[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78T87JQWRMCT1CZ0DAS2VXT":3,"skill-same:01M78T87JQWRMCT1CZ0DAS2VXT":69},{"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},"01M78T87JQWRMCT1CZ0DAS2VXT","analysis-visualization",null,"Inspect and visualize trained BERTopic models with topic, document, distribution, time, class, and hierarchy views.","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\u002Fbertopic\u002Fsub-skills\u002Fanalysis-visualization\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: analysis-visualization\ndescription: \"Inspect and visualize trained BERTopic models with topic,\n  document, distribution, time, class, and hierarchy views.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\n  package: BERTopic\n  package-version: \"0.17.4\"\n  parent-skill: bertopic\nlicense: MIT\n---\n\n# analysis-visualization\n\nUse this sub-skill when the model is already fitted and the task is to inspect, compare, or visualize topics, documents, topic distributions, hierarchy, temporal change, or class-specific topic views.\n\n## Route here for\n\n- `get_topic_info`, `get_topic`, `get_topics`, `get_topic_freq`, `get_representative_docs`\n- `hierarchical_topics`, `get_topic_tree`\n- `approximate_distribution`, `topics_over_time`, `topics_per_class`\n- all `visualize_*` methods, including topic maps, document views, hierarchy views, heatmaps, bar charts, term-rank plots, topic-over-time plots, topics-per-class plots, probability\u002Fdistribution plots, and approximate-distribution tables\n\n## Route elsewhere\n\n- Fitting, transforming, partial updates, topic mutation, outlier reassignment, or model building: use the topic-modeling sub-skill.\n- Embedding backend selection or downloads: use the embeddings-backends sub-skill.\n- Vectorizer \u002F c-TF-IDF tuning and topic-word refreshes: use the vectorizers-ctfidf sub-skill.\n- Representation models, labeling, or multi-aspect label generation: use the representations-labeling sub-skill.\n- Save\u002Fload, hub publishing, or serialization formats: use the serialization sub-skill.\n\n## Operating references\n\n1. [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md)\n2. [`references\u002Fworkflows.md`](references\u002Fworkflows.md)\n3. [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md)\n4. [`scripts\u002Fsmoke_visualization.py`](scripts\u002Fsmoke_visualization.py)\n\n## Minimal decision flow\n\n- Need a quick readout of what the model learned? Start with `get_topic_info()`, `get_topic_freq()`, `get_topic()`, and `get_representative_docs()`.\n- Need a global topic landscape? Use `visualize_topics()`, `visualize_barchart()`, `visualize_heatmap()`, and `visualize_term_rank()`.\n- Need document-level inspection? Use `visualize_documents()` or `visualize_hierarchical_documents()` with precomputed `reduced_embeddings` when possible.\n- Need a single-document distribution? Use `approximate_distribution()` and then `visualize_distribution()` or `visualize_approximate_distribution()`.\n- Need time or class comparison? Use `topics_over_time()` \u002F `visualize_topics_over_time()` or `topics_per_class()` \u002F `visualize_topics_per_class()`.\n- Need hierarchy? Use `hierarchical_topics()`, inspect `get_topic_tree()`, then render `visualize_hierarchy()`.\n\n## Notes\n\n- Most plot functions exclude topic `-1` by default.\n- `custom_labels` in plotting calls can be a boolean or an aspect-name string when the model has matching topic aspects.\n- `visualize_topics()` and `visualize_hierarchy()` need UMAP for internal 2D topic layout; document views can avoid UMAP by accepting `reduced_embeddings`.\n- `visualize_document_datamap()` needs `datamapplot`; `visualize_approximate_distribution()` returns a styled table only when Jinja2 is available.\n\n## Verification anchors\n\n- Tiny synthetic no-download model: exercise `visualize_topics`, `visualize_barchart`, `visualize_heatmap`, `visualize_documents`, and `visualize_distribution` from precomputed embeddings without downloading external models.\n- Small-corpus analysis loop: compute `approximate_distribution`, `hierarchical_topics`, and `get_topic_tree`, then connect them to the distribution and hierarchy plots.\n\n## Handoff constraint\n\nKeep this sub-skill focused on inspection and visualization. Do not pull fit, backend, vectorizer, representation, or serialization setup into this skill.\n","# analysis-visualization\n\nUse this sub-skill when the model is already fitted and the task is to inspect, compare, or visualize topics, documents, topic distributions, hierarchy, temporal change, or class-specific topic views.\n\n## Route here for\n\n- `get_topic_info`, `get_topic`, `get_topics`, `get_topic_freq`, `get_representative_docs`\n- `hierarchical_topics`, `get_topic_tree`\n- `approximate_distribution`, `topics_over_time`, `topics_per_class`\n- all `visualize_*` methods, including topic maps, document views, hierarchy views, heatmaps, bar charts, term-rank plots, topic-over-time plots, topics-per-class plots, probability\u002Fdistribution plots, and approximate-distribution tables\n\n## Route elsewhere\n\n- Fitting, transforming, partial updates, topic mutation, outlier reassignment, or model building: use the topic-modeling sub-skill.\n- Embedding backend selection or downloads: use the embeddings-backends sub-skill.\n- Vectorizer \u002F c-TF-IDF tuning and topic-word refreshes: use the vectorizers-ctfidf sub-skill.\n- Representation models, labeling, or multi-aspect label generation: use the representations-labeling sub-skill.\n- Save\u002Fload, hub publishing, or serialization formats: use the serialization sub-skill.\n\n## Operating references\n\n1. [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md)\n2. [`references\u002Fworkflows.md`](references\u002Fworkflows.md)\n3. [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md)\n4. [`scripts\u002Fsmoke_visualization.py`](scripts\u002Fsmoke_visualization.py)\n\n## Minimal decision flow\n\n- Need a quick readout of what the model learned? Start with `get_topic_info()`, `get_topic_freq()`, `get_topic()`, and `get_representative_docs()`.\n- Need a global topic landscape? Use `visualize_topics()`, `visualize_barchart()`, `visualize_heatmap()`, and `visualize_term_rank()`.\n- Need document-level inspection? Use `visualize_documents()` or `visualize_hierarchical_documents()` with precomputed `reduced_embeddings` when possible.\n- Need a single-document distribution? Use `approximate_distribution()` and then `visualize_distribution()` or `visualize_approximate_distribution()`.\n- Need time or class comparison? Use `topics_over_time()` \u002F `visualize_topics_over_time()` or `topics_per_class()` \u002F `visualize_topics_per_class()`.\n- Need hierarchy? Use `hierarchical_topics()`, inspect `get_topic_tree()`, then render `visualize_hierarchy()`.\n\n## Notes\n\n- Most plot functions exclude topic `-1` by default.\n- `custom_labels` in plotting calls can be a boolean or an aspect-name string when the model has matching topic aspects.\n- `visualize_topics()` and `visualize_hierarchy()` need UMAP for internal 2D topic layout; document views can avoid UMAP by accepting `reduced_embeddings`.\n- `visualize_document_datamap()` needs `datamapplot`; `visualize_approximate_distribution()` returns a styled table only when Jinja2 is available.\n\n## Verification anchors\n\n- Tiny synthetic no-download model: exercise `visualize_topics`, `visualize_barchart`, `visualize_heatmap`, `visualize_documents`, and `visualize_distribution` from precomputed embeddings without downloading external models.\n- Small-corpus analysis loop: compute `approximate_distribution`, `hierarchical_topics`, and `get_topic_tree`, then connect them to the distribution and hierarchy plots.\n\n## Handoff constraint\n\nKeep this sub-skill focused on inspection and visualization. Do not pull fit, backend, vectorizer, representation, or serialization setup into this skill.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":28},{"package":24,"disco-role":25,"parent-skill":26,"package-version":27},"BERTopic","operating","bertopic","0.17.4",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fbertopic\u002Fsub-skills\u002Fanalysis-visualization",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 analysis-visualization",{"tool":42,"command":43},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill analysis-visualization",{"tool":45,"command":46},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill analysis-visualization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbertopic\u002Fsub-skills\u002Fanalysis-visualization\u002FSKILL.md",[49,55,59,63],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fapi-reference.md","REFERENCE","参考文档",11864,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbertopic\u002Fsub-skills\u002Fanalysis-visualization\u002Freferences\u002Fapi-reference.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Ftroubleshooting.md",7388,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbertopic\u002Fsub-skills\u002Fanalysis-visualization\u002Freferences\u002Ftroubleshooting.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fworkflows.md",6437,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbertopic\u002Fsub-skills\u002Fanalysis-visualization\u002Freferences\u002Fworkflows.md",{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"scripts\u002Fsmoke_visualization.py","SCRIPT","脚本",11354,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbertopic\u002Fsub-skills\u002Fanalysis-visualization\u002Fscripts\u002Fsmoke_visualization.py",[70,78,85,92,99,106],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":74,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":74,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":74,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":74,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":74,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":74,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"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",[],[]]