[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BKJNJ2XPVRDG206ZV8VJGC":3,"skill-same:01M7BKJNJ2XPVRDG206ZV8VJGC":70},{"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":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7BKJNJ2XPVRDG206ZV8VJGC","demo-day",null,"Prepare a feature-review demo for a demo day — a story planned with the user, demo script, setup scenarios that seed the environment and print test data and users, a rehearsal recording each feature's demonstrability, and polished demo videos.","BetoFrega\u002Fskills","BetoFrega","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F637874?v=4","01M7BKHP444BSK41T281GQDPM7","Beto Frega","01M7BKHP5863T6EC03B63D0Q4T",0,"MIT","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdemo-day\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: demo-day\ndescription: Prepare a feature-review demo for a demo day — a story planned with the user, demo script, setup scenarios that seed the environment and print test data and users, a rehearsal recording each feature's demonstrability, and polished demo videos.\n---\n\n# Demo day\n\nRead [beto-mode](..\u002Fbeto-mode\u002FSKILL.md) first and apply the principles it routes to;\nname each principle that changed a choice. Global rules keep authority over decisions\nand permissions.\n\nThe invocation authorizes the demo artifacts below: scenarios, setup, demo script,\nrehearsal report, and demo videos. Product code, shared environments, and tracker writes beyond\nthe verdict comment need their own authority.\n\n## 1. Select features\n\nThe user names the features. For each, find its work item or PR and read the draft\ndemo script from its validation section (see\n[plan-increment](..\u002Fplan-increment\u002FSKILL.md)), acceptance, and references. Without a\ndraft, reconstruct the steps from the work item, PR, and code, and mark them as\ninferred per [Separate Documented From Inferred](..\u002Fbeto-mode\u002Fprinciples\u002Fseparate-documented-from-inferred.md).\n\nResolve the records location: an existing project convention or configured product\ndocumentation; otherwise ask, defaulting to `docs\u002Fdemos\u002F\u003CYYYY-MM-DD>\u002F`. Record the\nchosen convention in the project's agent-skills entry so later demo days reuse it.\n\n## 2. Plan the story with the user\n\nBefore building anything, agree on the demo's story with the user through\n[grilling](..\u002Fgrilling\u002FSKILL.md). Open with one drafted proposal they can correct,\none line per item, drafted from what step 1 read. Mark each guess. Guess where a\nwrong guess is cheap to correct (time budget, cast); ask where the answer would\nreshape the proposal (usually the audience). Put the first such question after the\nproposal, and continue the remaining ones as grilling rounds. The proposal is\ngrilling's opening plan; its topics, progress counts, and session tree cover only the\nquestions that stay open. The proposal covers:\n\n- **Audience:** who watches, what they should leave believing, and the time budget.\n  It sets how much theatre fits.\n- **Per feature:** the problem and before\u002Fafter; the key moment, the screen the\n  audience came to see; the cut, which steps appear and which become starting state;\n  the cast and data, the people, companies, and numbers that tell the story.\n- **Order** of the features and how one leads into the next, when there are several.\n\nName what step 1 found that limits the story, such as a \"before\" that can no longer\nbe shown, and how the cut handles it. A suspected product defect waits for step 5's\nclassification.\n\nRecord the settled answers in the demo script's Audience section and each feature's\nKey moment and Cast lines. The scenarios in step 3 seed exactly that cast and data.\n\n## 3. Build setup scenarios\n\nTarget the local environment. Use staging or another shared environment only when\nthe user names it for this demo day; then isolate demo data under a per-demo marker,\nprovide a cleanup command, and keep credentials out of tracked files and output\nrecords ([Security by Design](..\u002Fbeto-mode\u002Fprinciples\u002Fsecurity-by-design.md)).\n\nGive each feature a reusable, idempotent scenario, versioned in the project and built\non its existing seed, factories, or fixtures. Extend that tooling before adding a new\nmechanism; when the project has no seed entry point, add the smallest one the\nscenarios need. Compose the demo day's setup from the scenarios: one command that\nbrings the environment to the demo state and prints what the presenter needs — URLs,\ntest users and credentials, record identifiers, and the state each feature starts in.\n\n## 4. Write the demo script\n\nFill [the demo script template](assets\u002Fdemo-script-template.md) per feature: the\nproblem, the before\u002Fafter, the observable steps on the audience-facing interface,\nwhat each step shows, and the reset or recovery for a step that goes wrong. Keep the\norder, cut, and key moments agreed in step 2, and estimate each feature's time.\n\n## 5. Rehearse\n\nRun the setup from a clean state, then perform every step through the interface the\naudience will see: drive UI with Playwright and capture a screenshot per step; use a\nCLI or API only when that is the feature's own interface. When the audience-facing\ninterface cannot be driven here, the feature is not demonstrable; record exactly what\nblocked it.\n\nOn a failed step, classify the cause per [Fix Root Causes](..\u002Fbeto-mode\u002Fprinciples\u002Ffix-root-causes.md):\n\n- **Demo artifact** (scenario, setup, script): fix it and rehearse the feature again\n  from a clean setup.\n- **Product defect**: stop that feature, mark it not demonstrable, record the\n  diagnosis and evidence, and bring a proposed fix to the user. Change product code\n  only after their decision.\n\nAssign each feature a verdict — **demonstrable**, **demonstrable with caveats**, or\n**not demonstrable** — supported by the rehearsal evidence\n([Evidence Before Claims](..\u002Fbeto-mode\u002Fprinciples\u002Fevidence-before-claims.md)).\n\n## 6. Record videos\n\nWhen the user asks for videos, record each demonstrable feature after its rehearsal\npasses, following [recording](references\u002Frecording.md).\n\n1. **Plan the staging.** Propose each step's staging over its rehearsal screenshot,\n   in the same proposal-then-questions shape as step 2: captions and their text, which moment\n   gets spotlight, zoom, or suspense, the motion style, chapter titles, and the\n   cursor's acting: its entrance and exit and the expression at each turn of the\n   story. Be bold on the key moment and brisk elsewhere. Record the answers in the\n   Staging column.\n2. **Record** from a clean setup, following the Staging column, and check the frames.\n3. **Get approval.** Send each video and ask for direction notes. Turn each note into\n   a Staging change and record that feature again. A video is done only when the user\n   approves it ([Evidence Before Claims](..\u002Fbeto-mode\u002Fprinciples\u002Fevidence-before-claims.md));\n   until then the report marks it awaiting approval.\n\n## 7. Record and report\n\nSave the filled template in the demo day's folder as the demo script and rehearsal\nreport: each step's result, evidence links, timing, verdict, and video link with its\napproval state. Record only the\nverdict and a link to the report in each feature's canonical work item or record\n([One Canonical Record](..\u002Fbeto-mode\u002Fprinciples\u002Fone-canonical-record.md)); features\nknown only by PR keep the report alone.\n\nComplete when every named feature has a verdict backed by a rehearsal from a clean\nsetup, the setup command reproduces the demo state, each requested video is approved\nby the user, and each pending product decision is presented to the user. Report the verdicts, the setup command and its\noutput, the pending decisions, and the\n[delivery state](..\u002Fconsolidate\u002Freferences\u002Flocal-document-delivery.md) of the\nversioned scenarios and records.\n","# Demo day\n\nRead [beto-mode](..\u002Fbeto-mode\u002FSKILL.md) first and apply the principles it routes to;\nname each principle that changed a choice. Global rules keep authority over decisions\nand permissions.\n\nThe invocation authorizes the demo artifacts below: scenarios, setup, demo script,\nrehearsal report, and demo videos. Product code, shared environments, and tracker writes beyond\nthe verdict comment need their own authority.\n\n## 1. Select features\n\nThe user names the features. For each, find its work item or PR and read the draft\ndemo script from its validation section (see\n[plan-increment](..\u002Fplan-increment\u002FSKILL.md)), acceptance, and references. Without a\ndraft, reconstruct the steps from the work item, PR, and code, and mark them as\ninferred per [Separate Documented From Inferred](..\u002Fbeto-mode\u002Fprinciples\u002Fseparate-documented-from-inferred.md).\n\nResolve the records location: an existing project convention or configured product\ndocumentation; otherwise ask, defaulting to `docs\u002Fdemos\u002F\u003CYYYY-MM-DD>\u002F`. Record the\nchosen convention in the project's agent-skills entry so later demo days reuse it.\n\n## 2. Plan the story with the user\n\nBefore building anything, agree on the demo's story with the user through\n[grilling](..\u002Fgrilling\u002FSKILL.md). Open with one drafted proposal they can correct,\none line per item, drafted from what step 1 read. Mark each guess. Guess where a\nwrong guess is cheap to correct (time budget, cast); ask where the answer would\nreshape the proposal (usually the audience). Put the first such question after the\nproposal, and continue the remaining ones as grilling rounds. The proposal is\ngrilling's opening plan; its topics, progress counts, and session tree cover only the\nquestions that stay open. The proposal covers:\n\n- **Audience:** who watches, what they should leave believing, and the time budget.\n  It sets how much theatre fits.\n- **Per feature:** the problem and before\u002Fafter; the key moment, the screen the\n  audience came to see; the cut, which steps appear and which become starting state;\n  the cast and data, the people, companies, and numbers that tell the story.\n- **Order** of the features and how one leads into the next, when there are several.\n\nName what step 1 found that limits the story, such as a \"before\" that can no longer\nbe shown, and how the cut handles it. A suspected product defect waits for step 5's\nclassification.\n\nRecord the settled answers in the demo script's Audience section and each feature's\nKey moment and Cast lines. The scenarios in step 3 seed exactly that cast and data.\n\n## 3. Build setup scenarios\n\nTarget the local environment. Use staging or another shared environment only when\nthe user names it for this demo day; then isolate demo data under a per-demo marker,\nprovide a cleanup command, and keep credentials out of tracked files and output\nrecords ([Security by Design](..\u002Fbeto-mode\u002Fprinciples\u002Fsecurity-by-design.md)).\n\nGive each feature a reusable, idempotent scenario, versioned in the project and built\non its existing seed, factories, or fixtures. Extend that tooling before adding a new\nmechanism; when the project has no seed entry point, add the smallest one the\nscenarios need. Compose the demo day's setup from the scenarios: one command that\nbrings the environment to the demo state and prints what the presenter needs — URLs,\ntest users and credentials, record identifiers, and the state each feature starts in.\n\n## 4. Write the demo script\n\nFill [the demo script template](assets\u002Fdemo-script-template.md) per feature: the\nproblem, the before\u002Fafter, the observable steps on the audience-facing interface,\nwhat each step shows, and the reset or recovery for a step that goes wrong. Keep the\norder, cut, and key moments agreed in step 2, and estimate each feature's time.\n\n## 5. Rehearse\n\nRun the setup from a clean state, then perform every step through the interface the\naudience will see: drive UI with Playwright and capture a screenshot per step; use a\nCLI or API only when that is the feature's own interface. When the audience-facing\ninterface cannot be driven here, the feature is not demonstrable; record exactly what\nblocked it.\n\nOn a failed step, classify the cause per [Fix Root Causes](..\u002Fbeto-mode\u002Fprinciples\u002Ffix-root-causes.md):\n\n- **Demo artifact** (scenario, setup, script): fix it and rehearse the feature again\n  from a clean setup.\n- **Product defect**: stop that feature, mark it not demonstrable, record the\n  diagnosis and evidence, and bring a proposed fix to the user. Change product code\n  only after their decision.\n\nAssign each feature a verdict — **demonstrable**, **demonstrable with caveats**, or\n**not demonstrable** — supported by the rehearsal evidence\n([Evidence Before Claims](..\u002Fbeto-mode\u002Fprinciples\u002Fevidence-before-claims.md)).\n\n## 6. Record videos\n\nWhen the user asks for videos, record each demonstrable feature after its rehearsal\npasses, following [recording](references\u002Frecording.md).\n\n1. **Plan the staging.** Propose each step's staging over its rehearsal screenshot,\n   in the same proposal-then-questions shape as step 2: captions and their text, which moment\n   gets spotlight, zoom, or suspense, the motion style, chapter titles, and the\n   cursor's acting: its entrance and exit and the expression at each turn of the\n   story. Be bold on the key moment and brisk elsewhere. Record the answers in the\n   Staging column.\n2. **Record** from a clean setup, following the Staging column, and check the frames.\n3. **Get approval.** Send each video and ask for direction notes. Turn each note into\n   a Staging change and record that feature again. A video is done only when the user\n   approves it ([Evidence Before Claims](..\u002Fbeto-mode\u002Fprinciples\u002Fevidence-before-claims.md));\n   until then the report marks it awaiting approval.\n\n## 7. Record and report\n\nSave the filled template in the demo day's folder as the demo script and rehearsal\nreport: each step's result, evidence links, timing, verdict, and video link with its\napproval state. Record only the\nverdict and a link to the report in each feature's canonical work item or record\n([One Canonical Record](..\u002Fbeto-mode\u002Fprinciples\u002Fone-canonical-record.md)); features\nknown only by PR keep the report alone.\n\nComplete when every named feature has a verdict backed by a rehearsal from a clean\nsetup, the setup command reproduces the demo state, each requested video is approved\nby the user, and each pending product decision is presented to the user. Report the verdicts, the setup command and its\noutput, the pending decisions, and the\n[delivery state](..\u002Fconsolidate\u002Freferences\u002Flocal-document-delivery.md) of the\nversioned scenarios and records.\n",{"name":5,"description":7},"main","b212a89a4ff3d13380a0ee75a91d99ee0aad2858","skills\u002Fdemo-day","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills","https:\u002F\u002Fgithub.com\u002FBetoFrega","2026-11-14 02:43:03",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add BetoFrega\u002Fskills --skill demo-day",{"tool":36,"command":37},"bunx","bunx skills add BetoFrega\u002Fskills --skill demo-day",{"tool":39,"command":40},"pnpm","pnpm dlx skills add BetoFrega\u002Fskills --skill demo-day","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdemo-day\u002FSKILL.md",true,[44,50,56,60,66],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"agents\u002Fopenai.yaml","REFERENCE","参考文档",147,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdemo-day\u002Fagents\u002Fopenai.yaml",{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"assets\u002Fdemo-script-template.md","ASSET","资产文件",1116,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdemo-day\u002Fassets\u002Fdemo-script-template.md",{"path":57,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frecording.md",6063,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdemo-day\u002Freferences\u002Frecording.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Ffinish-recording.mjs","SCRIPT","脚本",5799,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdemo-day\u002Fscripts\u002Ffinish-recording.mjs",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Frecorder.mjs",43435,"https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdemo-day\u002Fscripts\u002Frecorder.mjs",[71,78,86,93,101,108],{"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},"01M7BKPW918QFBHANWQRR8JXTA","writing-for-humans","Load before writing any reader-facing text, including messages, and follow its rules as you write. Also use to rewrite or audit existing prose for plain language, clarity, readability, or actionability.","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-for-humans\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":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7BKPSYAK48C7RBZXKQN805M","writing-for-agents","Write agent-facing documents. Use when creating or editing skills, AGENTS.md, or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-for-agents\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7BKPQG1ZNVYYJVSGE69V5DZ","write-adr","Write, revise, or supersede architecture decision records (ADRs) documenting an architectural choice and its rationale.","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-adr\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7BKPMZC59QZ0G1746SCZ3S4","wizard","Wizard scripts for human-only provisioning, credential\u002FCI setup, unfamiliar dashboards, migrations, or cutovers; use only for steps the agent cannot perform.","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwizard\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwizard\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},"01M7BKPHD7Y6X4BM9SV06PNKAC","verify","Check whether the current task's claimed outcome is confirmed.","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fverify\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M7BKPESBZ2WZYN1EWK6SGB67","verb-tense","Choose verb tense and mood by when each event happens and how certain it is. Use when writing or reviewing any text, and when a reader asks for a tense review.","https:\u002F\u002Fgithub.com\u002FBetoFrega\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fverb-tense\u002FSKILL.md",[],[]]