[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ECTZX3NBVTG58CJTK5GRG6":3,"skill-same:01M7ECTZX3NBVTG58CJTK5GRG6":60},{"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},"01M7ECTZX3NBVTG58CJTK5GRG6","mobilize",null,"Get a required number of confirmed responses from a consented pool of people within a deadline by calling multiple candidates in parallel waves via CALL-E, stopping as soon as the need is met. Use for urgent mobilization tasks like \"find 3 donors in the next hour\" or \"get 2 volunteers by 5pm\" from a registry of people who opted in to be contacted.","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\u002Fmobilize\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: mobilize\ndescription: Get a required number of confirmed responses from a consented pool of people within a deadline by calling multiple candidates in parallel waves via CALL-E, stopping as soon as the need is met. Use for urgent mobilization tasks like \"find 3 donors in the next hour\" or \"get 2 volunteers by 5pm\" from a registry of people who opted in to be contacted.\nlicense: MIT\n---\n\n# Mobilize\n\nUse this skill when the user needs a specific number of confirmed people from\nan existing, consented pool, under a deadline -- not one call, and not a\ncold-outreach campaign. `mobilize` wraps the `mobilize\u002F` engine in this\nrepository (parallel wave dispatch, commitment calibration, a crash-safe\nledger) so an agent can trigger a real mobilization without reimplementing\nany of it.\n\n## When To Use\n\nUse this skill for:\n\n- \"I need N people to do X by \u003Cdeadline>\" from a registry, roster, or list\n  of people who already agreed to be contacted for this purpose\n- urgent staffing, donor, or volunteer mobilization\n- any task where calling candidates one at a time is clearly too slow and\n  the pool is large enough that parallel dispatch matters\n\n## When Not To Use\n\nDo not use this skill to:\n\n- cold-call people who have not consented to being contacted for this\n  purpose -- `mobilize` assumes the pool is a consented registry; it is not\n  a lead-generation or cold-outreach tool\n- place a single one-off call (use CALL-E directly for that)\n- guess phone numbers, need counts, or deadlines the user did not provide\n- run `mobilize_real` calls without the user's explicit confirmation that\n  the phone numbers are real, owned, or authorized contacts\n\n## Core Workflow\n\n1. Confirm the pool is consented (the user should say so explicitly, e.g.\n   \"call our registered donors\" or \"text the on-call rotation\").\n2. Extract required fields: `need_label` (what you're asking), `count` (how\n   many confirmations needed), `deadline_minutes`, and the phone numbers or\n   pool source.\n3. If no real phone numbers exist yet, or the user wants to see the engine\n   work first, run the **simulated** path (`mobilize_simulated` via the MCP\n   server, or `python -m mobilize.app.cli`) -- zero cost, instant, safe to\n   run freely.\n4. Only call `mobilize_real` (or `python -m mobilize.app.cli --real`) when\n   the user has explicitly confirmed the phone numbers and wants to spend\n   real CALL-E call credits. Never pass more numbers than the user\n   explicitly provided.\n5. Report the result: filled or not, how many confirmed, how many calls\n   used, and time to fill.\n\n## Why Wave Dispatch, Not \"Cancel and Retry\"\n\nCALL-E's API has no operation to cancel an in-flight call (verified against\nthe CALL-E OpenAPI spec). `mobilize` therefore dispatches in **waves**: size\nthe first wave using each candidate's prior likelihood of confirming, wait\nfor results, and only dispatch a further wave if the need is still unmet.\nOnce the need is met, no further wave is ever dispatched -- calls already in\nflight are allowed to finish, but nobody new is ever called. Do not describe\nthis as \"cancelling calls.\"\n\n## Why a Stated \"Yes\" Is Not a Confirmation\n\nPeople say yes to be agreeable and then don't follow through (acquiescence\nbias). `mobilize`'s reconciler scores commitment from the call's evidence\ntext -- firm language (\"leaving now\") scores higher than hedged language\n(\"I'll try\") -- blended with the candidate's historical show-up rate. Only\nresponses above the commitment threshold count toward the need. See\n`references\u002Fcommitment-model.md` for the scoring detail, and\n`mobilize\u002Fsim\u002Fharness.py` in this repo for the measured accuracy gain over\ntreating every stated yes as confirmed.\n\n## Safety Rules\n\nRead `references\u002Fsafety.md` for the full safety contract used by the\ngovernance module (`mobilize\u002Fcore\u002Fpolicy.py`). Always follow these rules:\n\n- Every call must disclose it is an AI at the start (enforced in the task\n  prompt sent to CALL-E).\n- Never call anyone on the do-not-call list, in cooldown, or over the\n  contact-fatigue limit for the configured window -- the governance module\n  enforces this before dispatch, not after.\n- Respect configured calling-hour windows unless the need is explicitly\n  marked as an emergency override, and log every override.\n- Never dispatch to a larger pool than the user explicitly authorized.\n- If CALLE_API_KEY is missing or the user has not confirmed real numbers,\n  stop and use the simulated path instead of guessing.\n\n## Output Format\n\nReport:\n\n- `filled`: whether the need was met\n- `confirmed_count` \u002F `count` needed\n- `calls_used` and `waves_dispatched`\n- `time_to_fill_seconds` if filled\n- for each confirmed candidate: outcome and commitment score\n\nIf not filled, report the blocker (pool exhausted, call budget hit, or\ndeadline) and never claim the need was met unless `filled` is true.\n","# Mobilize\n\nUse this skill when the user needs a specific number of confirmed people from\nan existing, consented pool, under a deadline -- not one call, and not a\ncold-outreach campaign. `mobilize` wraps the `mobilize\u002F` engine in this\nrepository (parallel wave dispatch, commitment calibration, a crash-safe\nledger) so an agent can trigger a real mobilization without reimplementing\nany of it.\n\n## When To Use\n\nUse this skill for:\n\n- \"I need N people to do X by \u003Cdeadline>\" from a registry, roster, or list\n  of people who already agreed to be contacted for this purpose\n- urgent staffing, donor, or volunteer mobilization\n- any task where calling candidates one at a time is clearly too slow and\n  the pool is large enough that parallel dispatch matters\n\n## When Not To Use\n\nDo not use this skill to:\n\n- cold-call people who have not consented to being contacted for this\n  purpose -- `mobilize` assumes the pool is a consented registry; it is not\n  a lead-generation or cold-outreach tool\n- place a single one-off call (use CALL-E directly for that)\n- guess phone numbers, need counts, or deadlines the user did not provide\n- run `mobilize_real` calls without the user's explicit confirmation that\n  the phone numbers are real, owned, or authorized contacts\n\n## Core Workflow\n\n1. Confirm the pool is consented (the user should say so explicitly, e.g.\n   \"call our registered donors\" or \"text the on-call rotation\").\n2. Extract required fields: `need_label` (what you're asking), `count` (how\n   many confirmations needed), `deadline_minutes`, and the phone numbers or\n   pool source.\n3. If no real phone numbers exist yet, or the user wants to see the engine\n   work first, run the **simulated** path (`mobilize_simulated` via the MCP\n   server, or `python -m mobilize.app.cli`) -- zero cost, instant, safe to\n   run freely.\n4. Only call `mobilize_real` (or `python -m mobilize.app.cli --real`) when\n   the user has explicitly confirmed the phone numbers and wants to spend\n   real CALL-E call credits. Never pass more numbers than the user\n   explicitly provided.\n5. Report the result: filled or not, how many confirmed, how many calls\n   used, and time to fill.\n\n## Why Wave Dispatch, Not \"Cancel and Retry\"\n\nCALL-E's API has no operation to cancel an in-flight call (verified against\nthe CALL-E OpenAPI spec). `mobilize` therefore dispatches in **waves**: size\nthe first wave using each candidate's prior likelihood of confirming, wait\nfor results, and only dispatch a further wave if the need is still unmet.\nOnce the need is met, no further wave is ever dispatched -- calls already in\nflight are allowed to finish, but nobody new is ever called. Do not describe\nthis as \"cancelling calls.\"\n\n## Why a Stated \"Yes\" Is Not a Confirmation\n\nPeople say yes to be agreeable and then don't follow through (acquiescence\nbias). `mobilize`'s reconciler scores commitment from the call's evidence\ntext -- firm language (\"leaving now\") scores higher than hedged language\n(\"I'll try\") -- blended with the candidate's historical show-up rate. Only\nresponses above the commitment threshold count toward the need. See\n`references\u002Fcommitment-model.md` for the scoring detail, and\n`mobilize\u002Fsim\u002Fharness.py` in this repo for the measured accuracy gain over\ntreating every stated yes as confirmed.\n\n## Safety Rules\n\nRead `references\u002Fsafety.md` for the full safety contract used by the\ngovernance module (`mobilize\u002Fcore\u002Fpolicy.py`). Always follow these rules:\n\n- Every call must disclose it is an AI at the start (enforced in the task\n  prompt sent to CALL-E).\n- Never call anyone on the do-not-call list, in cooldown, or over the\n  contact-fatigue limit for the configured window -- the governance module\n  enforces this before dispatch, not after.\n- Respect configured calling-hour windows unless the need is explicitly\n  marked as an emergency override, and log every override.\n- Never dispatch to a larger pool than the user explicitly authorized.\n- If CALLE_API_KEY is missing or the user has not confirmed real numbers,\n  stop and use the simulated path instead of guessing.\n\n## Output Format\n\nReport:\n\n- `filled`: whether the need was met\n- `confirmed_count` \u002F `count` needed\n- `calls_used` and `waves_dispatched`\n- `time_to_fill_seconds` if filled\n- for each confirmed candidate: outcome and commitment score\n\nIf not filled, report the blocker (pool exhausted, call budget hit, or\ndeadline) and never claim the need was met unless `filled` is true.\n",{"name":5,"license":15,"description":7},"master","8c91ae30409640de28e218b3e9c7fe01c01d257b","skills\u002Fmobilize","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 mobilize",{"tool":38,"command":39},"bunx","bunx skills add fozagtx\u002FBuildOS-workflow --skill mobilize",{"tool":41,"command":42},"pnpm","pnpm dlx skills add fozagtx\u002FBuildOS-workflow --skill mobilize","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fmobilize\u002FSKILL.md",true,[46,52,56],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fcommitment-model.md","REFERENCE","参考文档",2096,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fmobilize\u002Freferences\u002Fcommitment-model.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fexamples.md",3268,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fmobilize\u002Freferences\u002Fexamples.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fsafety.md",1926,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fmobilize\u002Freferences\u002Fsafety.md",[61,68,75,82,89,98],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"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":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":93,"licenseFileUrl":94,"sourceHtmlUrl":95,"categories":96,"keywords":97,"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"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",[],[]]