Ftests\u002Funit\u002Fvizro_mcp\u002Ftest_server.py`\n- `tools\u002Fpycafe\u002Fcreate_pycafe_links_comments.py`\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\u002Fvizro\u002Fsub-skills\u002Fmcp-agent-workflows",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 mcp-agent-workflows",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill mcp-agent-workflows",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill mcp-agent-workflows","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvizro\u002Fsub-skills\u002Fmcp-agent-workflows\u002FSKILL.md",[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"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":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"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":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":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},"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":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},"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",[],[]]