[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6J4NFBXTGG0R4M484T0KNYW":3,"skill-same:01M6J4NFBXTGG0R4M484T0KNYW":80},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":61,"ownerHtmlUrl":62,"ownerBlogUrl":63,"ownerDescription":64,"updatedAt":65,"install":66,"resources":79},"01M6J4NFBXTGG0R4M484T0KNYW","video-script",null,"Turn a repo, product page, or update into a recording-ready video script in a receipts-first format - verifies every claim against live sources, then writes timestamped VO + on-screen direction with a plain-language glossary, assets checklist, anti-tells, and a verify-before-recording list","MiroShark\u002Fmiroshark-aeon","MiroShark","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F304594232?v=4","01M6J466B8NNAZ4H6NNK3N3TT5","01M6J466FXNNWH622S3B9PC496",20,"MIT","https:\u002F\u002Fgithub.com\u002FMiroShark\u002Fmiroshark-aeon\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-script\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"video script","script","Video","receipts","live","list","format","update","screen","product","verify","first","with","glossary","plain-language","claim","basics","repo","page","direction","ready","sources","recording","2026-11-10 10:12:30",false,"---\nname: video-script\ndescription: Turn a repo, product page, or update into a recording-ready video script in a receipts-first format - verifies every claim against live sources, then writes timestamped VO + on-screen direction with a plain-language glossary, assets checklist, anti-tells, and a verify-before-recording list\nmetadata:\n  title: Video Script\n  category: basics\n  var: \"\"\n  tags:\n    - content\n---\n\n> **${var}** — Selector: `\u003Csource> [--minutes N]`.\n>\n> - **`repo:\u003Cowner\u002Frepo>`** → script about that repo's latest update wave (README + recent releases\u002Fcommits decide what \"the update\" is).\n> - **`\u003Curl>`** → script about that product page \u002F doc \u002F announcement.\n> - **`\u003Ctopic>`** (anything else non-empty) → script about that topic; research it first.\n> - **empty** → pick the most script-worthy update from the last 7 days of `memory\u002Flogs\u002F` (a shipped feature, a release, a milestone with receipts). If nothing qualifies, log `VIDEO_SCRIPT_NO_SOURCE`, send no notification, and exit clean.\n> - **`--minutes N`** anywhere → runtime target (default 4; ~150 spoken words per minute).\n>\n> Examples: `\"repo:aeonfun\u002Faeon --minutes 6\"`, `\"https:\u002F\u002Fexample.com\u002Flaunch\"`, `\"our new payments integration --minutes 3\"`.\n\nToday is ${today}. Write a recording-ready video script. No placeholders — every number, address, and date in it must be verified this run.\n\n## Shared preamble\n\n1. Read `memory\u002FMEMORY.md` and the last 7 days of `memory\u002Flogs\u002F` — know what has already been covered, and don't script the same story twice.\n2. If a `soul\u002F` directory exists, read `soul\u002FSOUL.md` and `soul\u002FSTYLE.md` for voice calibration. The script is *the operator talking to a smart friend* — if `soul\u002F` is empty, default to terse, direct, first-person.\n3. Parse `${var}` per the selector above into `source` + `minutes`.\n\n## Step 1 — Research and verify (never skip)\n\nThe format is called receipts-first because the receipts are real:\n\n- Fetch the live source **now** (WebFetch \u002F `gh api` for repos — README **and** recent releases\u002Fcommits). Do not write numbers, counts, addresses, or dates from memory.\n- Collect concrete verifiable artifacts: contract addresses, live dashboards, version numbers, dollar figures, dates. These become the cold open and the Receipts section.\n- Every claim you could NOT verify either gets cut or becomes a checkbox in \"Verify before recording\".\n\n## Step 2 — Find the angle\n\nThe cold open is never the pitch. It is the single most concrete, verifiable, surprising fact — shown, not claimed (a live dashboard, a list of on-chain addresses, a terminal). Test: could a skeptic check it in 30 seconds? The flex is usually the *credibility mechanism* (immutability, safety gates, audit trail, reproducible tests), not the feature list.\n\n## Step 3 — Write the script\n\nHeader block:\n\n```markdown\n# \u003Cproject> - \"\u003CWorking Title>\" - Video Script\n\n**Runtime target:** ~M:SS\n**Framing:** receipts-first (open on \u003Cthe artifact>)\n**Byline:** \u003Cthe project's public handle>\n**One-line pitch:** \u003Cone sentence, no hype>\n**Rev:** v1, ${today} - plain-language pass baked in; every technical term explained in one line or cut.\n```\n\nChapters, each with a time range:\n\n```markdown\n## \u003CChapter name> - 0:00 - 0:25\n\n**VO:**\n> Spoken text as blockquote. Short sentences. Operator voice.\n\n**On screen:**\n- Concrete shot list: screencaps, terminals, motion graphics, captions in `backticks`.\n```\n\nCanonical arc (adapt, don't force): **cold open** (the receipt, no greeting) → **context\u002Fproblem** (one plain-language line for the underlying tech) → **how it works** (the mechanism, credibility story first) → **what's new** or **the demo** → **straight talk** (limits, flat delivery — every script has this section; it is a feature, not a concession) → **close + CTA** (one action).\n\nAfter the chapters, ALWAYS:\n\n- **Plain-language glossary** — jargon → the phrasing used on screen, plus terms deliberately cut.\n- **Assets checklist** — everything to capture or build; mark what must be captured day-of.\n- **Anti-tells checklist** — the voice rules below plus per-video specifics (what not to oversell, whose failures not to dunk on).\n- **Verify before recording** — dated checkboxes for every volatile fact, each with where to re-check it.\n- **Receipts** — the verified facts with sources and the date verified (mandatory when the video makes on-chain or factual claims).\n\n## Voice rules (the anti-tells)\n\n- Banned: \"In this video\", \"Let's dive in\", \"game-changer\", \"insane\", \"mind-blowing\", \"revolutionary\", \"trustless\" (name what enforces it instead).\n- Short declaratives; read VO lines aloud mentally before keeping them.\n- Numbers stay conservative — round down; \"tens of millions\" beats a precise figure that might drift.\n- Incidents and competitors are stakes, not villains — flat delivery, no dunking.\n- The safety\u002Fverification story outranks the feature list.\n- Every technical term gets one plain-language line or gets cut.\n- On-screen text must NOT mirror the VO verbatim — reword it so the viewer isn't reading what they're hearing.\n- Never reference private forks or internal accounts — point at the upstream\u002Fpublic repo.\n\n## Step 4 — Deliver\n\n1. Write the script to `output\u002Fvideo-scripts\u002F${today}-\u003Cslug>.md` (shell redirection; `mkdir -p` first).\n2. Notify with `.\u002Fnotify -f \u002Ftmp\u002Fvideo-script-notify.md` (write the body under `\u002Ftmp\u002F`, never `memory\u002F` or `output\u002F`): the working title, runtime, the chosen angle in one line, one thing deliberately left out, and a **clickable** link to the script built from the run's environment:\n\n   ```bash\n   SCRIPT_URL=\"${GITHUB_SERVER_URL:-https:\u002F\u002Fgithub.com}\u002F${GITHUB_REPOSITORY}\u002Fblob\u002Fmain\u002Foutput\u002Fvideo-scripts\u002F\u003Cfile>.md\"\n   ```\n\n3. Log to `memory\u002Flogs\u002F${today}.md` under a `### video-script` heading: source, angle, runtime, output path, and any claims deferred to day-of verification. Status codes: `VIDEO_SCRIPT_OK` on success, `VIDEO_SCRIPT_NO_SOURCE` when `${var}` was empty and the logs offered nothing script-worthy.\n\n## Limits\n\n- This writes the script; it does not record, edit, or generate footage. The assets checklist is a to-do list for a human (or other skills).\n- Verification is only as fresh as this run — volatile facts must still be re-checked day-of; that is what the \"Verify before recording\" section is for.\n- If the source is private or unreachable, say so and stop — a script built on unverifiable claims defeats the format.\n","> **${var}** — Selector: `\u003Csource> [--minutes N]`.\n>\n> - **`repo:\u003Cowner\u002Frepo>`** → script about that repo's latest update wave (README + recent releases\u002Fcommits decide what \"the update\" is).\n> - **`\u003Curl>`** → script about that product page \u002F doc \u002F announcement.\n> - **`\u003Ctopic>`** (anything else non-empty) → script about that topic; research it first.\n> - **empty** → pick the most script-worthy update from the last 7 days of `memory\u002Flogs\u002F` (a shipped feature, a release, a milestone with receipts). If nothing qualifies, log `VIDEO_SCRIPT_NO_SOURCE`, send no notification, and exit clean.\n> - **`--minutes N`** anywhere → runtime target (default 4; ~150 spoken words per minute).\n>\n> Examples: `\"repo:aeonfun\u002Faeon --minutes 6\"`, `\"https:\u002F\u002Fexample.com\u002Flaunch\"`, `\"our new payments integration --minutes 3\"`.\n\nToday is ${today}. Write a recording-ready video script. No placeholders — every number, address, and date in it must be verified this run.\n\n## Shared preamble\n\n1. Read `memory\u002FMEMORY.md` and the last 7 days of `memory\u002Flogs\u002F` — know what has already been covered, and don't script the same story twice.\n2. If a `soul\u002F` directory exists, read `soul\u002FSOUL.md` and `soul\u002FSTYLE.md` for voice calibration. The script is *the operator talking to a smart friend* — if `soul\u002F` is empty, default to terse, direct, first-person.\n3. Parse `${var}` per the selector above into `source` + `minutes`.\n\n## Step 1 — Research and verify (never skip)\n\nThe format is called receipts-first because the receipts are real:\n\n- Fetch the live source **now** (WebFetch \u002F `gh api` for repos — README **and** recent releases\u002Fcommits). Do not write numbers, counts, addresses, or dates from memory.\n- Collect concrete verifiable artifacts: contract addresses, live dashboards, version numbers, dollar figures, dates. These become the cold open and the Receipts section.\n- Every claim you could NOT verify either gets cut or becomes a checkbox in \"Verify before recording\".\n\n## Step 2 — Find the angle\n\nThe cold open is never the pitch. It is the single most concrete, verifiable, surprising fact — shown, not claimed (a live dashboard, a list of on-chain addresses, a terminal). Test: could a skeptic check it in 30 seconds? The flex is usually the *credibility mechanism* (immutability, safety gates, audit trail, reproducible tests), not the feature list.\n\n## Step 3 — Write the script\n\nHeader block:\n\n```markdown\n# \u003Cproject> - \"\u003CWorking Title>\" - Video Script\n\n**Runtime target:** ~M:SS\n**Framing:** receipts-first (open on \u003Cthe artifact>)\n**Byline:** \u003Cthe project's public handle>\n**One-line pitch:** \u003Cone sentence, no hype>\n**Rev:** v1, ${today} - plain-language pass baked in; every technical term explained in one line or cut.\n```\n\nChapters, each with a time range:\n\n```markdown\n## \u003CChapter name> - 0:00 - 0:25\n\n**VO:**\n> Spoken text as blockquote. Short sentences. Operator voice.\n\n**On screen:**\n- Concrete shot list: screencaps, terminals, motion graphics, captions in `backticks`.\n```\n\nCanonical arc (adapt, don't force): **cold open** (the receipt, no greeting) → **context\u002Fproblem** (one plain-language line for the underlying tech) → **how it works** (the mechanism, credibility story first) → **what's new** or **the demo** → **straight talk** (limits, flat delivery — every script has this section; it is a feature, not a concession) → **close + CTA** (one action).\n\nAfter the chapters, ALWAYS:\n\n- **Plain-language glossary** — jargon → the phrasing used on screen, plus terms deliberately cut.\n- **Assets checklist** — everything to capture or build; mark what must be captured day-of.\n- **Anti-tells checklist** — the voice rules below plus per-video specifics (what not to oversell, whose failures not to dunk on).\n- **Verify before recording** — dated checkboxes for every volatile fact, each with where to re-check it.\n- **Receipts** — the verified facts with sources and the date verified (mandatory when the video makes on-chain or factual claims).\n\n## Voice rules (the anti-tells)\n\n- Banned: \"In this video\", \"Let's dive in\", \"game-changer\", \"insane\", \"mind-blowing\", \"revolutionary\", \"trustless\" (name what enforces it instead).\n- Short declaratives; read VO lines aloud mentally before keeping them.\n- Numbers stay conservative — round down; \"tens of millions\" beats a precise figure that might drift.\n- Incidents and competitors are stakes, not villains — flat delivery, no dunking.\n- The safety\u002Fverification story outranks the feature list.\n- Every technical term gets one plain-language line or gets cut.\n- On-screen text must NOT mirror the VO verbatim — reword it so the viewer isn't reading what they're hearing.\n- Never reference private forks or internal accounts — point at the upstream\u002Fpublic repo.\n\n## Step 4 — Deliver\n\n1. Write the script to `output\u002Fvideo-scripts\u002F${today}-\u003Cslug>.md` (shell redirection; `mkdir -p` first).\n2. Notify with `.\u002Fnotify -f \u002Ftmp\u002Fvideo-script-notify.md` (write the body under `\u002Ftmp\u002F`, never `memory\u002F` or `output\u002F`): the working title, runtime, the chosen angle in one line, one thing deliberately left out, and a **clickable** link to the script built from the run's environment:\n\n   ```bash\n   SCRIPT_URL=\"${GITHUB_SERVER_URL:-https:\u002F\u002Fgithub.com}\u002F${GITHUB_REPOSITORY}\u002Fblob\u002Fmain\u002Foutput\u002Fvideo-scripts\u002F\u003Cfile>.md\"\n   ```\n\n3. Log to `memory\u002Flogs\u002F${today}.md` under a `### video-script` heading: source, angle, runtime, output path, and any claims deferred to day-of verification. Status codes: `VIDEO_SCRIPT_OK` on success, `VIDEO_SCRIPT_NO_SOURCE` when `${var}` was empty and the logs offered nothing script-worthy.\n\n## Limits\n\n- This writes the script; it does not record, edit, or generate footage. The assets checklist is a to-do list for a human (or other skills).\n- Verification is only as fresh as this run — volatile facts must still be re-checked day-of; that is what the \"Verify before recording\" section is for.\n- If the source is private or unreachable, say so and stop — a script built on unverifiable claims defeats the format.\n",{"name":5,"metadata":51,"description":7},{"var":52,"tags":53,"title":55,"category":39},"",[54],"content","Video Script","main","9c042aa1b6d79fd49679637374e88c5874cc3aae","skills\u002Fvideo-script",2,"https:\u002F\u002Fgithub.com\u002FMiroShark\u002Fmiroshark-aeon","https:\u002F\u002Ft.me\u002Fmiroshark_aeon","https:\u002F\u002Fgithub.com\u002FMiroShark","https:\u002F\u002Fwww.miroshark.xyz\u002F","Simulate anything, for $1 & less than 10 min.","2026-11-14 00:33:09",{"source":8,"skillName":5,"commands":67,"prompt":77,"zipAvailable":78},[68,71,74],{"tool":69,"command":70},"npx","npx skills add MiroShark\u002Fmiroshark-aeon --skill video-script",{"tool":72,"command":73},"bunx","bunx skills add MiroShark\u002Fmiroshark-aeon --skill video-script",{"tool":75,"command":76},"pnpm","pnpm dlx skills add MiroShark\u002Fmiroshark-aeon --skill video-script","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMiroShark\u002Fmiroshark-aeon\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-script\u002FSKILL.md",true,[],[81,115,136,162,187,210],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":95,"publishedAt":46},"01M6J4P8XKB8RJ7PCYMZPZ0F6S","you-web-search","Web search using You.com Search API with high-quality, cited results — runs keyless out of the box; YDC_API_KEY unlocks higher limits and real-time web crawling","https:\u002F\u002Fgithub.com\u002FMiroShark\u002Fmiroshark-aeon\u002Fblob\u002Fmain\u002Fskills\u002Fyou-web-search\u002FSKILL.md",[87,90],{"categoryNo":88,"categoryName":89,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[96,97,98,99,100,101,102,103,104,105,106,107,39,108,35,109,110,111,112,113,114],"web search","search","you","you web search","web","time","only","api","web crawling","read","read-only","real-time","keyless","research","results","high","quality","box","limits",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":46},"01M6J4P4H35WQG6RHGTTACSMVW","write-tweet","Multi-format tweet studio - standalone drafts (10 across 5 size tiers), a 5-10 tweet thread, or 10 remixes of past tweets, selected via ${var}","https:\u002F\u002Fgithub.com\u002FMiroShark\u002Fmiroshark-aeon\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-tweet\u002FSKILL.md",[],[122,123,124,125,126,103,127,128,129,130,39,131,132,133,134,135,29,54],"write","write tweet","standalone","social","studio","across","xai","past","drafts","twitter","thread","multi","size","via",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":143,"publishedAt":46},"01M6J4P11K7ZJ2PJDHDTTFZ1HY","weekly-aeoncard","Build a weekly token-consumption recap image from memory\u002Ftoken-usage.csv - this week + all-time totals, top skills, rendered as a shareable SVG card.","https:\u002F\u002Fgithub.com\u002FMiroShark\u002Fmiroshark-aeon\u002Fblob\u002Fmain\u002Fskills\u002Fweekly-aeoncard\u002FSKILL.md",[142],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[144,145,146,147,148,149,150,101,151,152,153,154,155,156,157,158,159,122,160,161],"weekly","weekly aeoncard","as","usage","SVG","memory","card","Meta","image","recap","csv","monitoring","notifications","productivity","top","build","token","aeon",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":168,"publishedAt":46},"01M6J4NVJYQP5DNKSGXAXQW06B","vuln-tracker","One lifecycle poll over everything vuln-scanner produces - PR and advisory status, PVR triage transitions, and pending-disclosure aging, with a stars-secured impact headline and one action queue.","https:\u002F\u002Fgithub.com\u002FMiroShark\u002Fmiroshark-aeon\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-tracker\u002FSKILL.md",[],[169,170,151,171,172,122,160,173,174,175,176,177,178,179,180,181,182,35,183,184,185,186],"tracker","vuln tracker","impact","scanner","status","action","security","pr","stars","lifecycle","dev","gh","aging","advisory","github","transitions","triage","global",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":196,"publishedAt":46},"01M6J4NNQCHTKNGENAPJQ8KYHR","vuln-scanner","Audit trending repos for real security vulnerabilities and disclose responsibly - scan and route findings (PVR \u002F dependency PR), re-submit queued advisories, and send armed email disclosures","https:\u002F\u002Fgithub.com\u002FMiroShark\u002Fmiroshark-aeon\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-scanner\u002FSKILL.md",[193],{"categoryNo":194,"categoryName":195,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000005","邮件与沟通",[172,197,198,199,200,151,201,175,202,203,204,179,183,205,186,206,103,207,208,209],"vuln scanner","resend","re","trending","repos","email","for","scan","vulnerabilities","submit","route","audit","send",{"skillNo":211,"name":212,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":214,"categories":215,"keywords":216,"publishedAt":46},"01M6J4NAFNHVTAVBKK843SYVQX","unlock-monitor","Token unlock and vesting tracker - quantify supply pressure via absorption ratio, classify cliff vs linear, and deliver one-line market reads","https:\u002F\u002Fgithub.com\u002FMiroShark\u002Fmiroshark-aeon\u002Fblob\u002Fmain\u002Fskills\u002Funlock-monitor\u002FSKILL.md",[],[217,218,219,220,221,222,135,223,169,224,122,160,225,226,227,228],"monitor","unlock monitor","supply","true","Market","crypto","classify","line","vesting","absorption","linear","deliver"]