[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M791EQRBJSFC0SJWBX8V6N6V":3,"skill-same:01M791EQRBJSFC0SJWBX8V6N6V":66},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M791EQRBJSFC0SJWBX8V6N6V","htm-algorithms",null,"Direct NuPIC legacy HTM encoders, SpatialPooler, TemporalMemory, SDRClassifier, anomaly score, and anomaly likelihood workflows.","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\u002Fnupic-legacy\u002Fsub-skills\u002Fhtm-algorithms\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: htm-algorithms\ndescription: \"Direct NuPIC legacy HTM encoders, SpatialPooler, TemporalMemory,\n  SDRClassifier, anomaly score, and anomaly likelihood workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# HTM Algorithms\n\nUse this sub-skill when a task asks for direct NuPIC legacy HTM algorithm APIs: encoders, `SpatialPooler`, `TemporalMemory`, `SDRClassifier`, raw anomaly score, or anomaly likelihood for a small streaming scalar\u002Ftemporal example.\n\nNuPIC legacy is a Python 2.7 package. Direct algorithm workflows normally require installed `nupic`, `nupic.bindings`, `numpy` in the legacy-compatible range, and `pycapnp`\u002FCap'n Proto only when serialization is needed.\n\n## Route first\n\n- Stay here for: `ScalarEncoder`, `RandomDistributedScalarEncoder`, `DateEncoder`, `CategoryEncoder`, `MultiEncoder`, `SpatialPooler.compute`, `TemporalMemory.compute`, `SDRClassifier.compute`, `computeRawAnomalyScore`, and `AnomalyLikelihood.anomalyProbability`.\n- Read [references\u002Fapi-reference.md](references\u002Fapi-reference.md) when you need constructor signatures, input\u002Foutput shapes, classifier result keys, or anomaly helper semantics.\n- Read [references\u002Fworkflows.md](references\u002Fworkflows.md) when you need a direct encoders -> SP -> TM -> classifier\u002Fanomaly recipe or a debugging checklist for algorithm pipelines.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when an algorithm example fails with encoder parameter, active-array shape, TM state\u002Freset, classifier dict, Python 2, bindings, or serialization errors.\n- Run [scripts\u002Falgorithm_smoke.py](scripts\u002Falgorithm_smoke.py) when you need a deterministic installed-package smoke check for tiny encoders, SP\u002FTM, classifier, and anomaly helpers.\n- Route CSV stream headers, field metadata, OPF model parameter files, and config validation to [..\u002Fdata-and-configuration\u002F](..\u002Fdata-and-configuration\u002F).\n- Route high-level `ModelFactory`, OPF inference dictionaries, checkpoints, and experiment workflows to [..\u002Fopf-prediction\u002F](..\u002Fopf-prediction\u002F).\n- For package-wide install\u002Fimport failures before algorithm code runs, start with the root troubleshooting guide at `..\u002F..\u002Freferences\u002Ftroubleshooting.md`; local reference files also cross-link to that guide from their own relative paths.\n\n## Direct API checklist\n\n1. Confirm the runtime is Python 2.7 and can import `nupic`, `nupic.bindings`, and `numpy`.\n2. Encode every raw value into a one-dimensional binary SDR. Allocate one zero-filled NumPy array per encoder with `encoder.getWidth()` and call `encoder.encodeIntoArray(value, bits)`.\n3. Concatenate encoder outputs. Set `SpatialPooler(inputDimensions=(encodingWidth,), columnDimensions=(columnCount,), ...)` so `encodingWidth == len(concatenatedEncoding)`.\n4. Allocate `activeArray = numpy.zeros(columnCount, dtype=\"uint32\")`, call `sp.compute(encoding, learn, activeArray)`, then pass `numpy.nonzero(activeArray)[0]` to `TemporalMemory.compute`.\n5. Set `TemporalMemory(columnDimensions=(columnCount,), ...)` to the same column count used by the SP. Use `tm.getActiveCells()` for classifier `patternNZ`; use `tm.getPredictiveCells()` plus `tm.columnForCell(cell)` to build next-step predicted columns for anomaly score.\n6. For scalar predictions, call `classifier.compute(recordNum, patternNZ, {\"bucketIdx\": bucketIdx, \"actValue\": rawValue}, learn=True, infer=True)`. Look for integer step keys such as `1` plus the `\"actualValues\"` key in the result.\n7. For anomaly checks, compare current active columns with previous-step predicted columns using `computeRawAnomalyScore(activeColumns, prevPredictedColumns)`, then optionally update `AnomalyLikelihood` with the raw value, anomaly score, and timestamp.\n\n## Minimal validation command\n\nFrom this sub-skill directory in a prepared NuPIC legacy environment:\n\n```bash\npython scripts\u002Falgorithm_smoke.py --mode all --records 20 --encoder scalar\n```\n\nExpected success signal: the script prints `PASS`, encoder\u002FSP\u002FTM dimensions, a final one-step prediction summary, and bounded anomaly likelihood values. If it fails before imports, use root install\u002Fimport troubleshooting; if it fails after imports, use the local troubleshooting reference.\n\n## Evidence provenance\n\nThis sub-skill distills NuPIC legacy algorithm evidence from source\u002Fdoc paths such as `src\u002Fnupic\u002Falgorithms\u002F`, `src\u002Fnupic\u002Fencoders\u002F`, `docs\u002Fsource\u002Fquick-start\u002Falgorithms.rst`, `docs\u002Fexamples\u002Falgo\u002Fcomplete-algo-example.py`, `examples\u002Fsp\u002Fhello_sp.py`, `examples\u002Ftm\u002Fhello_tm.py`, and unit tests under `tests\u002Funit\u002Fnupic\u002Falgorithms\u002F` and `tests\u002Funit\u002Fnupic\u002Fencoders\u002F`. Runtime guidance here is self-contained; future agents should not need to open the original checkout examples to use it.\n","# HTM Algorithms\n\nUse this sub-skill when a task asks for direct NuPIC legacy HTM algorithm APIs: encoders, `SpatialPooler`, `TemporalMemory`, `SDRClassifier`, raw anomaly score, or anomaly likelihood for a small streaming scalar\u002Ftemporal example.\n\nNuPIC legacy is a Python 2.7 package. Direct algorithm workflows normally require installed `nupic`, `nupic.bindings`, `numpy` in the legacy-compatible range, and `pycapnp`\u002FCap'n Proto only when serialization is needed.\n\n## Route first\n\n- Stay here for: `ScalarEncoder`, `RandomDistributedScalarEncoder`, `DateEncoder`, `CategoryEncoder`, `MultiEncoder`, `SpatialPooler.compute`, `TemporalMemory.compute`, `SDRClassifier.compute`, `computeRawAnomalyScore`, and `AnomalyLikelihood.anomalyProbability`.\n- Read [references\u002Fapi-reference.md](references\u002Fapi-reference.md) when you need constructor signatures, input\u002Foutput shapes, classifier result keys, or anomaly helper semantics.\n- Read [references\u002Fworkflows.md](references\u002Fworkflows.md) when you need a direct encoders -> SP -> TM -> classifier\u002Fanomaly recipe or a debugging checklist for algorithm pipelines.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when an algorithm example fails with encoder parameter, active-array shape, TM state\u002Freset, classifier dict, Python 2, bindings, or serialization errors.\n- Run [scripts\u002Falgorithm_smoke.py](scripts\u002Falgorithm_smoke.py) when you need a deterministic installed-package smoke check for tiny encoders, SP\u002FTM, classifier, and anomaly helpers.\n- Route CSV stream headers, field metadata, OPF model parameter files, and config validation to [..\u002Fdata-and-configuration\u002F](..\u002Fdata-and-configuration\u002F).\n- Route high-level `ModelFactory`, OPF inference dictionaries, checkpoints, and experiment workflows to [..\u002Fopf-prediction\u002F](..\u002Fopf-prediction\u002F).\n- For package-wide install\u002Fimport failures before algorithm code runs, start with the root troubleshooting guide at `..\u002F..\u002Freferences\u002Ftroubleshooting.md`; local reference files also cross-link to that guide from their own relative paths.\n\n## Direct API checklist\n\n1. Confirm the runtime is Python 2.7 and can import `nupic`, `nupic.bindings`, and `numpy`.\n2. Encode every raw value into a one-dimensional binary SDR. Allocate one zero-filled NumPy array per encoder with `encoder.getWidth()` and call `encoder.encodeIntoArray(value, bits)`.\n3. Concatenate encoder outputs. Set `SpatialPooler(inputDimensions=(encodingWidth,), columnDimensions=(columnCount,), ...)` so `encodingWidth == len(concatenatedEncoding)`.\n4. Allocate `activeArray = numpy.zeros(columnCount, dtype=\"uint32\")`, call `sp.compute(encoding, learn, activeArray)`, then pass `numpy.nonzero(activeArray)[0]` to `TemporalMemory.compute`.\n5. Set `TemporalMemory(columnDimensions=(columnCount,), ...)` to the same column count used by the SP. Use `tm.getActiveCells()` for classifier `patternNZ`; use `tm.getPredictiveCells()` plus `tm.columnForCell(cell)` to build next-step predicted columns for anomaly score.\n6. For scalar predictions, call `classifier.compute(recordNum, patternNZ, {\"bucketIdx\": bucketIdx, \"actValue\": rawValue}, learn=True, infer=True)`. Look for integer step keys such as `1` plus the `\"actualValues\"` key in the result.\n7. For anomaly checks, compare current active columns with previous-step predicted columns using `computeRawAnomalyScore(activeColumns, prevPredictedColumns)`, then optionally update `AnomalyLikelihood` with the raw value, anomaly score, and timestamp.\n\n## Minimal validation command\n\nFrom this sub-skill directory in a prepared NuPIC legacy environment:\n\n```bash\npython scripts\u002Falgorithm_smoke.py --mode all --records 20 --encoder scalar\n```\n\nExpected success signal: the script prints `PASS`, encoder\u002FSP\u002FTM dimensions, a final one-step prediction summary, and bounded anomaly likelihood values. If it fails before imports, use root install\u002Fimport troubleshooting; if it fails after imports, use the local troubleshooting reference.\n\n## Evidence provenance\n\nThis sub-skill distills NuPIC legacy algorithm evidence from source\u002Fdoc paths such as `src\u002Fnupic\u002Falgorithms\u002F`, `src\u002Fnupic\u002Fencoders\u002F`, `docs\u002Fsource\u002Fquick-start\u002Falgorithms.rst`, `docs\u002Fexamples\u002Falgo\u002Fcomplete-algo-example.py`, `examples\u002Fsp\u002Fhello_sp.py`, `examples\u002Ftm\u002Fhello_tm.py`, and unit tests under `tests\u002Funit\u002Fnupic\u002Falgorithms\u002F` and `tests\u002Funit\u002Fnupic\u002Fencoders\u002F`. Runtime guidance here is self-contained; future agents should not need to open the original checkout examples to use it.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fnupic-legacy\u002Fsub-skills\u002Fhtm-algorithms",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill htm-algorithms",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill htm-algorithms",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill htm-algorithms","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnupic-legacy\u002Fsub-skills\u002Fhtm-algorithms\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",10108,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnupic-legacy\u002Fsub-skills\u002Fhtm-algorithms\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",11108,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnupic-legacy\u002Fsub-skills\u002Fhtm-algorithms\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",9479,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnupic-legacy\u002Fsub-skills\u002Fhtm-algorithms\u002Freferences\u002Fworkflows.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Falgorithm_smoke.py","SCRIPT","脚本",13303,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnupic-legacy\u002Fsub-skills\u002Fhtm-algorithms\u002Fscripts\u002Falgorithm_smoke.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]