[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F1FEA0E5DXGBV3Y0BJ1FST":3,"skill-same:01M7F1FEA0E5DXGBV3Y0BJ1FST":66},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7F1FEA0E5DXGBV3Y0BJ1FST","meta-wearables-device-capabilities",null,"Design, implement, or review what a native DAT app does with Meta smart glasses hardware — camera streams and photo capture, HFP microphone and A2DP audio routes, native DAT Display views and ButtonGroup input, D-pad\u002FEMG\u002Ftemple input and IMU\u002Fmotion\u002Flocation sensors, and the Bluetooth\u002FWi-Fi transport, backpressure, thermal, disconnect, and recovery behavior underneath them. Use when a request involves glasses camera, microphone, audio route, native Display UI, wearer input or sensors, dropped frames, link instability, latency, or reliability claims.","shotcowboystyle\u002Fag-skills","shotcowboystyle","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F62471?v=4","01M7EZTCFCZJ6K3MYW8BPM4X6R","Curtis Blanton","01M7EZTCG1S5M04J90A931X9BX",0,"MIT","https:\u002F\u002Fgithub.com\u002Fshotcowboystyle\u002Fag-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fmeta-wearables-ops\u002Fskills\u002Fmeta-wearables-device-capabilities\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: meta-wearables-device-capabilities\ndescription: Design, implement, or review what a native DAT app does with Meta smart glasses hardware — camera streams and photo capture, HFP microphone and A2DP audio routes, native DAT Display views and ButtonGroup input, D-pad\u002FEMG\u002Ftemple input and IMU\u002Fmotion\u002Flocation sensors, and the Bluetooth\u002FWi-Fi transport, backpressure, thermal, disconnect, and recovery behavior underneath them. Use when a request involves glasses camera, microphone, audio route, native Display UI, wearer input or sensors, dropped frames, link instability, latency, or reliability claims.\nallowed-tools: Read, Grep, Glob\nlast_verified: 2026-08-22\n---\n\n# Meta Wearables device capabilities\n\n## Overview\n\nOwn each hardware capability as its own contract — source, owner, permission, bounded queue, stop order, phone fallback, evidence — on top of a started DAT session. Keep this chain explicit:\n\n`runtime capability gate -> permission\u002Fconsent -> owned capability -> bounded consumer -> teardown -> phone fallback`\n\nRay-Ban Display **Web App** HTML surfaces are not native Display; they belong to [Web Apps](..\u002Fmeta-wearables-web-apps\u002FSKILL.md). Package setup, registration, and sessions belong to [DAT integration](..\u002Fmeta-wearables-dat-integration\u002FSKILL.md).\n\nApply the [shared rules](..\u002Fmeta-wearables-knowledge-base\u002Freferences\u002Fshared-rules.md) — evidence ladder, device labels, secrets, claims.\n\n## Lanes\n\n| Lane | Detail | Knowledge base |\n| --- | --- | --- |\n| Camera and photo | [camera-audio.md](references\u002Fcamera-audio.md) | [session, camera, audio](..\u002Fmeta-wearables-knowledge-base\u002Freferences\u002F70-meta-wearables\u002F03-device-session-camera-and-audio.md) |\n| Audio (HFP in, A2DP out) | [camera-audio.md](references\u002Fcamera-audio.md) | [transport and audio](..\u002Fmeta-wearables-knowledge-base\u002Freferences\u002F70-meta-wearables\u002F22-transport-audio-and-runtime-reliability.md) |\n| Native Display | [display.md](references\u002Fdisplay.md) | [Display access](..\u002Fmeta-wearables-knowledge-base\u002Freferences\u002F70-meta-wearables\u002F04-display-access-and-glasses-ui.md) |\n| Input and sensors | [input-sensor-contract.md](references\u002Finput-sensor-contract.md) | [input and sensors](..\u002Fmeta-wearables-knowledge-base\u002Freferences\u002F70-meta-wearables\u002F24-input-sensors-and-physical-interaction.md) |\n| Transport and reliability | [transport-contract.md](references\u002Ftransport-contract.md) | [transport and audio](..\u002Fmeta-wearables-knowledge-base\u002Freferences\u002F70-meta-wearables\u002F22-transport-audio-and-runtime-reliability.md) |\n\n## Read before acting\n\n- Inspect the actual DAT version, platform audio setup (`AVAudioSession` or Android audio route), Bluetooth\u002Flocal-network keys, existing media pipeline, persistence, upload, and background behavior.\n- Read [on-device compliance](..\u002Fmeta-wearables-knowledge-base\u002Freferences\u002F70-meta-wearables\u002F17-on-device-compliance-and-runtime-contract.md) for processing location, raw-media boundaries, retention, and thermal fallback, and [application architecture](..\u002Fmeta-wearables-knowledge-base\u002Freferences\u002F70-meta-wearables\u002F19-application-architecture-and-platform-boundaries.md) for ownership, session epochs, and phone fallback seams.\n- Read [device-generation runtime support](..\u002Fmeta-wearables-knowledge-base\u002Freferences\u002F70-meta-wearables\u002F16-device-generation-and-runtime-support-matrix.md) before using Gen 2, Display, or Gen 3 language.\n- Start from a [camera](..\u002Fmeta-wearables-implementation-recipes\u002Fassets\u002Fmeta-wearables-ios-camera-starter\u002FMetaWearablesCameraStarter.swift) or [Display](..\u002Fmeta-wearables-implementation-recipes\u002Fassets\u002Fmeta-wearables-ios-display-starter\u002FMetaWearablesDisplayStarter.swift) seed in [implementation recipes](..\u002Fmeta-wearables-implementation-recipes\u002FSKILL.md); Android equivalents sit beside them.\n\n## Workflow\n\n1. Freeze the tuple: platform, DAT tag or artifact, Meta AI app, runtime device identity, firmware\u002FDAT-app, mode\u002Fchannel, requested capability.\n2. Gate on the runtime capability response (for example `supportsDisplay()`), registration, session readiness, and permission. Never gate on a product name.\n3. Name the source of every signal: glasses camera vs phone camera; HFP glasses mic vs phone mic vs A2DP playback vs remote transcription; native Display tap vs Web App focus event vs phone sensor.\n4. Classify each transport hop — Bluetooth control, Wi-Fi\u002Flocal network, HFP, A2DP, Internet — from the observed route. Keep processing location (glasses-native, phone-local, remote, mixed) separate from transport.\n5. Define ownership and bounded queues: drop, coalesce, or block policy; timestamps; session epoch; stop order (stop capability, cancel consumers, then stop the session).\n6. Model failure states — denied, unsupported, doff\u002Ffold, `hingesClosed`, timeout, disconnect, thermal, peak power — with a visible fallback and one bounded recovery. Never auto-retry a thermal or power shutdown.\n7. For Display, project a small sanitized phone-owned snapshot, model focus\u002Fdismiss\u002Ftimeout, and clear the view on every terminal path.\n8. For input and sensors, normalize events with source, action, epoch, and bounded payload; reject stale epochs, debounce duplicates, and stop listeners on exit or denial.\n9. Test with MockDevice and fixtures first (denied, stale, slow consumer, stop-while-streaming, reconnect), then record connected and physical runs separately.\n\n## Fast path\n\nTake one capability slice: gate → one owned stream, view, or listener → one event → teardown → phone fallback. Measure queue, latency, and thermal budgets at the adapter boundary. A working camera stream must not become a prerequisite for unrelated audio, Display, or input work.\n\n## Hard boundaries\n\n- Never call a phone microphone, A2DP playback, or phone camera a glasses capture.\n- Never send raw media or raw IMU\u002FEMG\u002Flocation traces off-device without documented consent, retention, and deletion; sensor availability is not consent.\n- Never claim native DAT IMU, EMG, Neural Band, or temple-gesture APIs from a conceptual reference label; keep them `to-verify` until the selected artifact exposes them.\n- Never infer Android Wi-Fi transport from iOS configuration or an `INTERNET` permission.\n- Never treat a Bluetooth link, registration, or `supportsDisplay()` as proof of camera, HFP, Wi-Fi, Display legibility, or input timing.\n- Never hide permission, link, timeout, thermal, or power failure behind a spinner or unbounded retry.\n\n## Required output\n\n1. Capability, permission, and runtime-gate matrix per lane, with unresolved rows marked `to-verify`.\n2. Source labeling for every signal (glasses vs phone vs remote) and the transport\u002Fprocessing-location diagram.\n3. Ownership, bounded-queue, epoch, and stop-order contract for each stream, view, or listener.\n4. Display state machine and phone handoff when Display is in scope.\n5. Failure\u002Frecovery table with the first failing state and typed fallback.\n6. Privacy and retention table for raw media and sensor data.\n7. Evidence plan using the `TRN-*` and `INP-*` rows plus mock, connected, and physical camera\u002Faudio\u002FDisplay scripts.\n\n## Related skills\n\nHardware proof: [device proof](..\u002Fmeta-wearables-device-proof\u002FSKILL.md). Link, firmware, and readiness failures: [diagnostics](..\u002Fmeta-wearables-diagnostics\u002FSKILL.md). On-device and privacy claims: [trust and release](..\u002Fmeta-wearables-trust-and-release\u002FSKILL.md). Cross-surface architecture: [route planner](..\u002Fmeta-wearables-route-planner\u002FSKILL.md).\n","# Meta Wearables device capabilities\n\n## Overview\n\nOwn each hardware capability as its own contract — source, owner, permission, bounded queue, stop order, phone fallback, evidence — on top of a started DAT session. Keep this chain explicit:\n\n`runtime capability gate -> permission\u002Fconsent -> owned capability -> bounded consumer -> teardown -> phone fallback`\n\nRay-Ban Display **Web App** HTML surfaces are not native Display; they belong to [Web Apps](..\u002Fmeta-wearables-web-apps\u002FSKILL.md). Package setup, registration, and sessions belong to [DAT integration](..\u002Fmeta-wearables-dat-integration\u002FSKILL.md).\n\nApply the [shared rules](..\u002Fmeta-wearables-knowledge-base\u002Freferences\u002Fshared-rules.md) — evidence ladder, device labels, secrets, claims.\n\n## Lanes\n\n| Lane | Detail | Knowledge base |\n| --- | --- | --- |\n| Camera and photo | [camera-audio.md](references\u002Fcamera-audio.md) | [session, camera, audio](..\u002Fmeta-wearables-knowledge-base\u002Freferences\u002F70-meta-wearables\u002F03-device-session-camera-and-audio.md) |\n| Audio (HFP in, A2DP out) | [camera-audio.md](references\u002Fcamera-audio.md) | [transport and audio](..\u002Fmeta-wearables-knowledge-base\u002Freferences\u002F70-meta-wearables\u002F22-transport-audio-and-runtime-reliability.md) |\n| Native Display | [display.md](references\u002Fdisplay.md) | [Display access](..\u002Fmeta-wearables-knowledge-base\u002Freferences\u002F70-meta-wearables\u002F04-display-access-and-glasses-ui.md) |\n| Input and sensors | [input-sensor-contract.md](references\u002Finput-sensor-contract.md) | [input and sensors](..\u002Fmeta-wearables-knowledge-base\u002Freferences\u002F70-meta-wearables\u002F24-input-sensors-and-physical-interaction.md) |\n| Transport and reliability | [transport-contract.md](references\u002Ftransport-contract.md) | [transport and audio](..\u002Fmeta-wearables-knowledge-base\u002Freferences\u002F70-meta-wearables\u002F22-transport-audio-and-runtime-reliability.md) |\n\n## Read before acting\n\n- Inspect the actual DAT version, platform audio setup (`AVAudioSession` or Android audio route), Bluetooth\u002Flocal-network keys, existing media pipeline, persistence, upload, and background behavior.\n- Read [on-device compliance](..\u002Fmeta-wearables-knowledge-base\u002Freferences\u002F70-meta-wearables\u002F17-on-device-compliance-and-runtime-contract.md) for processing location, raw-media boundaries, retention, and thermal fallback, and [application architecture](..\u002Fmeta-wearables-knowledge-base\u002Freferences\u002F70-meta-wearables\u002F19-application-architecture-and-platform-boundaries.md) for ownership, session epochs, and phone fallback seams.\n- Read [device-generation runtime support](..\u002Fmeta-wearables-knowledge-base\u002Freferences\u002F70-meta-wearables\u002F16-device-generation-and-runtime-support-matrix.md) before using Gen 2, Display, or Gen 3 language.\n- Start from a [camera](..\u002Fmeta-wearables-implementation-recipes\u002Fassets\u002Fmeta-wearables-ios-camera-starter\u002FMetaWearablesCameraStarter.swift) or [Display](..\u002Fmeta-wearables-implementation-recipes\u002Fassets\u002Fmeta-wearables-ios-display-starter\u002FMetaWearablesDisplayStarter.swift) seed in [implementation recipes](..\u002Fmeta-wearables-implementation-recipes\u002FSKILL.md); Android equivalents sit beside them.\n\n## Workflow\n\n1. Freeze the tuple: platform, DAT tag or artifact, Meta AI app, runtime device identity, firmware\u002FDAT-app, mode\u002Fchannel, requested capability.\n2. Gate on the runtime capability response (for example `supportsDisplay()`), registration, session readiness, and permission. Never gate on a product name.\n3. Name the source of every signal: glasses camera vs phone camera; HFP glasses mic vs phone mic vs A2DP playback vs remote transcription; native Display tap vs Web App focus event vs phone sensor.\n4. Classify each transport hop — Bluetooth control, Wi-Fi\u002Flocal network, HFP, A2DP, Internet — from the observed route. Keep processing location (glasses-native, phone-local, remote, mixed) separate from transport.\n5. Define ownership and bounded queues: drop, coalesce, or block policy; timestamps; session epoch; stop order (stop capability, cancel consumers, then stop the session).\n6. Model failure states — denied, unsupported, doff\u002Ffold, `hingesClosed`, timeout, disconnect, thermal, peak power — with a visible fallback and one bounded recovery. Never auto-retry a thermal or power shutdown.\n7. For Display, project a small sanitized phone-owned snapshot, model focus\u002Fdismiss\u002Ftimeout, and clear the view on every terminal path.\n8. For input and sensors, normalize events with source, action, epoch, and bounded payload; reject stale epochs, debounce duplicates, and stop listeners on exit or denial.\n9. Test with MockDevice and fixtures first (denied, stale, slow consumer, stop-while-streaming, reconnect), then record connected and physical runs separately.\n\n## Fast path\n\nTake one capability slice: gate → one owned stream, view, or listener → one event → teardown → phone fallback. Measure queue, latency, and thermal budgets at the adapter boundary. A working camera stream must not become a prerequisite for unrelated audio, Display, or input work.\n\n## Hard boundaries\n\n- Never call a phone microphone, A2DP playback, or phone camera a glasses capture.\n- Never send raw media or raw IMU\u002FEMG\u002Flocation traces off-device without documented consent, retention, and deletion; sensor availability is not consent.\n- Never claim native DAT IMU, EMG, Neural Band, or temple-gesture APIs from a conceptual reference label; keep them `to-verify` until the selected artifact exposes them.\n- Never infer Android Wi-Fi transport from iOS configuration or an `INTERNET` permission.\n- Never treat a Bluetooth link, registration, or `supportsDisplay()` as proof of camera, HFP, Wi-Fi, Display legibility, or input timing.\n- Never hide permission, link, timeout, thermal, or power failure behind a spinner or unbounded retry.\n\n## Required output\n\n1. Capability, permission, and runtime-gate matrix per lane, with unresolved rows marked `to-verify`.\n2. Source labeling for every signal (glasses vs phone vs remote) and the transport\u002Fprocessing-location diagram.\n3. Ownership, bounded-queue, epoch, and stop-order contract for each stream, view, or listener.\n4. Display state machine and phone handoff when Display is in scope.\n5. Failure\u002Frecovery table with the first failing state and typed fallback.\n6. Privacy and retention table for raw media and sensor data.\n7. Evidence plan using the `TRN-*` and `INP-*` rows plus mock, connected, and physical camera\u002Faudio\u002FDisplay scripts.\n\n## Related skills\n\nHardware proof: [device proof](..\u002Fmeta-wearables-device-proof\u002FSKILL.md). Link, firmware, and readiness failures: [diagnostics](..\u002Fmeta-wearables-diagnostics\u002FSKILL.md). On-device and privacy claims: [trust and release](..\u002Fmeta-wearables-trust-and-release\u002FSKILL.md). Cross-surface architecture: [route planner](..\u002Fmeta-wearables-route-planner\u002FSKILL.md).\n",{"name":5,"description":7,"allowed-tools":24,"last_verified":25},"Read, Grep, Glob",1787356800000,"main","f846d9a97082ff30d613b55a085cef425d822473","plugins\u002Fmeta-wearables-ops\u002Fskills\u002Fmeta-wearables-device-capabilities","https:\u002F\u002Fgithub.com\u002Fshotcowboystyle\u002Fag-skills","https:\u002F\u002Fgithub.com\u002Fshotcowboystyle","https:\u002F\u002Fshotcowboystyle.github.io","Building smarter with AI, automation & modern tools. Exploring how far one person can go without a big team using today’s AI.","2026-11-10 04:58:27",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add shotcowboystyle\u002Fag-skills --skill meta-wearables-device-capabilities",{"tool":40,"command":41},"bunx","bunx skills add shotcowboystyle\u002Fag-skills --skill meta-wearables-device-capabilities",{"tool":43,"command":44},"pnpm","pnpm dlx skills add shotcowboystyle\u002Fag-skills --skill meta-wearables-device-capabilities","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fshotcowboystyle\u002Fag-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fmeta-wearables-ops\u002Fskills\u002Fmeta-wearables-device-capabilities\u002FSKILL.md",true,[48,54,58,62],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fcamera-audio.md","REFERENCE","参考文档",4255,"https:\u002F\u002Fgithub.com\u002Fshotcowboystyle\u002Fag-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fmeta-wearables-ops\u002Fskills\u002Fmeta-wearables-device-capabilities\u002Freferences\u002Fcamera-audio.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fdisplay.md",4149,"https:\u002F\u002Fgithub.com\u002Fshotcowboystyle\u002Fag-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fmeta-wearables-ops\u002Fskills\u002Fmeta-wearables-device-capabilities\u002Freferences\u002Fdisplay.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Finput-sensor-contract.md",6522,"https:\u002F\u002Fgithub.com\u002Fshotcowboystyle\u002Fag-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fmeta-wearables-ops\u002Fskills\u002Fmeta-wearables-device-capabilities\u002Freferences\u002Finput-sensor-contract.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Ftransport-contract.md",5965,"https:\u002F\u002Fgithub.com\u002Fshotcowboystyle\u002Fag-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fmeta-wearables-ops\u002Fskills\u002Fmeta-wearables-device-capabilities\u002Freferences\u002Ftransport-contract.md",[67,73,80,87,94,101],{"skillNo":68,"name":69,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7F1YRY5S5QRJ1V0BJS130QX","no-description","https:\u002F\u002Fgithub.com\u002Fshotcowboystyle\u002Fag-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fno-description\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7F1Y9BV2FJNQJ3NB32JS5CM","good-skill","Fixture skill that satisfies every rule.","https:\u002F\u002Fgithub.com\u002Fshotcowboystyle\u002Fag-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fgood-skill\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7F1XXBQ3NQRXZSS0KAGAR9V","broken-link","Links to a reference file that does not exist.","https:\u002F\u002Fgithub.com\u002Fshotcowboystyle\u002Fag-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fbroken-link\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7F1XBX4R46NR9W0HXQ7XCDX","Bad_Name","Name violates the kebab-case rule and does not match the directory.","https:\u002F\u002Fgithub.com\u002Fshotcowboystyle\u002Fag-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fbad-name\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7F1WNAF8WNEQ7S5HKT5VK0D","skill-authoring","Write, review, and validate portable agent skills in SKILL.md format. Use when creating a new skill, editing an existing one, or asked whether a skill follows the Agent Skills spec.","https:\u002F\u002Fgithub.com\u002Fshotcowboystyle\u002Fag-skills\u002Fblob\u002Fmain\u002Fskills\u002Fskill-authoring\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M7F1W30TC0XFNSF7YBRGETK2","weigh-bags","Record scale readings for each bag — empty (tare), outbound, current, final — and reconcile them against the itemised inventory to find unaccounted weight. Use when the user gives a bag weight, says how heavy something is, weighs their luggage, or asks how close to the limit they are. Appends to bags.yaml and runs scripts\u002Freconcile.py.","https:\u002F\u002Fgithub.com\u002Fshotcowboystyle\u002Fag-skills\u002Fblob\u002Fmain\u002Fplugins\u002Ftravel-packing-assistant\u002Fskills\u002Fweigh-bags\u002FSKILL.md",[],[]]