[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EAWVB6R8TRD6WVGSMCWA59":3,"skill-same:01M7EAWVB6R8TRD6WVGSMCWA59":84},{"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},"01M7EAWVB6R8TRD6WVGSMCWA59","appointment-call-confirm",null,"Places outbound CALL-E confirmation calls for a batch of upcoming appointments or bookings and returns a structured confirmed \u002F needs-reschedule \u002F declined \u002F no-answer result per recipient, so a business can close its next-day no-show gap without a staff member manually dialing down the list.","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\u002Fappointment-call-confirm\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: appointment-call-confirm\ndescription: Places outbound CALL-E confirmation calls for a batch of upcoming appointments or bookings and returns a structured confirmed \u002F needs-reschedule \u002F declined \u002F no-answer result per recipient, so a business can close its next-day no-show gap without a staff member manually dialing down the list.\nlicense: MIT\n---\n\n# Appointment Call Confirm\n\n## Why this exists\n\nAny service business that books time slots — clinics, salons, repair\nshops, tutoring, veterinary practices, small logistics\u002Fdelivery\nwindows — loses revenue to no-shows. The standard mitigation is a\nperson on staff spending part of every afternoon manually phoning\ntomorrow's appointment list to confirm, reschedule, or free up a slot.\nIt is repetitive, easy to skip on a busy day, and does not scale past a\nhandful of bookings.\n\n`appointment-call-confirm` automates exactly that one workflow — not a\ngeneral-purpose \"AI that makes phone calls.\" Given a list of upcoming\nappointments (recipient, phone, appointment time, business\u002Ftask\ncontext), it places one outbound CALL-E call per appointment, asks the\nrecipient to confirm, reschedule, or cancel, and returns a structured\nresult per call that a host can write back to wherever appointments\nalready live (a spreadsheet, a calendar, a CRM, a CSV).\n\nThis is a **workflow skill**, not a new CALL-E backend API. It does not\nadd call-scheduling, recurrence, or provider-side state — it wraps\nCALL-E's existing one-off `POST \u002Fv1\u002Fcalls` \u002F `GET \u002Fv1\u002Fcalls\u002F{id}`\nDeveloper API in a batch-confirmation shape and hands the caller a\nconsistent result contract.\n\n## When To Use\n\nUse this skill when:\n\n- a user has a list of upcoming appointments\u002Fbookings and wants each\n  recipient called to confirm, reschedule, or cancel before the slot\n- a user asks something like *\"call everyone on tomorrow's schedule and\n  confirm they're still coming\"* or *\"phone these 12 customers and ask\n  if 2pm still works\"*\n- the result of each call needs to be written back somewhere\n  structured (a sheet, a file, a downstream system) rather than just\n  read aloud in chat\n\n## When Not To Use\n\nDo not use this skill to:\n\n- place a single one-off call with no confirm\u002Freschedule\u002Fdecline\n  structure — use CALL-E's plain call API directly instead\n- create a recurring\u002Fscheduled calling job — see the `call-reminder`\n  skill in this repository for scheduler-wrapped recurring calls\n- call any recipient who has not already been given a specific\n  appointment\u002Fbooking with the caller's business — this skill is for\n  confirming existing appointments, not cold outreach or lead\n  generation\n- guess a recipient's phone number, region, or language from anything\n  other than what the caller\u002Fhost explicitly provided\n- place a call before the user has explicitly confirmed the appointment\n  list is correct and that the calls should go out\n\n## Core Workflow\n\n1. **Collect the appointment batch.** Each entry needs, at minimum:\n   `recipient_name`, `phone` (E.164), `appointment_time` (ISO 8601,\n   with timezone), and a short `context` string (what the appointment\n   is for — e.g. \"annual checkup with Dr. Rao\", \"car pickup for\n   invoice #4021\"). Ask for any missing required field rather than\n   inferring it.\n2. **Dry-run the batch before calling anyone.** Print the full list\n   (name, masked phone, time, context) and require explicit\n   confirmation before any call is placed — see\n   `references\u002Fsafety.md`. This mirrors CALL-E's own guidance that\n   phone-call workflows must be safe to preview without a real call.\n3. **Build the CALL-E task per recipient** using\n   `references\u002Fresult-schema.md`'s `result_schema`, so CALL-E returns\n   a structured `status` (`confirmed` \u002F `needs_reschedule` \u002F\n   `declined` \u002F `no_answer` \u002F `voicemail`) and an optional\n   `requested_new_time` instead of free text that has to be\n   re-parsed.\n4. **Place calls serially, not in parallel.** One call in flight per\n   recipient at a time (see `scripts\u002Fplace_confirmation_calls.py`).\n   This keeps behavior predictable, keeps a single failing call from\n   masking others, and avoids surprising a business with a burst of\n   simultaneous outbound calls.\n5. **Require a separate, explicit authorization record per number.**\n   `--confirm` says the batch as a whole should place real calls;\n   a distinct `--authorized-numbers` file is the record of which\n   specific numbers consent has actually been confirmed for. A\n   recipient missing from that file is never called, even with\n   `--confirm` set — see `references\u002Fsafety.md`.\n6. **Poll each call to a terminal state** using CALL-E's\n   `GET \u002Fv1\u002Fcalls\u002F{call_id}` before moving to the next recipient (or\n   asynchronously, if the host has its own webhook\u002Fqueue — see the\n   script's `--webhook-url` option). If a call's outcome is ever\n   ambiguous — a local\u002Fnetwork error, a missing call id, or a poll\n   that times out — **halt the entire batch immediately** rather than\n   guessing or advancing to the next recipient; a call CALL-E may or\n   may not have actually placed must be reconciled by a human before\n   anything else is dialed.\n7. **Write back one structured row per recipient**: name, masked\n   phone, appointment time, call status, structured result, and the\n   CALL-E `call_id` for auditability — to CSV by default\n   (`scripts\u002Fplace_confirmation_calls.py --out results.csv`), or\n   forward each result to a host-provided sink (webhook, sheet,\n   ticketing system).\n8. **Never claim a call happened if CALL-E rejected the request.**\n   Report the rejection reason from the API and halt rather than\n   retrying silently or moving on as if nothing happened.\n\n## Required Fields (per appointment)\n\n- `recipient_name`\n- `phone` — E.164, e.g. `+14155550101`\n- `appointment_time` — ISO 8601 with timezone, e.g.\n  `2026-09-05T15:00:00-04:00`\n- `context` — one sentence describing what the appointment is for,\n  used to build the call's `task`\n\nOptional: `region` (CALL-E region code, defaults to inferring from the\nphone country code if omitted — see `references\u002Fresult-schema.md`),\n`locale`, `business_name` (used in the call script), `metadata`\n(free-form, echoed back with the result).\n\n## Safety Rules\n\nRead `references\u002Fsafety.md` for the full contract. In short:\n\n- This skill places real phone calls with real consequences — never\n  run the batch without the user explicitly reviewing and approving\n  the dry-run list first.\n- Only call the phone numbers explicitly provided for this batch —\n  never a number pulled from an unrelated contact list or guessed.\n- Mask phone numbers in every user-facing summary (`+1415•••0101`);\n  the full number is only ever sent to CALL-E's API, never printed to\n  a log a bystander could read over someone's shoulder.\n- Do not fabricate a `confirmed` \u002F `declined` \u002F etc. result if CALL-E's\n  response doesn't clearly support it — report `unclear` and surface\n  the raw summary instead of guessing.\n- Do not retry a failed call automatically more than once per\n  recipient per run; repeated unwanted calls are a real-world harm,\n  not just a technical annoyance. If any call's outcome is ambiguous,\n  halt the whole batch rather than continuing — see\n  `references\u002Fsafety.md`.\n- Never expose the CALL-E API key in output, logs, or the results\n  file, and never send it to a CALL-E origin outside the script's\n  explicit allowlist even if `CALLE_BASE_URL` is overridden.\n- Treat any appointment context that reads as medical, legal, or\n  financial as logistics-only — the call confirms a time, it does not\n  discuss the underlying medical\u002Flegal\u002Ffinancial matter.\n- CALL-E does not currently expose a call-cancellation endpoint.\n  Stopping this script prevents further calls in the batch, but\n  cannot cancel a call already created — see the \"Cancellation\"\n  section of `references\u002Fsafety.md`.\n\n## Output Format\n\nAfter a batch run, report per recipient:\n\n- masked phone, appointment time, and CALL-E `call_id`\n- final status: `confirmed` \u002F `needs_reschedule` (with the requested\n  new time, if any) \u002F `declined` \u002F `no_answer` \u002F `voicemail` \u002F\n  `unclear` \u002F `failed` (with the rejection reason)\n\nAnd a one-line batch summary: `N confirmed, N to reschedule, N\ndeclined, N no answer, N failed` — so a business can act on the\nexceptions first instead of re-reading every row.\n\nNever state a call was completed unless CALL-E's own status for that\n`call_id` reached a terminal state.\n\n## Files\n\n- `scripts\u002Fplace_confirmation_calls.py` — standalone runner: reads a\n  CSV\u002FJSON batch, dry-runs it (stdlib only, no install needed), then\n  requires both `--confirm` and `--authorized-numbers` to place real\n  calls through CALL-E's Developer API with the shared\n  `result_schema`, polls to completion, halts the whole batch on any\n  ambiguous outcome, and writes a results CSV.\n- `requirements.txt` — the one dependency (`requests`) needed only\n  for live calls; dry-run needs nothing beyond it being present in\n  the repo so `--confirm` runs can install it.\n- `assets\u002Fauthorized_numbers.example.txt` — format reference for the\n  required `--authorized-numbers` file; copy it, don't commit your\n  real one.\n- `references\u002Fresult-schema.md` — the exact `result_schema` sent to\n  CALL-E and how each field maps to the output above.\n- `references\u002Fsafety.md` — the full safety contract this skill\n  follows, aligned with this repository's repo-wide safety patterns,\n  including the authorization gate, halt-on-ambiguity behavior, and\n  CALL-E's current lack of a cancellation endpoint.\n","# Appointment Call Confirm\n\n## Why this exists\n\nAny service business that books time slots — clinics, salons, repair\nshops, tutoring, veterinary practices, small logistics\u002Fdelivery\nwindows — loses revenue to no-shows. The standard mitigation is a\nperson on staff spending part of every afternoon manually phoning\ntomorrow's appointment list to confirm, reschedule, or free up a slot.\nIt is repetitive, easy to skip on a busy day, and does not scale past a\nhandful of bookings.\n\n`appointment-call-confirm` automates exactly that one workflow — not a\ngeneral-purpose \"AI that makes phone calls.\" Given a list of upcoming\nappointments (recipient, phone, appointment time, business\u002Ftask\ncontext), it places one outbound CALL-E call per appointment, asks the\nrecipient to confirm, reschedule, or cancel, and returns a structured\nresult per call that a host can write back to wherever appointments\nalready live (a spreadsheet, a calendar, a CRM, a CSV).\n\nThis is a **workflow skill**, not a new CALL-E backend API. It does not\nadd call-scheduling, recurrence, or provider-side state — it wraps\nCALL-E's existing one-off `POST \u002Fv1\u002Fcalls` \u002F `GET \u002Fv1\u002Fcalls\u002F{id}`\nDeveloper API in a batch-confirmation shape and hands the caller a\nconsistent result contract.\n\n## When To Use\n\nUse this skill when:\n\n- a user has a list of upcoming appointments\u002Fbookings and wants each\n  recipient called to confirm, reschedule, or cancel before the slot\n- a user asks something like *\"call everyone on tomorrow's schedule and\n  confirm they're still coming\"* or *\"phone these 12 customers and ask\n  if 2pm still works\"*\n- the result of each call needs to be written back somewhere\n  structured (a sheet, a file, a downstream system) rather than just\n  read aloud in chat\n\n## When Not To Use\n\nDo not use this skill to:\n\n- place a single one-off call with no confirm\u002Freschedule\u002Fdecline\n  structure — use CALL-E's plain call API directly instead\n- create a recurring\u002Fscheduled calling job — see the `call-reminder`\n  skill in this repository for scheduler-wrapped recurring calls\n- call any recipient who has not already been given a specific\n  appointment\u002Fbooking with the caller's business — this skill is for\n  confirming existing appointments, not cold outreach or lead\n  generation\n- guess a recipient's phone number, region, or language from anything\n  other than what the caller\u002Fhost explicitly provided\n- place a call before the user has explicitly confirmed the appointment\n  list is correct and that the calls should go out\n\n## Core Workflow\n\n1. **Collect the appointment batch.** Each entry needs, at minimum:\n   `recipient_name`, `phone` (E.164), `appointment_time` (ISO 8601,\n   with timezone), and a short `context` string (what the appointment\n   is for — e.g. \"annual checkup with Dr. Rao\", \"car pickup for\n   invoice #4021\"). Ask for any missing required field rather than\n   inferring it.\n2. **Dry-run the batch before calling anyone.** Print the full list\n   (name, masked phone, time, context) and require explicit\n   confirmation before any call is placed — see\n   `references\u002Fsafety.md`. This mirrors CALL-E's own guidance that\n   phone-call workflows must be safe to preview without a real call.\n3. **Build the CALL-E task per recipient** using\n   `references\u002Fresult-schema.md`'s `result_schema`, so CALL-E returns\n   a structured `status` (`confirmed` \u002F `needs_reschedule` \u002F\n   `declined` \u002F `no_answer` \u002F `voicemail`) and an optional\n   `requested_new_time` instead of free text that has to be\n   re-parsed.\n4. **Place calls serially, not in parallel.** One call in flight per\n   recipient at a time (see `scripts\u002Fplace_confirmation_calls.py`).\n   This keeps behavior predictable, keeps a single failing call from\n   masking others, and avoids surprising a business with a burst of\n   simultaneous outbound calls.\n5. **Require a separate, explicit authorization record per number.**\n   `--confirm` says the batch as a whole should place real calls;\n   a distinct `--authorized-numbers` file is the record of which\n   specific numbers consent has actually been confirmed for. A\n   recipient missing from that file is never called, even with\n   `--confirm` set — see `references\u002Fsafety.md`.\n6. **Poll each call to a terminal state** using CALL-E's\n   `GET \u002Fv1\u002Fcalls\u002F{call_id}` before moving to the next recipient (or\n   asynchronously, if the host has its own webhook\u002Fqueue — see the\n   script's `--webhook-url` option). If a call's outcome is ever\n   ambiguous — a local\u002Fnetwork error, a missing call id, or a poll\n   that times out — **halt the entire batch immediately** rather than\n   guessing or advancing to the next recipient; a call CALL-E may or\n   may not have actually placed must be reconciled by a human before\n   anything else is dialed.\n7. **Write back one structured row per recipient**: name, masked\n   phone, appointment time, call status, structured result, and the\n   CALL-E `call_id` for auditability — to CSV by default\n   (`scripts\u002Fplace_confirmation_calls.py --out results.csv`), or\n   forward each result to a host-provided sink (webhook, sheet,\n   ticketing system).\n8. **Never claim a call happened if CALL-E rejected the request.**\n   Report the rejection reason from the API and halt rather than\n   retrying silently or moving on as if nothing happened.\n\n## Required Fields (per appointment)\n\n- `recipient_name`\n- `phone` — E.164, e.g. `+14155550101`\n- `appointment_time` — ISO 8601 with timezone, e.g.\n  `2026-09-05T15:00:00-04:00`\n- `context` — one sentence describing what the appointment is for,\n  used to build the call's `task`\n\nOptional: `region` (CALL-E region code, defaults to inferring from the\nphone country code if omitted — see `references\u002Fresult-schema.md`),\n`locale`, `business_name` (used in the call script), `metadata`\n(free-form, echoed back with the result).\n\n## Safety Rules\n\nRead `references\u002Fsafety.md` for the full contract. In short:\n\n- This skill places real phone calls with real consequences — never\n  run the batch without the user explicitly reviewing and approving\n  the dry-run list first.\n- Only call the phone numbers explicitly provided for this batch —\n  never a number pulled from an unrelated contact list or guessed.\n- Mask phone numbers in every user-facing summary (`+1415•••0101`);\n  the full number is only ever sent to CALL-E's API, never printed to\n  a log a bystander could read over someone's shoulder.\n- Do not fabricate a `confirmed` \u002F `declined` \u002F etc. result if CALL-E's\n  response doesn't clearly support it — report `unclear` and surface\n  the raw summary instead of guessing.\n- Do not retry a failed call automatically more than once per\n  recipient per run; repeated unwanted calls are a real-world harm,\n  not just a technical annoyance. If any call's outcome is ambiguous,\n  halt the whole batch rather than continuing — see\n  `references\u002Fsafety.md`.\n- Never expose the CALL-E API key in output, logs, or the results\n  file, and never send it to a CALL-E origin outside the script's\n  explicit allowlist even if `CALLE_BASE_URL` is overridden.\n- Treat any appointment context that reads as medical, legal, or\n  financial as logistics-only — the call confirms a time, it does not\n  discuss the underlying medical\u002Flegal\u002Ffinancial matter.\n- CALL-E does not currently expose a call-cancellation endpoint.\n  Stopping this script prevents further calls in the batch, but\n  cannot cancel a call already created — see the \"Cancellation\"\n  section of `references\u002Fsafety.md`.\n\n## Output Format\n\nAfter a batch run, report per recipient:\n\n- masked phone, appointment time, and CALL-E `call_id`\n- final status: `confirmed` \u002F `needs_reschedule` (with the requested\n  new time, if any) \u002F `declined` \u002F `no_answer` \u002F `voicemail` \u002F\n  `unclear` \u002F `failed` (with the rejection reason)\n\nAnd a one-line batch summary: `N confirmed, N to reschedule, N\ndeclined, N no answer, N failed` — so a business can act on the\nexceptions first instead of re-reading every row.\n\nNever state a call was completed unless CALL-E's own status for that\n`call_id` reached a terminal state.\n\n## Files\n\n- `scripts\u002Fplace_confirmation_calls.py` — standalone runner: reads a\n  CSV\u002FJSON batch, dry-runs it (stdlib only, no install needed), then\n  requires both `--confirm` and `--authorized-numbers` to place real\n  calls through CALL-E's Developer API with the shared\n  `result_schema`, polls to completion, halts the whole batch on any\n  ambiguous outcome, and writes a results CSV.\n- `requirements.txt` — the one dependency (`requests`) needed only\n  for live calls; dry-run needs nothing beyond it being present in\n  the repo so `--confirm` runs can install it.\n- `assets\u002Fauthorized_numbers.example.txt` — format reference for the\n  required `--authorized-numbers` file; copy it, don't commit your\n  real one.\n- `references\u002Fresult-schema.md` — the exact `result_schema` sent to\n  CALL-E and how each field maps to the output above.\n- `references\u002Fsafety.md` — the full safety contract this skill\n  follows, aligned with this repository's repo-wide safety patterns,\n  including the authorization gate, halt-on-ambiguity behavior, and\n  CALL-E's current lack of a cancellation endpoint.\n",{"name":5,"license":15,"description":7},"master","8c91ae30409640de28e218b3e9c7fe01c01d257b","skills\u002Fappointment-call-confirm","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 appointment-call-confirm",{"tool":38,"command":39},"bunx","bunx skills add fozagtx\u002FBuildOS-workflow --skill appointment-call-confirm",{"tool":41,"command":42},"pnpm","pnpm dlx skills add fozagtx\u002FBuildOS-workflow --skill appointment-call-confirm","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fappointment-call-confirm\u002FSKILL.md",true,[46,52,56,62,66,70,74,80],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"assets\u002Fauthorized_numbers.example.txt","ASSET","资产文件",304,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fappointment-call-confirm\u002Fassets\u002Fauthorized_numbers.example.txt",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"assets\u002Fsample_appointments.csv",151,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fappointment-call-confirm\u002Fassets\u002Fsample_appointments.csv",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fexamples.md","REFERENCE","参考文档",4241,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fappointment-call-confirm\u002Freferences\u002Fexamples.md",{"path":63,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fresult-schema.md",2130,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fappointment-call-confirm\u002Freferences\u002Fresult-schema.md",{"path":67,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fsafety.md",5655,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fappointment-call-confirm\u002Freferences\u002Fsafety.md",{"path":71,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":72,"sourceHtmlUrl":73},"requirements.txt",18,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fappointment-call-confirm\u002Frequirements.txt",{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"scripts\u002Fplace_confirmation_calls.py","SCRIPT","脚本",21921,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fappointment-call-confirm\u002Fscripts\u002Fplace_confirmation_calls.py",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"scripts\u002Ftest_place_confirmation_calls.py",1604,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fappointment-call-confirm\u002Fscripts\u002Ftest_place_confirmation_calls.py",[85,92,99,106,113,122],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"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":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":117,"licenseFileUrl":118,"sourceHtmlUrl":119,"categories":120,"keywords":121,"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":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"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",[],[]]