[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EDZF9SDYTMNHWEWZAR94V8":3,"skill-same:01M7EDZF9SDYTMNHWEWZAR94V8":82},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7EDZF9SDYTMNHWEWZAR94V8","urgent-help-escalation-call",null,"When a vulnerable person asks for help inside an app, ring the human responsible for them and say only what is needed — who asked, and when. Returns whether the message actually landed and whether anyone confirmed they are going. Use for panic and help buttons, lone-worker duress alarms, fall and inactivity alerts, post-discharge escalation, care-home call bells, and any \"the notification is not enough, phone someone\" workflow.","fozagtx\u002FBuildOS-workflow","fozagtx","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160292135?v=4","01M7EAS4W39D2X3WNCCVVZ7CVZ","fawuzan","01M7EAS4WP1G4JD4KG87P6PTK6",0,"MIT","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Furgent-help-escalation-call\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: urgent-help-escalation-call\ndescription: When a vulnerable person asks for help inside an app, ring the human responsible for them and say only what is needed — who asked, and when. Returns whether the message actually landed and whether anyone confirmed they are going. Use for panic and help buttons, lone-worker duress alarms, fall and inactivity alerts, post-discharge escalation, care-home call bells, and any \"the notification is not enough, phone someone\" workflow.\nlicense: MIT\n---\n\n# Urgent Help Escalation Call\n\nUse this skill when software has learned that someone needs a human, and a\nnotification is not good enough.\n\nAn in-app alert is only as good as somebody looking at a screen. The moments\nwhen that assumption fails are exactly the moments the alert exists for: the\nmiddle of the night, a shower, a meeting, a commute. A ringing phone is the one\nchannel that reliably interrupts.\n\nThis skill is the bridge. One trigger, one call, one clear answer about whether\nit landed.\n\n## The two people\n\nGetting this wrong is the failure mode that matters most, so name them\nseparately in your own code:\n\n| | Who | Role |\n| --- | --- | --- |\n| **Subject** | the vulnerable person | asked for help; is **never** called by this skill |\n| **Recipient** | the carer, responder, or next of kin | the one whose phone rings |\n\nDialling the subject instead of the recipient means telling a frightened person\nthat a frightened person needs help. Keep the two numbers in separate fields,\nlabel them unambiguously in any UI, and validate them separately.\n\n## When To Use\n\n- panic buttons and help buttons in apps used by vulnerable people\n- lone-worker duress alarms\n- fall detection, inactivity timeouts, or bed-exit alerts\n- care-home call bells that need to reach staff who are not at a station\n- post-discharge deterioration flags\n- any in-app urgent signal where \"they will see the notification\" is a bad bet\n\n## When Not To Use\n\nDo not use this skill to:\n\n- replace emergency services — see [Emergencies](#emergencies)\n- call the subject themselves, for any reason\n- deliver clinical detail, triage, or advice by phone\n- send routine or digest notifications; this is for urgent signals only\n- escalate something the subject did not actually ask for, without saying so\n- call a responder who has not agreed to be called\n\n## Required Fields\n\nAsk for anything missing. **Never** infer these:\n\n| Field | Notes |\n| --- | --- |\n| `recipient_phone` | E.164. The responder's number, never the subject's. Validate; never guess a country code. |\n| `subject_name` | What the responder should be told, e.g. \"Eleanor\". |\n| `triggered_at` | When the request happened, so the call can say *when* rather than \"just now\". |\n| `recipient_name` | Optional but strongly preferred — being addressed by name at 3am is worth a lot. |\n| `region` | Optional. Chosen, not inferred — it decides which line the call comes from. |\n\n## Core Workflow\n\n1. Confirm the trigger is genuinely urgent and came from the subject or a\n   sensor, not from a routine event.\n2. Check the cooldown for this subject. If a call went out recently, stop —\n   see [`references\u002Frepeat-triggers.md`](references\u002Frepeat-triggers.md).\n3. Build the message from [`references\u002Fcall-goal.md`](references\u002Fcall-goal.md).\n   Short. One fact, one instruction.\n4. Place exactly one call to `recipient_phone`, with an idempotency key derived\n   from the recipient and the trigger minute so a retried request cannot ring\n   twice.\n5. Read the structured result: did it reach the recipient, and did they confirm.\n6. If it did not reach them, follow\n   [`references\u002Fescalation-ladder.md`](references\u002Fescalation-ladder.md).\n7. Record the outcome where the humans involved can see it.\n\n**Fire the call without blocking the trigger.** The subject is standing there\nhaving asked for help; the app's response to them must not wait on a phone\nnetwork, and a failure to connect must never surface to them as an error. Raise\nyour in-app alert first, place the call alongside it.\n\n## What The Call Says\n\n**Confirm who is listening before you disclose anything.** This ordering is the\ndesign, not a nicety:\n\n```\n\"Hello, this is \u003Cproduct>. Am I speaking with \u003Crecipient>?\"\n   ├─ no \u002F unsure → \"Sorry to have troubled you. Goodbye.\"  → hang up, say nothing\n   └─ yes         → \"\u003Csubject> has pressed the help button and is asking for\n                     you. Please go to them when you can.\"\n                  → \"Are you able to get to them?\" → thank them → hang up\n```\n\nThe obvious design leads with the message to save a second. It is wrong. A\nnumber will eventually be answered by a neighbour, a partner, a child, or a\nstranger with a recycled number — and leading with the message tells them a\nnamed vulnerable person has asked for help before you know who is listening.\nNothing downstream can un-say it, and a \"if it's the wrong person, stop\" branch\nfires only after the model has already spoken.\n\nAfter the gate:\n\n- Do not sound alarmed. Panic on the phone gets nobody there faster.\n- Do not speculate about *why*. You do not know, and a guess becomes what the\n  responder believes on the drive over.\n- Say nothing about the subject's health, condition, or history.\n- Never ask a stranger to pass the message on — that is a disclosure with extra\n  steps.\n- Ask whether they can go — **a question, not an instruction**. \"Confirm you are\n  going to her\" reads as an order barked at someone just woken up. Ask once,\n  accept the answer, do not press. They may be two hours away.\n- Sound like a person passing on a message, not a system issuing one. Models\n  drift officious when handed numbered steps and a schema; say the register you\n  want out loud.\n- **Voicemail names nobody.** It is the one case where the gate cannot run, so\n  the message must be safe for a whole room to overhear: no name, no reason,\n  just \"there is an alert waiting in your app\".\n- Keep it under a minute.\n\nFull template and the reasoning line by line: [`references\u002Fcall-goal.md`](references\u002Fcall-goal.md).\n\n## Structured Result\n\nTwo questions, no more:\n\n```json\n{\n  \"reached\": \"caregiver | someone_else | voicemail | no_answer\",\n  \"acknowledged\": \"yes | no | unknown\"\n}\n```\n\n`reached` is not the same as `acknowledged`. A voicemail is a message left, not\na person on their way, and the difference decides whether the ladder continues.\nFull schema and the reasoning: [`references\u002Fresult-schema.md`](references\u002Fresult-schema.md).\n\n## Consent\n\nSimpler than a call *to* a vulnerable person, but not nothing:\n\n- **The recipient agreed to be called.** They configured the number, or someone\n  authorized to did. Record who and when.\n- **The subject knows this happens.** Pressing a help button should be\n  understood as \"this will fetch someone\", and any consent flow should say so\n  plainly rather than burying it.\n- **Health information is disclosed to whoever answers.** That is why the\n  message says only that someone asked for you. See\n  [`references\u002Fconsent-and-boundaries.md`](references\u002Fconsent-and-boundaries.md).\n\n## Repeat Triggers\n\nSomeone frightened, confused, or in pain may press a button many times in a\nminute. The responder needs one call, not eleven — and each one costs money.\n\nHold a cooldown per subject, not per request. Suppress inside the window and log\nthat you did. Never let one subject's cooldown silence another's.\nDetails and the trade-offs: [`references\u002Frepeat-triggers.md`](references\u002Frepeat-triggers.md).\n\n## Emergencies\n\n**This is not an emergency service and must never be presented as one.**\n\nIt reaches one nominated person, who may be asleep, driving, or unreachable. It\ncannot assess anything. It does not know whether the subject is hurt.\n\nSay plainly in your product and your setup docs that the subject must have a\nreal route to emergency help that does not depend on this call being placed,\nanswered, or correctly understood.\n\n## Side Effects, Cancellation, Cost\n\n- **Side effect:** one real outbound phone call to a real person, per trigger\n  that survives the cooldown.\n- **Cancellation:** nothing to cancel once a call connects. This skill creates\n  no provider-side recurrence — it fires on an event, not a schedule.\n- **Cost:** one call from the CALL-E account per escalation. The cooldown is\n  what stands between a distressed subject and a large bill.\n- **No-call path:** this contribution ships a fake CALL-E server\n  (`scripts\u002Ffake-calle-api.mjs`) serving the documented shapes, so the trigger,\n  call contract, structured result, and escalation ladder can be exercised\n  without ringing anyone. Use it for tests, CI, and demos.\n\n## Reference design\n\nThis pattern was developed for **Yadira**, a companion for people living with\ndementia. In that product, a person presses a help button; the ordinary in-app\nalert is raised immediately, and CALL-E separately rings the configured\ncaregiver. The subject's number is never supplied to this workflow.\n\nTwo decisions from that implementation are worth copying:\n\n**Do not make the phone call the only alert.** A call can be delayed, silenced,\nor missed. Raise the in-app alert first and treat the phone call as an\nadditional interruptive channel.\n\n**The provider's voice is not yours.** If your product depends on a specific,\nfamiliar voice for the vulnerable person, an outbound provider voice may be the\nwrong channel. This skill deliberately calls the responder instead.\n","# Urgent Help Escalation Call\n\nUse this skill when software has learned that someone needs a human, and a\nnotification is not good enough.\n\nAn in-app alert is only as good as somebody looking at a screen. The moments\nwhen that assumption fails are exactly the moments the alert exists for: the\nmiddle of the night, a shower, a meeting, a commute. A ringing phone is the one\nchannel that reliably interrupts.\n\nThis skill is the bridge. One trigger, one call, one clear answer about whether\nit landed.\n\n## The two people\n\nGetting this wrong is the failure mode that matters most, so name them\nseparately in your own code:\n\n| | Who | Role |\n| --- | --- | --- |\n| **Subject** | the vulnerable person | asked for help; is **never** called by this skill |\n| **Recipient** | the carer, responder, or next of kin | the one whose phone rings |\n\nDialling the subject instead of the recipient means telling a frightened person\nthat a frightened person needs help. Keep the two numbers in separate fields,\nlabel them unambiguously in any UI, and validate them separately.\n\n## When To Use\n\n- panic buttons and help buttons in apps used by vulnerable people\n- lone-worker duress alarms\n- fall detection, inactivity timeouts, or bed-exit alerts\n- care-home call bells that need to reach staff who are not at a station\n- post-discharge deterioration flags\n- any in-app urgent signal where \"they will see the notification\" is a bad bet\n\n## When Not To Use\n\nDo not use this skill to:\n\n- replace emergency services — see [Emergencies](#emergencies)\n- call the subject themselves, for any reason\n- deliver clinical detail, triage, or advice by phone\n- send routine or digest notifications; this is for urgent signals only\n- escalate something the subject did not actually ask for, without saying so\n- call a responder who has not agreed to be called\n\n## Required Fields\n\nAsk for anything missing. **Never** infer these:\n\n| Field | Notes |\n| --- | --- |\n| `recipient_phone` | E.164. The responder's number, never the subject's. Validate; never guess a country code. |\n| `subject_name` | What the responder should be told, e.g. \"Eleanor\". |\n| `triggered_at` | When the request happened, so the call can say *when* rather than \"just now\". |\n| `recipient_name` | Optional but strongly preferred — being addressed by name at 3am is worth a lot. |\n| `region` | Optional. Chosen, not inferred — it decides which line the call comes from. |\n\n## Core Workflow\n\n1. Confirm the trigger is genuinely urgent and came from the subject or a\n   sensor, not from a routine event.\n2. Check the cooldown for this subject. If a call went out recently, stop —\n   see [`references\u002Frepeat-triggers.md`](references\u002Frepeat-triggers.md).\n3. Build the message from [`references\u002Fcall-goal.md`](references\u002Fcall-goal.md).\n   Short. One fact, one instruction.\n4. Place exactly one call to `recipient_phone`, with an idempotency key derived\n   from the recipient and the trigger minute so a retried request cannot ring\n   twice.\n5. Read the structured result: did it reach the recipient, and did they confirm.\n6. If it did not reach them, follow\n   [`references\u002Fescalation-ladder.md`](references\u002Fescalation-ladder.md).\n7. Record the outcome where the humans involved can see it.\n\n**Fire the call without blocking the trigger.** The subject is standing there\nhaving asked for help; the app's response to them must not wait on a phone\nnetwork, and a failure to connect must never surface to them as an error. Raise\nyour in-app alert first, place the call alongside it.\n\n## What The Call Says\n\n**Confirm who is listening before you disclose anything.** This ordering is the\ndesign, not a nicety:\n\n```\n\"Hello, this is \u003Cproduct>. Am I speaking with \u003Crecipient>?\"\n   ├─ no \u002F unsure → \"Sorry to have troubled you. Goodbye.\"  → hang up, say nothing\n   └─ yes         → \"\u003Csubject> has pressed the help button and is asking for\n                     you. Please go to them when you can.\"\n                  → \"Are you able to get to them?\" → thank them → hang up\n```\n\nThe obvious design leads with the message to save a second. It is wrong. A\nnumber will eventually be answered by a neighbour, a partner, a child, or a\nstranger with a recycled number — and leading with the message tells them a\nnamed vulnerable person has asked for help before you know who is listening.\nNothing downstream can un-say it, and a \"if it's the wrong person, stop\" branch\nfires only after the model has already spoken.\n\nAfter the gate:\n\n- Do not sound alarmed. Panic on the phone gets nobody there faster.\n- Do not speculate about *why*. You do not know, and a guess becomes what the\n  responder believes on the drive over.\n- Say nothing about the subject's health, condition, or history.\n- Never ask a stranger to pass the message on — that is a disclosure with extra\n  steps.\n- Ask whether they can go — **a question, not an instruction**. \"Confirm you are\n  going to her\" reads as an order barked at someone just woken up. Ask once,\n  accept the answer, do not press. They may be two hours away.\n- Sound like a person passing on a message, not a system issuing one. Models\n  drift officious when handed numbered steps and a schema; say the register you\n  want out loud.\n- **Voicemail names nobody.** It is the one case where the gate cannot run, so\n  the message must be safe for a whole room to overhear: no name, no reason,\n  just \"there is an alert waiting in your app\".\n- Keep it under a minute.\n\nFull template and the reasoning line by line: [`references\u002Fcall-goal.md`](references\u002Fcall-goal.md).\n\n## Structured Result\n\nTwo questions, no more:\n\n```json\n{\n  \"reached\": \"caregiver | someone_else | voicemail | no_answer\",\n  \"acknowledged\": \"yes | no | unknown\"\n}\n```\n\n`reached` is not the same as `acknowledged`. A voicemail is a message left, not\na person on their way, and the difference decides whether the ladder continues.\nFull schema and the reasoning: [`references\u002Fresult-schema.md`](references\u002Fresult-schema.md).\n\n## Consent\n\nSimpler than a call *to* a vulnerable person, but not nothing:\n\n- **The recipient agreed to be called.** They configured the number, or someone\n  authorized to did. Record who and when.\n- **The subject knows this happens.** Pressing a help button should be\n  understood as \"this will fetch someone\", and any consent flow should say so\n  plainly rather than burying it.\n- **Health information is disclosed to whoever answers.** That is why the\n  message says only that someone asked for you. See\n  [`references\u002Fconsent-and-boundaries.md`](references\u002Fconsent-and-boundaries.md).\n\n## Repeat Triggers\n\nSomeone frightened, confused, or in pain may press a button many times in a\nminute. The responder needs one call, not eleven — and each one costs money.\n\nHold a cooldown per subject, not per request. Suppress inside the window and log\nthat you did. Never let one subject's cooldown silence another's.\nDetails and the trade-offs: [`references\u002Frepeat-triggers.md`](references\u002Frepeat-triggers.md).\n\n## Emergencies\n\n**This is not an emergency service and must never be presented as one.**\n\nIt reaches one nominated person, who may be asleep, driving, or unreachable. It\ncannot assess anything. It does not know whether the subject is hurt.\n\nSay plainly in your product and your setup docs that the subject must have a\nreal route to emergency help that does not depend on this call being placed,\nanswered, or correctly understood.\n\n## Side Effects, Cancellation, Cost\n\n- **Side effect:** one real outbound phone call to a real person, per trigger\n  that survives the cooldown.\n- **Cancellation:** nothing to cancel once a call connects. This skill creates\n  no provider-side recurrence — it fires on an event, not a schedule.\n- **Cost:** one call from the CALL-E account per escalation. The cooldown is\n  what stands between a distressed subject and a large bill.\n- **No-call path:** this contribution ships a fake CALL-E server\n  (`scripts\u002Ffake-calle-api.mjs`) serving the documented shapes, so the trigger,\n  call contract, structured result, and escalation ladder can be exercised\n  without ringing anyone. Use it for tests, CI, and demos.\n\n## Reference design\n\nThis pattern was developed for **Yadira**, a companion for people living with\ndementia. In that product, a person presses a help button; the ordinary in-app\nalert is raised immediately, and CALL-E separately rings the configured\ncaregiver. The subject's number is never supplied to this workflow.\n\nTwo decisions from that implementation are worth copying:\n\n**Do not make the phone call the only alert.** A call can be delayed, silenced,\nor missed. Raise the in-app alert first and treat the phone call as an\nadditional interruptive channel.\n\n**The provider's voice is not yours.** If your product depends on a specific,\nfamiliar voice for the vulnerable person, an outbound provider voice may be the\nwrong channel. This skill deliberately calls the responder instead.\n",{"name":5,"license":15,"description":7},"master","8c91ae30409640de28e218b3e9c7fe01c01d257b","skills\u002Furgent-help-escalation-call","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow","https:\u002F\u002Fgithub.com\u002Ffozagtx","hi.fawuzanpima@gmail.com","Forward deployed","2026-10-08 00:13:28",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add fozagtx\u002FBuildOS-workflow --skill urgent-help-escalation-call",{"tool":38,"command":39},"bunx","bunx skills add fozagtx\u002FBuildOS-workflow --skill urgent-help-escalation-call",{"tool":41,"command":42},"pnpm","pnpm dlx skills add fozagtx\u002FBuildOS-workflow --skill urgent-help-escalation-call","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Furgent-help-escalation-call\u002FSKILL.md",true,[46,52,56,60,64,68,72,76],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fcall-goal.md","REFERENCE","参考文档",5140,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Furgent-help-escalation-call\u002Freferences\u002Fcall-goal.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fconsent-and-boundaries.md",2655,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Furgent-help-escalation-call\u002Freferences\u002Fconsent-and-boundaries.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fescalation-ladder.md",3326,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Furgent-help-escalation-call\u002Freferences\u002Fescalation-ladder.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fexamples.md",2151,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Furgent-help-escalation-call\u002Freferences\u002Fexamples.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Frepeat-triggers.md",2960,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Furgent-help-escalation-call\u002Freferences\u002Frepeat-triggers.md",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fresult-schema.md",2016,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Furgent-help-escalation-call\u002Freferences\u002Fresult-schema.md",{"path":73,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fsafety.md",1849,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Furgent-help-escalation-call\u002Freferences\u002Fsafety.md",{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"scripts\u002Ffake-calle-api.mjs","SCRIPT","脚本",4868,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Furgent-help-escalation-call\u002Fscripts\u002Ffake-calle-api.mjs",[83,90,97,104,111,120],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7EE49XAN8GE213J691P3RZ9","xitter","Interact with X\u002FTwitter via the x-cli terminal client using official X API credentials. Use for posting, reading timelines, searching tweets, liking, retweeting, bookmarks, mentions, and user lookups.","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fxitter\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7EE3TMR3CR7HR7HTCAKPTTR","writing-plans","Use when you have a spec or requirements for a multi-step task. Creates comprehensive implementation plans with bite-sized tasks, exact file paths, and complete code examples.","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M7EE3AJ6V2VBVAX1WTV7M447","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fwhisper\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M7EE36AAP5THSCQAHH6JCWVV","weights-and-biases","Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fweights-and-biases\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":115,"licenseFileUrl":116,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":19},"01M7EE30R3S4EAK1FWJEBG7MW9","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":19},"01M7EE2X3PJ0ZJR0JJNF2M4NS5","web-pentest","Authorized web pentest: recon, proof-based exploits, report.","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fweb-pentest\u002FSKILL.md",[],[]]