[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7974C0VB56WRNCQRZQSNFRE":3,"skill-same:01M7974C0VB56WRNCQRZQSNFRE":74},{"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},"01M7974C0VB56WRNCQRZQSNFRE","viseron",null,"Guides Viseron self-hosted NVR deployment, camera recording, computer-vision detection, integrations, and backend extension 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\u002Fviseron\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: viseron\ndescription: \"Guides Viseron self-hosted NVR deployment, camera recording,\n  computer-vision detection, integrations, and backend extension workflows.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# Viseron Repo Skill\n\nUse this skill when a task involves Viseron, the self-hosted local NVR and AI computer-vision application, especially when the user needs to configure cameras, recording, storage, object\u002Fmotion\u002Fface\u002Flicense-plate detection, notifications, automations, or backend components.\n\n## First checks\n\n- Viseron is normally operated as a containerized service with a YAML `config.yaml` and optional `secrets.yaml` mounted into the runtime config directory.\n- The Python distribution is named `viseron` and the primary import package is `viseron`; source checkouts also rely on a top-level `manager.py` helper for some subprocess modules.\n- Treat live cameras, Docker images, PostgreSQL, MQTT brokers, notification credentials, detector services, GPU\u002FEdgeTPU\u002FHailo devices, and model downloads as target-host requirements unless the user explicitly asks to verify them.\n- Run bundled scripts from this skill only against user-provided config snippets or an already prepared Viseron runtime\u002Fdevelopment environment; they are preflight helpers and do not replace Viseron startup validation.\n\n## Route by task\n\n- **Install, deploy, or validate global configuration**: load [configuration-and-deployment](sub-skills\u002Fconfiguration-and-deployment\u002FSKILL.md) for Docker\u002Fcontainer setup, `config.yaml`, `secrets.yaml`, webserver\u002Fauth\u002FAPI, logging, safe mode, and startup validation.\n- **Configure camera streams, NVR, recording, storage tiers, snapshots, timelapse, or live view**: load [camera-recording-pipeline](sub-skills\u002Fcamera-recording-pipeline\u002FSKILL.md) for FFmpeg\u002FGStreamer\u002Fgo2rtc, stream URLs, FFprobe metadata, recorder\u002FNVR behavior, retention, and storage troubleshooting.\n- **Choose or debug motion\u002Fobject\u002Fpost-processing AI components**: load [detection-and-ai-components](sub-skills\u002Fdetection-and-ai-components\u002FSKILL.md) for MOG2\u002Fbackground subtraction, MQTT external motion, YOLO, Darknet, EdgeTPU, Hailo, CodeProject.AI, DeepStack, dlib, CompreFace, labels, masks, zones, filters, and training\u002Fpost-processing touchpoints.\n- **Automate events or control integrations**: load [automation-and-integrations](sub-skills\u002Fautomation-and-integrations\u002FSKILL.md) for MQTT\u002FHome Assistant, webhooks, Discord\u002FGotify\u002FTelegram notifications, Telegram commands, ONVIF PTZ, data-stream events, and Jinja templates.\n- **Modify or extend Viseron source code**: load [developer-extension](sub-skills\u002Fdeveloper-extension\u002FSKILL.md) for component\u002Fdomain lifecycle, config schemas, reload behavior, entities, docs generation, tests, and source-root import caveats.\n\n## Root references and scripts\n\n- Read [component capability index](references\u002Fcomponent-capability-index.md) when deciding which component\u002Fdomain owns a user request before loading a sub-skill.\n- Read [cross-cutting troubleshooting](references\u002Ftroubleshooting.md) for install\u002Fimport, optional dependency, Docker, config, service, and source-root failures that span multiple sub-skills.\n- Read [repo provenance](references\u002Frepo-provenance.md) when checking whether this skill is stale relative to a newer Viseron checkout.\n- Run [scripts\u002Fcheck_viseron_imports.py](scripts\u002Fcheck_viseron_imports.py) in a Viseron Python environment to probe core imports and optional dependency availability without contacting cameras or services.\n- Run [scripts\u002Fextract_config_schema_summary.py](scripts\u002Fextract_config_schema_summary.py) in a Viseron source\u002Fruntime environment to list available component schemas and setup hooks.\n\n## Common workflow skeletons\n\n### Review a user configuration\n\n1. Load `configuration-and-deployment` and validate YAML\u002Fsecrets syntax first.\n2. Route each top-level component to the owning sub-skill using the component capability index.\n3. Check cross-component dependencies: cameras must load before NVR, object\u002Fmotion detectors are optional or required depending on the component, and post-processors need object-detector labels that can trigger them.\n4. For every external service, credential, device, model, or camera URL, separate static config review from target-host runtime verification.\n\n### Diagnose missing recordings or detections\n\n1. Load `camera-recording-pipeline` to check camera connectivity, stream metadata, recorder\u002FNVR settings, storage tiers, and live-frame availability.\n2. Load `detection-and-ai-components` to check whether motion\u002Fobject labels, zones, masks, `scan_on_motion_only`, `trigger_event_recording`, `store`, and post-processor labels can produce the expected event.\n3. Load `automation-and-integrations` only if the event exists in Viseron but an MQTT\u002Fwebhook\u002Fnotification\u002FTelegram side effect is missing.\n\n### Add or modify a backend component\n\n1. Load `developer-extension` before editing code.\n2. Keep `setup_domains()` hot-reload safe: register domain instances only, and avoid expensive shared initialization there.\n3. Put component-level resources in `setup()`, declare `CONFIG_SCHEMA`, and model domain dependencies with `RequireDomain` or `OptionalDomain`.\n4. After code changes, select focused native tests from the relevant sub-skill's candidate list rather than running hardware, container, or external-service checks by default.\n\n## Who owns what\n\n| User request signal | Owning route | Why |\n|---|---|---|\n| `config.yaml`, `secrets.yaml`, startup error, safe mode, web UI, API token, auth, or logging | `configuration-and-deployment` | These are global deployment concerns and should be checked before any camera or detector tuning. |\n| RTSP\u002FMJPEG URL, FFmpeg command, FFprobe timeout, recorder, NVR, live view, snapshots, timelapse, storage tier | `camera-recording-pipeline` | These concerns are tied to frame acquisition, recordings, and retained media. |\n| Motion detected but no recording, label mismatch, zone\u002Fmask issue, model\u002Fdevice choice, EdgeTPU\u002FHailo\u002FYOLO\u002FDarknet, face or plate recognition | `detection-and-ai-components` | These are AI pipeline and post-processing choices. |\n| MQTT entity\u002Ftopic, webhook, Telegram, Discord, Gotify, PTZ, event topic, Jinja template | `automation-and-integrations` | These are side effects or control surfaces layered on top of Viseron events. |\n| Setup hook, config schema, reload diff, domain dependency, entity class, docs generation, tests, or import caveat in source code | `developer-extension` | These are repo-maintenance and backend-extension tasks. |\n\n## How to use the bundled scripts\n\n- `scripts\u002Fcheck_viseron_imports.py` prints a compact import\u002Fprobe report for core modules and selected optional groups. Use it when you need to know whether a Viseron environment is ready for source inspection or which optional backend is missing.\n- `scripts\u002Fextract_config_schema_summary.py` summarizes which components expose `CONFIG_SCHEMA`, `setup()`, and `setup_domains()`. Use it when choosing which component-owned sub-skill should own a new configuration branch.\n- The sub-skill scripts are intentionally narrow and safe. They should fail fast on malformed local input instead of starting Viseron or contacting live hardware\u002Fservices.\n\n## Verification boundaries\n\nThis skill was constructed from source, docs, tests, generated component explorer config, and CPU-safe installed-package inspection. It does **not** claim that this construction host verified live cameras, Docker images, PostgreSQL services, MQTT brokers, notification endpoints, YOLO\u002FDarknet inference, EdgeTPU, Hailo, GStreamer\u002FPyGObject, or CUDA\u002FVA-API\u002FJetson\u002FRaspberry Pi acceleration. Those remain explicit target-host checks.\n","# Viseron Repo Skill\n\nUse this skill when a task involves Viseron, the self-hosted local NVR and AI computer-vision application, especially when the user needs to configure cameras, recording, storage, object\u002Fmotion\u002Fface\u002Flicense-plate detection, notifications, automations, or backend components.\n\n## First checks\n\n- Viseron is normally operated as a containerized service with a YAML `config.yaml` and optional `secrets.yaml` mounted into the runtime config directory.\n- The Python distribution is named `viseron` and the primary import package is `viseron`; source checkouts also rely on a top-level `manager.py` helper for some subprocess modules.\n- Treat live cameras, Docker images, PostgreSQL, MQTT brokers, notification credentials, detector services, GPU\u002FEdgeTPU\u002FHailo devices, and model downloads as target-host requirements unless the user explicitly asks to verify them.\n- Run bundled scripts from this skill only against user-provided config snippets or an already prepared Viseron runtime\u002Fdevelopment environment; they are preflight helpers and do not replace Viseron startup validation.\n\n## Route by task\n\n- **Install, deploy, or validate global configuration**: load [configuration-and-deployment](sub-skills\u002Fconfiguration-and-deployment\u002FSKILL.md) for Docker\u002Fcontainer setup, `config.yaml`, `secrets.yaml`, webserver\u002Fauth\u002FAPI, logging, safe mode, and startup validation.\n- **Configure camera streams, NVR, recording, storage tiers, snapshots, timelapse, or live view**: load [camera-recording-pipeline](sub-skills\u002Fcamera-recording-pipeline\u002FSKILL.md) for FFmpeg\u002FGStreamer\u002Fgo2rtc, stream URLs, FFprobe metadata, recorder\u002FNVR behavior, retention, and storage troubleshooting.\n- **Choose or debug motion\u002Fobject\u002Fpost-processing AI components**: load [detection-and-ai-components](sub-skills\u002Fdetection-and-ai-components\u002FSKILL.md) for MOG2\u002Fbackground subtraction, MQTT external motion, YOLO, Darknet, EdgeTPU, Hailo, CodeProject.AI, DeepStack, dlib, CompreFace, labels, masks, zones, filters, and training\u002Fpost-processing touchpoints.\n- **Automate events or control integrations**: load [automation-and-integrations](sub-skills\u002Fautomation-and-integrations\u002FSKILL.md) for MQTT\u002FHome Assistant, webhooks, Discord\u002FGotify\u002FTelegram notifications, Telegram commands, ONVIF PTZ, data-stream events, and Jinja templates.\n- **Modify or extend Viseron source code**: load [developer-extension](sub-skills\u002Fdeveloper-extension\u002FSKILL.md) for component\u002Fdomain lifecycle, config schemas, reload behavior, entities, docs generation, tests, and source-root import caveats.\n\n## Root references and scripts\n\n- Read [component capability index](references\u002Fcomponent-capability-index.md) when deciding which component\u002Fdomain owns a user request before loading a sub-skill.\n- Read [cross-cutting troubleshooting](references\u002Ftroubleshooting.md) for install\u002Fimport, optional dependency, Docker, config, service, and source-root failures that span multiple sub-skills.\n- Read [repo provenance](references\u002Frepo-provenance.md) when checking whether this skill is stale relative to a newer Viseron checkout.\n- Run [scripts\u002Fcheck_viseron_imports.py](scripts\u002Fcheck_viseron_imports.py) in a Viseron Python environment to probe core imports and optional dependency availability without contacting cameras or services.\n- Run [scripts\u002Fextract_config_schema_summary.py](scripts\u002Fextract_config_schema_summary.py) in a Viseron source\u002Fruntime environment to list available component schemas and setup hooks.\n\n## Common workflow skeletons\n\n### Review a user configuration\n\n1. Load `configuration-and-deployment` and validate YAML\u002Fsecrets syntax first.\n2. Route each top-level component to the owning sub-skill using the component capability index.\n3. Check cross-component dependencies: cameras must load before NVR, object\u002Fmotion detectors are optional or required depending on the component, and post-processors need object-detector labels that can trigger them.\n4. For every external service, credential, device, model, or camera URL, separate static config review from target-host runtime verification.\n\n### Diagnose missing recordings or detections\n\n1. Load `camera-recording-pipeline` to check camera connectivity, stream metadata, recorder\u002FNVR settings, storage tiers, and live-frame availability.\n2. Load `detection-and-ai-components` to check whether motion\u002Fobject labels, zones, masks, `scan_on_motion_only`, `trigger_event_recording`, `store`, and post-processor labels can produce the expected event.\n3. Load `automation-and-integrations` only if the event exists in Viseron but an MQTT\u002Fwebhook\u002Fnotification\u002FTelegram side effect is missing.\n\n### Add or modify a backend component\n\n1. Load `developer-extension` before editing code.\n2. Keep `setup_domains()` hot-reload safe: register domain instances only, and avoid expensive shared initialization there.\n3. Put component-level resources in `setup()`, declare `CONFIG_SCHEMA`, and model domain dependencies with `RequireDomain` or `OptionalDomain`.\n4. After code changes, select focused native tests from the relevant sub-skill's candidate list rather than running hardware, container, or external-service checks by default.\n\n## Who owns what\n\n| User request signal | Owning route | Why |\n|---|---|---|\n| `config.yaml`, `secrets.yaml`, startup error, safe mode, web UI, API token, auth, or logging | `configuration-and-deployment` | These are global deployment concerns and should be checked before any camera or detector tuning. |\n| RTSP\u002FMJPEG URL, FFmpeg command, FFprobe timeout, recorder, NVR, live view, snapshots, timelapse, storage tier | `camera-recording-pipeline` | These concerns are tied to frame acquisition, recordings, and retained media. |\n| Motion detected but no recording, label mismatch, zone\u002Fmask issue, model\u002Fdevice choice, EdgeTPU\u002FHailo\u002FYOLO\u002FDarknet, face or plate recognition | `detection-and-ai-components` | These are AI pipeline and post-processing choices. |\n| MQTT entity\u002Ftopic, webhook, Telegram, Discord, Gotify, PTZ, event topic, Jinja template | `automation-and-integrations` | These are side effects or control surfaces layered on top of Viseron events. |\n| Setup hook, config schema, reload diff, domain dependency, entity class, docs generation, tests, or import caveat in source code | `developer-extension` | These are repo-maintenance and backend-extension tasks. |\n\n## How to use the bundled scripts\n\n- `scripts\u002Fcheck_viseron_imports.py` prints a compact import\u002Fprobe report for core modules and selected optional groups. Use it when you need to know whether a Viseron environment is ready for source inspection or which optional backend is missing.\n- `scripts\u002Fextract_config_schema_summary.py` summarizes which components expose `CONFIG_SCHEMA`, `setup()`, and `setup_domains()`. Use it when choosing which component-owned sub-skill should own a new configuration branch.\n- The sub-skill scripts are intentionally narrow and safe. They should fail fast on malformed local input instead of starting Viseron or contacting live hardware\u002Fservices.\n\n## Verification boundaries\n\nThis skill was constructed from source, docs, tests, generated component explorer config, and CPU-safe installed-package inspection. It does **not** claim that this construction host verified live cameras, Docker images, PostgreSQL services, MQTT brokers, notification endpoints, YOLO\u002FDarknet inference, EdgeTPU, Hailo, GStreamer\u002FPyGObject, or CUDA\u002FVA-API\u002FJetson\u002FRaspberry Pi acceleration. Those remain explicit target-host checks.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fviseron",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 viseron",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill viseron",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill viseron","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fviseron\u002FSKILL.md",[46,52,56,60,64,70],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fcomponent-capability-index.md","REFERENCE","参考文档",5722,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fviseron\u002Freferences\u002Fcomponent-capability-index.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",2554,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fviseron\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",326,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fviseron\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",5660,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fviseron\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_viseron_imports.py","SCRIPT","脚本",4681,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fviseron\u002Fscripts\u002Fcheck_viseron_imports.py",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fextract_config_schema_summary.py",3417,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fviseron\u002Fscripts\u002Fextract_config_schema_summary.py",[75,83,90,97,104,111],{"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":79,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]