[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M791EGWX5MEBJSMPT5EHBZ7Z":3,"skill-same:01M791EGWX5MEBJSMPT5EHBZ7Z":70},{"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},"01M791EGWX5MEBJSMPT5EHBZ7Z","nupic-legacy",null,"Use NuPIC legacy HTM algorithms, OPF prediction, Network API pipelines, swarming search definitions, and data\u002Fconfig validation in Python 2.7-era runtimes.","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\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: nupic-legacy\ndescription: \"Use NuPIC legacy HTM algorithms, OPF prediction, Network API\n  pipelines, swarming search definitions, and data\u002Fconfig validation in Python\n  2.7-era runtimes.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# NuPIC Legacy\n\nUse this repo skill when a task involves NuPIC legacy, Hierarchical Temporal Memory (HTM), streaming anomaly\u002Fprediction workflows, `SpatialPooler`, `TemporalMemory`, `SDRClassifier`, OPF `ModelFactory`, Network API regions, `run_swarm`, or NuPIC three-header-row CSV\u002Fmodel-parameter files.\n\nNuPIC legacy is maintenance-mode, Python 2.7-era software. Start by checking the runtime before debugging workflow code.\n\n## Start here\n\n1. Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) when checking whether this skill matches a checkout or deciding whether to refresh it.\n2. Read [references\u002Finstallation-and-runtime.md](references\u002Finstallation-and-runtime.md) before installing or preparing a NuPIC legacy environment.\n3. Run [scripts\u002Fcheck_nupic_legacy_env.py](scripts\u002Fcheck_nupic_legacy_env.py) inside the candidate Python environment to verify imports and tiny API construction.\n4. Use [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when failures mention Python version, `nupic`, `nupic.bindings`, `numpy`, `capnp`\u002F`pycapnp`, dependency conflicts, or broad runtime setup.\n\nMinimal package smoke command from this skill root:\n\n```bash\npython scripts\u002Fcheck_nupic_legacy_env.py\n```\n\nExpected runtime for execution tasks: Python 2.7, installed `nupic`, compiled `nupic.bindings`, legacy-compatible NumPy, and `pycapnp`\u002FCap'n Proto where serialization is involved. Do not treat Python 3 import or syntax failures as surprising unless the user is explicitly porting NuPIC.\n\n## Route by task\n\n| User task or signal | Go to | Why |\n|---|---|---|\n| Direct encoders, `SpatialPooler`, `TemporalMemory`, `SDRClassifier`, anomaly score, anomaly likelihood, active columns\u002Fcells | [sub-skills\u002Fhtm-algorithms\u002F](sub-skills\u002Fhtm-algorithms\u002F) | Covers direct HTM algorithm APIs, signatures, array shapes, and tiny smoke checks. |\n| CSV stream headers, `FileRecordStream`, field metadata, model parameter YAML\u002FJSON, aggregation, configuration overrides | [sub-skills\u002Fdata-and-configuration\u002F](sub-skills\u002Fdata-and-configuration\u002F) | Validates and explains input\u002Fconfig artifacts shared by OPF, Network, and swarming. |\n| OPF `ModelFactory`, `HTMPredictionModel`, `model.run`, `result.inferences`, experiment directories, checkpoints | [sub-skills\u002Fopf-prediction\u002F](sub-skills\u002Fopf-prediction\u002F) | Covers high-level prediction workflows, inference keys, experiment runner guidance, and checkpoint use. |\n| `Network`, `RecordSensor`, `SPRegion`, `TMRegion`, classifier regions, region links, custom PyRegion | [sub-skills\u002Fnetwork-api\u002F](sub-skills\u002Fnetwork-api\u002F) | Covers Network API construction, linking, region specs, output extraction, and custom-region skeletons. |\n| `run_swarm`, `permutations_runner`, `search_def.json`, generated `model_0`, MySQL\u002FClientJobs errors | [sub-skills\u002Fswarming\u002F](sub-skills\u002Fswarming\u002F) | Covers safe search-definition linting, CLI\u002Faction options, service requirements, and using generated OPF models. |\n\n## Common workflows\n\n### Direct HTM algorithm pipeline\n\nUse `htm-algorithms` when the user wants to encode values, run SP\u002FTM, classify active cells, or compute anomaly likelihood without OPF. The bundled smoke is:\n\n```bash\npython sub-skills\u002Fhtm-algorithms\u002Fscripts\u002Falgorithm_smoke.py --mode all --records 20\n```\n\n### OPF prediction over a CSV stream\n\nUse `data-and-configuration` first to validate the NuPIC CSV and model parameters, then `opf-prediction` to create the model and extract `multiStepBestPredictions` \u002F `multiStepPredictions`. Useful checks:\n\n```bash\npython sub-skills\u002Fdata-and-configuration\u002Fscripts\u002Fvalidate_nupic_csv.py data.csv --predicted-field consumption\npython sub-skills\u002Fopf-prediction\u002Fscripts\u002Fopf_prediction_smoke.py\n```\n\n### Network API graph\n\nUse `network-api` when the user asks for explicit regions and links rather than OPF. Start with:\n\n```bash\npython sub-skills\u002Fnetwork-api\u002Fscripts\u002Fnetwork_smoke.py --inspect-region-types\n```\n\n### Swarming\u002Fsearch-definition workflow\n\nUse `swarming` for `search_def.json` authoring and hypersearch run planning. Lint before running anything service-backed:\n\n```bash\npython sub-skills\u002Fswarming\u002Fscripts\u002Fswarm_config_lint.py search_def.json --summary\n```\n\nFull swarming can require MySQL-compatible service configuration and may be expensive; never use it as a first install smoke.\n\n## Boundaries\n\n- This skill teaches using NuPIC legacy as a package. For source-code edits, release engineering, or Python 3 porting, treat the task as repository maintenance and do not use package workflow assumptions blindly.\n- This skill does not cover modern deep-learning time-series forecasting unless the task explicitly uses NuPIC\u002FHTM APIs.\n- Do not install developer requirements, visualization extras, Docker\u002FVagrant tooling, profiling scripts, or full benchmark suites unless the user asks for those surfaces.\n- Runtime instructions here are self-contained; bundled references\u002Fscripts replace the relevant example logic instead of requiring future agents to read or run original checkout files.\n","# NuPIC Legacy\n\nUse this repo skill when a task involves NuPIC legacy, Hierarchical Temporal Memory (HTM), streaming anomaly\u002Fprediction workflows, `SpatialPooler`, `TemporalMemory`, `SDRClassifier`, OPF `ModelFactory`, Network API regions, `run_swarm`, or NuPIC three-header-row CSV\u002Fmodel-parameter files.\n\nNuPIC legacy is maintenance-mode, Python 2.7-era software. Start by checking the runtime before debugging workflow code.\n\n## Start here\n\n1. Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) when checking whether this skill matches a checkout or deciding whether to refresh it.\n2. Read [references\u002Finstallation-and-runtime.md](references\u002Finstallation-and-runtime.md) before installing or preparing a NuPIC legacy environment.\n3. Run [scripts\u002Fcheck_nupic_legacy_env.py](scripts\u002Fcheck_nupic_legacy_env.py) inside the candidate Python environment to verify imports and tiny API construction.\n4. Use [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when failures mention Python version, `nupic`, `nupic.bindings`, `numpy`, `capnp`\u002F`pycapnp`, dependency conflicts, or broad runtime setup.\n\nMinimal package smoke command from this skill root:\n\n```bash\npython scripts\u002Fcheck_nupic_legacy_env.py\n```\n\nExpected runtime for execution tasks: Python 2.7, installed `nupic`, compiled `nupic.bindings`, legacy-compatible NumPy, and `pycapnp`\u002FCap'n Proto where serialization is involved. Do not treat Python 3 import or syntax failures as surprising unless the user is explicitly porting NuPIC.\n\n## Route by task\n\n| User task or signal | Go to | Why |\n|---|---|---|\n| Direct encoders, `SpatialPooler`, `TemporalMemory`, `SDRClassifier`, anomaly score, anomaly likelihood, active columns\u002Fcells | [sub-skills\u002Fhtm-algorithms\u002F](sub-skills\u002Fhtm-algorithms\u002F) | Covers direct HTM algorithm APIs, signatures, array shapes, and tiny smoke checks. |\n| CSV stream headers, `FileRecordStream`, field metadata, model parameter YAML\u002FJSON, aggregation, configuration overrides | [sub-skills\u002Fdata-and-configuration\u002F](sub-skills\u002Fdata-and-configuration\u002F) | Validates and explains input\u002Fconfig artifacts shared by OPF, Network, and swarming. |\n| OPF `ModelFactory`, `HTMPredictionModel`, `model.run`, `result.inferences`, experiment directories, checkpoints | [sub-skills\u002Fopf-prediction\u002F](sub-skills\u002Fopf-prediction\u002F) | Covers high-level prediction workflows, inference keys, experiment runner guidance, and checkpoint use. |\n| `Network`, `RecordSensor`, `SPRegion`, `TMRegion`, classifier regions, region links, custom PyRegion | [sub-skills\u002Fnetwork-api\u002F](sub-skills\u002Fnetwork-api\u002F) | Covers Network API construction, linking, region specs, output extraction, and custom-region skeletons. |\n| `run_swarm`, `permutations_runner`, `search_def.json`, generated `model_0`, MySQL\u002FClientJobs errors | [sub-skills\u002Fswarming\u002F](sub-skills\u002Fswarming\u002F) | Covers safe search-definition linting, CLI\u002Faction options, service requirements, and using generated OPF models. |\n\n## Common workflows\n\n### Direct HTM algorithm pipeline\n\nUse `htm-algorithms` when the user wants to encode values, run SP\u002FTM, classify active cells, or compute anomaly likelihood without OPF. The bundled smoke is:\n\n```bash\npython sub-skills\u002Fhtm-algorithms\u002Fscripts\u002Falgorithm_smoke.py --mode all --records 20\n```\n\n### OPF prediction over a CSV stream\n\nUse `data-and-configuration` first to validate the NuPIC CSV and model parameters, then `opf-prediction` to create the model and extract `multiStepBestPredictions` \u002F `multiStepPredictions`. Useful checks:\n\n```bash\npython sub-skills\u002Fdata-and-configuration\u002Fscripts\u002Fvalidate_nupic_csv.py data.csv --predicted-field consumption\npython sub-skills\u002Fopf-prediction\u002Fscripts\u002Fopf_prediction_smoke.py\n```\n\n### Network API graph\n\nUse `network-api` when the user asks for explicit regions and links rather than OPF. Start with:\n\n```bash\npython sub-skills\u002Fnetwork-api\u002Fscripts\u002Fnetwork_smoke.py --inspect-region-types\n```\n\n### Swarming\u002Fsearch-definition workflow\n\nUse `swarming` for `search_def.json` authoring and hypersearch run planning. Lint before running anything service-backed:\n\n```bash\npython sub-skills\u002Fswarming\u002Fscripts\u002Fswarm_config_lint.py search_def.json --summary\n```\n\nFull swarming can require MySQL-compatible service configuration and may be expensive; never use it as a first install smoke.\n\n## Boundaries\n\n- This skill teaches using NuPIC legacy as a package. For source-code edits, release engineering, or Python 3 porting, treat the task as repository maintenance and do not use package workflow assumptions blindly.\n- This skill does not cover modern deep-learning time-series forecasting unless the task explicitly uses NuPIC\u002FHTM APIs.\n- Do not install developer requirements, visualization extras, Docker\u002FVagrant tooling, profiling scripts, or full benchmark suites unless the user asks for those surfaces.\n- Runtime instructions here are self-contained; bundled references\u002Fscripts replace the relevant example logic instead of requiring future agents to read or run original checkout files.\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",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 nupic-legacy",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill nupic-legacy",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill nupic-legacy","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnupic-legacy\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Finstallation-and-runtime.md","REFERENCE","参考文档",4521,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnupic-legacy\u002Freferences\u002Finstallation-and-runtime.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",2804,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnupic-legacy\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",496,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnupic-legacy\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",3989,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnupic-legacy\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_nupic_legacy_env.py","SCRIPT","脚本",5417,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnupic-legacy\u002Fscripts\u002Fcheck_nupic_legacy_env.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]