[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EB3C33QWXW3ZPBF8WMCQE1":3,"skill-same:01M7EB3C33QWXW3ZPBF8WMCQE1":56},{"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},"01M7EB3C33QWXW3ZPBF8WMCQE1","call-rehearsal",null,"Rehearse a phone call plan against every realistic ending of the call before dialling anyone, and refuse a plan whose automation acts on a call that never reached a consenting human.","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\u002Fcall-rehearsal\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: call-rehearsal\ndescription: Rehearse a phone call plan against every realistic ending of the call before dialling anyone, and refuse a plan whose automation acts on a call that never reached a consenting human.\nlicense: MIT\n---\n\n# Call Rehearsal\n\nA CALL-E call returns a structured result, and something downstream acts on it.\nThe dangerous failure is not a call that fails loudly. It is a call that never\nreached a consenting human whose result still resolves to the branch that ships\nthe order.\n\nThat happens because an unestablished field is absent, and absent is falsy. A\nrule as ordinary as `confirmed != false` is true when voicemail picked up and\nnothing at all was extracted.\n\nThis skill covers finding that before the call, by rehearsing the plan against\nthe ways calls actually end.\n\n## When to use it\n\nUse it before the first real call of any workflow whose result triggers a\nreal-world side effect: dispatching, shipping, charging, cancelling, granting\naccess, or writing a confirmation into a system of record. Use it again whenever\nthe `task`, the `result_schema`, or the rule that reads the result changes, since\nthis failure is introduced by editing any one of the three without the others.\n\nSkip it for a call whose result nobody acts on automatically. A call that only\nproduces a note for a human to read has no branch to get wrong.\n\n## The procedure\n\n1. **Name the single decision.** Write down the one thing the call exists to\n   establish. If there seem to be several, the call is doing too much and the\n   rehearsal will show the decision field carrying weight it cannot hold.\n2. **Write the call plan.** One JSON file with the `task`, the `result_schema`,\n   the `fields` roles, and the `decision_rule` including what each branch does\n   and whether it changes the real world.\n3. **Declare the field roles.** Map result fields onto `decision`,\n   `reachability`, `consent`, `identity` and `deferral`. Only `decision` is\n   required. Do not guess a role: if you cannot say which field carries the\n   decision, ask the person who owns the workflow.\n4. **Rehearse.** Run the plan and read what the automation does for each ending.\n5. **Gate on the exit code.** `0` means no ending above the threshold reaches a\n   side effect, `20` means the plan should not go out as written, `30` means the\n   plan could not be read.\n\n```bash\ncd apps\u002Fpython\u002Fcall-rehearsal\npython3 -m callrehearsal \u003Cplan.json> --fail-on high\n```\n\nNo call is placed, no credential is read, and nothing connects to the network,\nso rehearsing is always safe, including in CI on every commit.\n\n## Reading the result\n\nEvery ending that is not a verified, consenting yes must land on a branch with\n`side_effect: false`. A `CRITICAL` finding means one did not.\n\nThe two fixes that resolve almost every report:\n\n- **Record what happened on the line.** Add fields for reachability, identity\n  and consent, so voicemail is distinguishable from a refusal and a stranger\n  saying yes is distinguishable from the callee saying yes.\n- **Require a confirmation, not the absence of a refusal.** Replace\n  `confirmed != false` with `confirmed == true`, and conjoin the identity and\n  consent fields.\n\nRead `references\u002Fexamples.md` for a worked before-and-after, and\n`references\u002Fsafety.md` for the rules about what may follow a call.\n\n## What this does not do\n\nIt reasons about the shape of the result, not the words spoken. It cannot tell\nyou whether the phrasing is persuasive or whether extraction is reliable on a\nlive line. Use `calle-script-advisor` for the task text and schema, and\n`voice-preflight` for what the critical lines sound like when spoken. A clean\nrehearsal means the plan survives the endings in the library, which is not a\nguarantee about any individual real call.\n","# Call Rehearsal\n\nA CALL-E call returns a structured result, and something downstream acts on it.\nThe dangerous failure is not a call that fails loudly. It is a call that never\nreached a consenting human whose result still resolves to the branch that ships\nthe order.\n\nThat happens because an unestablished field is absent, and absent is falsy. A\nrule as ordinary as `confirmed != false` is true when voicemail picked up and\nnothing at all was extracted.\n\nThis skill covers finding that before the call, by rehearsing the plan against\nthe ways calls actually end.\n\n## When to use it\n\nUse it before the first real call of any workflow whose result triggers a\nreal-world side effect: dispatching, shipping, charging, cancelling, granting\naccess, or writing a confirmation into a system of record. Use it again whenever\nthe `task`, the `result_schema`, or the rule that reads the result changes, since\nthis failure is introduced by editing any one of the three without the others.\n\nSkip it for a call whose result nobody acts on automatically. A call that only\nproduces a note for a human to read has no branch to get wrong.\n\n## The procedure\n\n1. **Name the single decision.** Write down the one thing the call exists to\n   establish. If there seem to be several, the call is doing too much and the\n   rehearsal will show the decision field carrying weight it cannot hold.\n2. **Write the call plan.** One JSON file with the `task`, the `result_schema`,\n   the `fields` roles, and the `decision_rule` including what each branch does\n   and whether it changes the real world.\n3. **Declare the field roles.** Map result fields onto `decision`,\n   `reachability`, `consent`, `identity` and `deferral`. Only `decision` is\n   required. Do not guess a role: if you cannot say which field carries the\n   decision, ask the person who owns the workflow.\n4. **Rehearse.** Run the plan and read what the automation does for each ending.\n5. **Gate on the exit code.** `0` means no ending above the threshold reaches a\n   side effect, `20` means the plan should not go out as written, `30` means the\n   plan could not be read.\n\n```bash\ncd apps\u002Fpython\u002Fcall-rehearsal\npython3 -m callrehearsal \u003Cplan.json> --fail-on high\n```\n\nNo call is placed, no credential is read, and nothing connects to the network,\nso rehearsing is always safe, including in CI on every commit.\n\n## Reading the result\n\nEvery ending that is not a verified, consenting yes must land on a branch with\n`side_effect: false`. A `CRITICAL` finding means one did not.\n\nThe two fixes that resolve almost every report:\n\n- **Record what happened on the line.** Add fields for reachability, identity\n  and consent, so voicemail is distinguishable from a refusal and a stranger\n  saying yes is distinguishable from the callee saying yes.\n- **Require a confirmation, not the absence of a refusal.** Replace\n  `confirmed != false` with `confirmed == true`, and conjoin the identity and\n  consent fields.\n\nRead `references\u002Fexamples.md` for a worked before-and-after, and\n`references\u002Fsafety.md` for the rules about what may follow a call.\n\n## What this does not do\n\nIt reasons about the shape of the result, not the words spoken. It cannot tell\nyou whether the phrasing is persuasive or whether extraction is reliable on a\nlive line. Use `calle-script-advisor` for the task text and schema, and\n`voice-preflight` for what the critical lines sound like when spoken. A clean\nrehearsal means the plan survives the endings in the library, which is not a\nguarantee about any individual real call.\n",{"name":5,"license":15,"description":7},"master","8c91ae30409640de28e218b3e9c7fe01c01d257b","skills\u002Fcall-rehearsal","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 call-rehearsal",{"tool":38,"command":39},"bunx","bunx skills add fozagtx\u002FBuildOS-workflow --skill call-rehearsal",{"tool":41,"command":42},"pnpm","pnpm dlx skills add fozagtx\u002FBuildOS-workflow --skill call-rehearsal","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fcall-rehearsal\u002FSKILL.md",true,[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fexamples.md","REFERENCE","参考文档",3408,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fcall-rehearsal\u002Freferences\u002Fexamples.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fsafety.md",2735,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fcall-rehearsal\u002Freferences\u002Fsafety.md",[57,64,71,78,85,94],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"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":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":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},"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",[],[]]