[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78YNEP5AEBZJ78P0EFJC09Y":3,"skill-same:01M78YNEP5AEBZJ78P0EFJC09Y":83},{"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},"01M78YNEP5AEBZJ78P0EFJC09Y","keras-attention",null,"Guides use of the Keras Attention Layer attention package for TensorFlow\u002FKeras sequence models, save\u002Fload checks, debug-mode attention weights, and example workflow troubleshooting.","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\u002Fkeras-attention\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: keras-attention\ndescription: \"Guides use of the Keras Attention Layer attention package for\n  TensorFlow\u002FKeras sequence models, save\u002Fload checks, debug-mode attention\n  weights, and example workflow troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Keras Attention Layer\n\nUse this repo skill when a task involves the `attention` Python package, the\nKeras Attention Layer project, `from attention import Attention`, Luong or\nBahdanau score functions in TensorFlow\u002FKeras sequence models, attention-weight\nvisualization with `KERAS_ATTENTION_DEBUG`, or troubleshooting the package's\nexample workflows.\n\nThe package surface is small and the skill is intentionally root-only: all\nruntime guidance is in this skill directory, with detailed API, examples,\ncompatibility, and troubleshooting notes in bundled references.\n\n## Quick routing\n\n| User need | Read or run |\n| --- | --- |\n| Install and smoke-test the package | Start here, then run `scripts\u002Fsmoke_attention.py`. |\n| Add an attention layer after an RNN\u002FLSTM\u002FGRU | Read `references\u002Fapi-reference.md`. |\n| Choose `score=\"luong\"` vs `score=\"bahdanau\"` or set `units` | Read `references\u002Fapi-reference.md`. |\n| Save and reload a model that contains `Attention` | Read `references\u002Fapi-reference.md` and run `scripts\u002Fsmoke_attention.py --save-format h5`. |\n| Enable\u002Fdebug attention weights or adapt the visualization demos | Read `references\u002Fexamples.md` and `references\u002Ftroubleshooting.md`; run `scripts\u002Fcheck_example_dependencies.py`. |\n| Decide whether a TensorFlow\u002FKeras\u002FPython version is compatible | Read `references\u002Fcompatibility.md`. |\n| Diagnose install\u002Fimport, Keras, Graphviz, dataset, or GPU-warning issues | Read `references\u002Ftroubleshooting.md`. |\n| Check whether this skill is stale for a checkout | Read `references\u002Frepo-provenance.md`. |\n\n## Minimal package contract\n\nInstall from PyPI when using the public package:\n\n```bash\npython -m pip install attention\n```\n\nThen verify the import:\n\n```python\nfrom attention import Attention\n```\n\nThe core layer pattern is:\n\n```python\nfrom tensorflow.keras import Input\nfrom tensorflow.keras.layers import Dense, LSTM\nfrom tensorflow.keras.models import Model\nfrom attention import Attention\n\nmodel_input = Input(shape=(time_steps, input_dim))\nx = LSTM(64, return_sequences=True)(model_input)\nx = Attention(units=32, score=\"luong\")(x)  # or score=\"bahdanau\"\nx = Dense(output_dim)(x)\nmodel = Model(model_input, x)\n```\n\nImportant facts to preserve when helping users:\n\n- Distribution name: `attention`; import module: `attention`; public class:\n  `Attention`.\n- `Attention(units=128, score=\"luong\", **kwargs)` expects a 3D sequence tensor\n  `(batch_size, timesteps, input_dim)` and returns `(batch_size, units)`.\n- Valid score functions are exactly `\"luong\"` and `\"bahdanau\"`; other values\n  raise `ValueError`.\n- Put `return_sequences=True` on the preceding recurrent layer so `Attention`\n  receives all timesteps, not only the final state.\n- When loading a saved model, pass `custom_objects={\"Attention\": Attention}`.\n- Set `KERAS_ATTENTION_DEBUG=1` before importing `attention` only when you need\n  intermediate attention tensors; debug mode changes `Attention` so it is no\n  longer a normal Keras `Layer`.\n\n## Bundled scripts\n\nRun these scripts from the generated skill directory or address them by path\nfrom another working directory. They do not read the original repository\ncheckout.\n\n```bash\npython scripts\u002Fsmoke_attention.py --score both --save-format h5 --force-cpu\n```\n\n`smoke_attention.py` builds tiny Luong and Bahdanau models, checks prediction\nshapes, verifies `get_config()`, and optionally save\u002Floads the model with the\nproper `custom_objects` mapping. Use it after installing the package or when a\nTensorFlow\u002FKeras upgrade may have changed behavior.\n\n```bash\npython scripts\u002Fcheck_example_dependencies.py\n```\n\n`check_example_dependencies.py` verifies optional packages and the Graphviz\n`dot` executable needed by the visualization-oriented examples; it does not run\nlong training or download datasets.\n\n## Boundaries and safety\n\n- This is a package-use skill, not a maintainer workflow. For editing lint,\n  release, or CI configuration, use a repository-maintenance workflow instead.\n- The package has no public CLI and no dataset\u002Fconfig schema beyond ordinary\n  TensorFlow\u002FKeras tensors.\n- The basic bundled smoke is safe and CPU-capable. The IMDB and visualization\n  demos are long-running, may download data or write plots, and should not be\n  treated as default smoke tests.\n- Do not point users back to source-checkout examples or scripts. Use the\n  bundled references and scripts here as the self-contained operating context.\n","# Keras Attention Layer\n\nUse this repo skill when a task involves the `attention` Python package, the\nKeras Attention Layer project, `from attention import Attention`, Luong or\nBahdanau score functions in TensorFlow\u002FKeras sequence models, attention-weight\nvisualization with `KERAS_ATTENTION_DEBUG`, or troubleshooting the package's\nexample workflows.\n\nThe package surface is small and the skill is intentionally root-only: all\nruntime guidance is in this skill directory, with detailed API, examples,\ncompatibility, and troubleshooting notes in bundled references.\n\n## Quick routing\n\n| User need | Read or run |\n| --- | --- |\n| Install and smoke-test the package | Start here, then run `scripts\u002Fsmoke_attention.py`. |\n| Add an attention layer after an RNN\u002FLSTM\u002FGRU | Read `references\u002Fapi-reference.md`. |\n| Choose `score=\"luong\"` vs `score=\"bahdanau\"` or set `units` | Read `references\u002Fapi-reference.md`. |\n| Save and reload a model that contains `Attention` | Read `references\u002Fapi-reference.md` and run `scripts\u002Fsmoke_attention.py --save-format h5`. |\n| Enable\u002Fdebug attention weights or adapt the visualization demos | Read `references\u002Fexamples.md` and `references\u002Ftroubleshooting.md`; run `scripts\u002Fcheck_example_dependencies.py`. |\n| Decide whether a TensorFlow\u002FKeras\u002FPython version is compatible | Read `references\u002Fcompatibility.md`. |\n| Diagnose install\u002Fimport, Keras, Graphviz, dataset, or GPU-warning issues | Read `references\u002Ftroubleshooting.md`. |\n| Check whether this skill is stale for a checkout | Read `references\u002Frepo-provenance.md`. |\n\n## Minimal package contract\n\nInstall from PyPI when using the public package:\n\n```bash\npython -m pip install attention\n```\n\nThen verify the import:\n\n```python\nfrom attention import Attention\n```\n\nThe core layer pattern is:\n\n```python\nfrom tensorflow.keras import Input\nfrom tensorflow.keras.layers import Dense, LSTM\nfrom tensorflow.keras.models import Model\nfrom attention import Attention\n\nmodel_input = Input(shape=(time_steps, input_dim))\nx = LSTM(64, return_sequences=True)(model_input)\nx = Attention(units=32, score=\"luong\")(x)  # or score=\"bahdanau\"\nx = Dense(output_dim)(x)\nmodel = Model(model_input, x)\n```\n\nImportant facts to preserve when helping users:\n\n- Distribution name: `attention`; import module: `attention`; public class:\n  `Attention`.\n- `Attention(units=128, score=\"luong\", **kwargs)` expects a 3D sequence tensor\n  `(batch_size, timesteps, input_dim)` and returns `(batch_size, units)`.\n- Valid score functions are exactly `\"luong\"` and `\"bahdanau\"`; other values\n  raise `ValueError`.\n- Put `return_sequences=True` on the preceding recurrent layer so `Attention`\n  receives all timesteps, not only the final state.\n- When loading a saved model, pass `custom_objects={\"Attention\": Attention}`.\n- Set `KERAS_ATTENTION_DEBUG=1` before importing `attention` only when you need\n  intermediate attention tensors; debug mode changes `Attention` so it is no\n  longer a normal Keras `Layer`.\n\n## Bundled scripts\n\nRun these scripts from the generated skill directory or address them by path\nfrom another working directory. They do not read the original repository\ncheckout.\n\n```bash\npython scripts\u002Fsmoke_attention.py --score both --save-format h5 --force-cpu\n```\n\n`smoke_attention.py` builds tiny Luong and Bahdanau models, checks prediction\nshapes, verifies `get_config()`, and optionally save\u002Floads the model with the\nproper `custom_objects` mapping. Use it after installing the package or when a\nTensorFlow\u002FKeras upgrade may have changed behavior.\n\n```bash\npython scripts\u002Fcheck_example_dependencies.py\n```\n\n`check_example_dependencies.py` verifies optional packages and the Graphviz\n`dot` executable needed by the visualization-oriented examples; it does not run\nlong training or download datasets.\n\n## Boundaries and safety\n\n- This is a package-use skill, not a maintainer workflow. For editing lint,\n  release, or CI configuration, use a repository-maintenance workflow instead.\n- The package has no public CLI and no dataset\u002Fconfig schema beyond ordinary\n  TensorFlow\u002FKeras tensors.\n- The basic bundled smoke is safe and CPU-capable. The IMDB and visualization\n  demos are long-running, may download data or write plots, and should not be\n  treated as default smoke tests.\n- Do not point users back to source-checkout examples or scripts. Use the\n  bundled references and scripts here as the self-contained operating context.\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\u002Fkeras-attention",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 keras-attention",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill keras-attention",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill keras-attention","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkeras-attention\u002FSKILL.md",[47,53,57,61,65,69,73,79],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",5658,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkeras-attention\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fcompatibility.md",3046,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkeras-attention\u002Freferences\u002Fcompatibility.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fexamples.md",5689,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkeras-attention\u002Freferences\u002Fexamples.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Frepo-provenance.md",3552,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkeras-attention\u002Freferences\u002Frepo-provenance.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Frepo-routing-metadata.json",352,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkeras-attention\u002Freferences\u002Frepo-routing-metadata.json",{"path":70,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Ftroubleshooting.md",6562,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkeras-attention\u002Freferences\u002Ftroubleshooting.md",{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Fcheck_example_dependencies.py","SCRIPT","脚本",3790,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkeras-attention\u002Fscripts\u002Fcheck_example_dependencies.py",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"scripts\u002Fsmoke_attention.py",5313,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkeras-attention\u002Fscripts\u002Fsmoke_attention.py",[84,91,98,105,112,119],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"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":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"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":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"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":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"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",[],[]]