[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7B3AF44G9KM393WRGSMEVHR":3,"skill-same:01M7B3AF44G9KM393WRGSMEVHR":53},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7B3AF44G9KM393WRGSMEVHR","email-voice-profile",null,"Build (or refresh) a voice profile of how the user writes email, from their own sent Gmail. The profile is what email-draft-in-voice consumes to ghostwrite email that sounds like them.","liangfeng520520\u002Fyc-aiPlatform-FeishuVersion","liangfeng520520","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180317841?v=4","01M7B38VTS5PETWZ8NP9DZNAEE","张浩然","01M7B38VVGTV327GX4KR6N72KY",0,"MIT","https:\u002F\u002Fgithub.com\u002Fliangfeng520520\u002Fyc-aiPlatform-FeishuVersion\u002Fblob\u002Fmain\u002Fskills-seed\u002Femail-voice-profile\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: email-voice-profile\ndescription: Build (or refresh) a voice profile of how the user writes email, from their own sent Gmail. The profile is what email-draft-in-voice consumes to ghostwrite email that sounds like them.\nrequiredCapabilities:\n  - egress:gmail.googleapis.com\n---\n\n# Email voice profile\n\nUse this when the user asks you to learn how they write email — \"learn my voice\",\n\"build my email voice profile\", \"study my sent mail so you can draft for me\" — or when\n`email-draft-in-voice` needs a profile that doesn't exist yet.\n\n**Personal DMs only.** Sent mail is private; refuse to run this from a channel or group\nand offer to continue in the user's DM. The profile you produce lives in their personal\nworkspace, so only their own conversations can read it.\n\n## 1. Pull the corpus\n\n```bash\npython3 skills\u002Femail-voice-profile\u002Fscripts\u002Ffetch_sent.py --limit 300\n```\n\nThis fetches the user's sent messages (their Google OAuth token is already on your\ncomputer; if it's missing, point them at the app-connect flow), strips quoted replies\nand signatures, drops automated and trivial messages, and writes one JSON line per\nemail to `voice\u002Fcorpus\u002Fcorpus.jsonl` — each tagged `internal` or `external` by\nrecipient domain. It prints corpus stats; if fewer than ~50 usable emails survive,\ntell the user the profile will be rough and ask whether to continue.\n\n## 2. Study it\n\nRead a deliberate spread, not just the top of the file: oldest and newest, internal\nand external, one-liners and long emails. You are looking for what is _distinctive_ —\npatterns a generic professional emailer would not share.\n\nWatch for a signature block: only `--`-delimited signatures are stripped, so a plain\nsignature (name \u002F title \u002F phone) survives at the end of many bodies. Treat a verbatim\nrecurring trailing block as the mail client's signature, not a chosen sign-off — note\nit in the profile so drafts never include it (Gmail appends it on send).\n\n## 3. Write the profile\n\nWrite `voice\u002Femail-voice-profile.md` in the workspace with exactly these sections,\nevery claim backed by observed frequency (\"uses 'Best,' in 80% of external mail\"),\nwith 2–3 verbatim example lines each:\n\n- **Register map** — how tone shifts by audience (internal vs external, familiar vs\n  cold), and how their length tracks the situation.\n- **Openers & sign-offs** — actual greetings and closings with rough frequencies,\n  including when they use none.\n- **Rhythm** — sentence length, paragraph shape, how they open and end a body, use of\n  fragments, lists, links.\n- **Vocabulary & phrases** — recurring words, pet phrases, how they hedge, how they say\n  yes and no.\n- **Punctuation & formatting quirks** — dashes, ellipses, casing, emoji, bolding.\n- **Hard rules** — things true of nearly every email (\"never opens with 'I hope this\n  finds you well'\", \"always lowercase to teammates\").\n- **Anti-patterns** — what they never do, plus the generic-AI tells to avoid\n  (enthusiastic adjectives, \"I'd be happy to\", bullet-point answers to plain questions).\n\n## 4. Validate before declaring done\n\nHold out 3 real threads the profile wasn't built from. For each, draft the user's\nreply using only the profile, then compare with what they actually sent. Where the\nreal email diverges, tighten the profile — usually a missing hard rule or register\ndistinction. Record `validated: \u003Cdate>` at the top of the profile once the drafts read\nas plausibly theirs.\n\nShow the user the finished profile and ask what feels wrong; their corrections go in\nas hard rules. Re-run this skill any time they want it refreshed — it overwrites the\ncorpus and profile in place.\n","# Email voice profile\n\nUse this when the user asks you to learn how they write email — \"learn my voice\",\n\"build my email voice profile\", \"study my sent mail so you can draft for me\" — or when\n`email-draft-in-voice` needs a profile that doesn't exist yet.\n\n**Personal DMs only.** Sent mail is private; refuse to run this from a channel or group\nand offer to continue in the user's DM. The profile you produce lives in their personal\nworkspace, so only their own conversations can read it.\n\n## 1. Pull the corpus\n\n```bash\npython3 skills\u002Femail-voice-profile\u002Fscripts\u002Ffetch_sent.py --limit 300\n```\n\nThis fetches the user's sent messages (their Google OAuth token is already on your\ncomputer; if it's missing, point them at the app-connect flow), strips quoted replies\nand signatures, drops automated and trivial messages, and writes one JSON line per\nemail to `voice\u002Fcorpus\u002Fcorpus.jsonl` — each tagged `internal` or `external` by\nrecipient domain. It prints corpus stats; if fewer than ~50 usable emails survive,\ntell the user the profile will be rough and ask whether to continue.\n\n## 2. Study it\n\nRead a deliberate spread, not just the top of the file: oldest and newest, internal\nand external, one-liners and long emails. You are looking for what is _distinctive_ —\npatterns a generic professional emailer would not share.\n\nWatch for a signature block: only `--`-delimited signatures are stripped, so a plain\nsignature (name \u002F title \u002F phone) survives at the end of many bodies. Treat a verbatim\nrecurring trailing block as the mail client's signature, not a chosen sign-off — note\nit in the profile so drafts never include it (Gmail appends it on send).\n\n## 3. Write the profile\n\nWrite `voice\u002Femail-voice-profile.md` in the workspace with exactly these sections,\nevery claim backed by observed frequency (\"uses 'Best,' in 80% of external mail\"),\nwith 2–3 verbatim example lines each:\n\n- **Register map** — how tone shifts by audience (internal vs external, familiar vs\n  cold), and how their length tracks the situation.\n- **Openers & sign-offs** — actual greetings and closings with rough frequencies,\n  including when they use none.\n- **Rhythm** — sentence length, paragraph shape, how they open and end a body, use of\n  fragments, lists, links.\n- **Vocabulary & phrases** — recurring words, pet phrases, how they hedge, how they say\n  yes and no.\n- **Punctuation & formatting quirks** — dashes, ellipses, casing, emoji, bolding.\n- **Hard rules** — things true of nearly every email (\"never opens with 'I hope this\n  finds you well'\", \"always lowercase to teammates\").\n- **Anti-patterns** — what they never do, plus the generic-AI tells to avoid\n  (enthusiastic adjectives, \"I'd be happy to\", bullet-point answers to plain questions).\n\n## 4. Validate before declaring done\n\nHold out 3 real threads the profile wasn't built from. For each, draft the user's\nreply using only the profile, then compare with what they actually sent. Where the\nreal email diverges, tighten the profile — usually a missing hard rule or register\ndistinction. Record `validated: \u003Cdate>` at the top of the profile once the drafts read\nas plausibly theirs.\n\nShow the user the finished profile and ask what feels wrong; their corrections go in\nas hard rules. Re-run this skill any time they want it refreshed — it overwrites the\ncorpus and profile in place.\n",{"name":5,"description":7,"requiredCapabilities":24},[25],"egress:gmail.googleapis.com","main","02b6fa5cba78634d3db4848f18dd95f807c4c33c","skills-seed\u002Femail-voice-profile","https:\u002F\u002Fgithub.com\u002Fliangfeng520520\u002Fyc-aiPlatform-FeishuVersion","https:\u002F\u002Fgithub.com\u002Fliangfeng520520","My name is HaoRan ZHANG. I am a student in the Chinese University of HongKong.My major is INFORMATION SCIENCE AND TECHNOLOGY MANAGEMENT.","2026-08-25 16:11:34",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add liangfeng520520\u002Fyc-aiPlatform-FeishuVersion --skill email-voice-profile",{"tool":39,"command":40},"bunx","bunx skills add liangfeng520520\u002Fyc-aiPlatform-FeishuVersion --skill email-voice-profile",{"tool":42,"command":43},"pnpm","pnpm dlx skills add liangfeng520520\u002Fyc-aiPlatform-FeishuVersion --skill email-voice-profile","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fliangfeng520520\u002Fyc-aiPlatform-FeishuVersion\u002Fblob\u002Fmain\u002Fskills-seed\u002Femail-voice-profile\u002FSKILL.md",true,[47],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"scripts\u002Ffetch_sent.py","SCRIPT","脚本",7621,"https:\u002F\u002Fgithub.com\u002Fliangfeng520520\u002Fyc-aiPlatform-FeishuVersion\u002Fblob\u002Fmain\u002Fskills-seed\u002Femail-voice-profile\u002Fscripts\u002Ffetch_sent.py",[54,61,69,76,83,90],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7B3BJC24VXXCNPN8NWHF1FN","use-shared-credential","When you need to call a service the org has a SHARED credential for (a SERP\u002Fsearch key, a paid-API key, a data-vendor feed, a Git remote) — and the platform has told you that credential is available to this conversation — make the call BY PROXY through the credential broker. You never see the secret; the core stamps it onto the outbound request for you.","https:\u002F\u002Fgithub.com\u002Fliangfeng520520\u002Fyc-aiPlatform-FeishuVersion\u002Fblob\u002Fmain\u002Fskills-seed\u002Fuse-shared-credential\u002FSKILL.md",[],[],{"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":65,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7B3BEYG1G1EA0X2X3615FV5","taste-skill","Design taste and process for anything a person will look at in a browser — landing page, dashboard, prototype, deck. The default design driver for a browsable artifact, with an anti-slop playbook for the visual language.","https:\u002F\u002Fgithub.com\u002Fliangfeng520520\u002Fyc-aiPlatform-FeishuVersion\u002Fblob\u002Fmain\u002Fskills-seed\u002Ftaste-skill\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fliangfeng520520\u002Fyc-aiPlatform-FeishuVersion\u002Fblob\u002Fmain\u002Fskills-seed\u002Ftaste-skill\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7B3BA8Q2YNWV2ZGEKD1NGSA","publish","Publish a long-lived internal web app, site, or dashboard from the agent computer. Scope-bound (only the owner's scope, plus whoever you share it with, can reach it), immutable versions with rollback, a stable friendly link. No public URL.","https:\u002F\u002Fgithub.com\u002Fliangfeng520520\u002Fyc-aiPlatform-FeishuVersion\u002Fblob\u002Fmain\u002Fskills-seed\u002Fpublish\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7B3B6P4CV10Q9Q0R5APHEZ0","popular-web-designs","54 real-world design systems (Stripe, Linear, Vercel, Notion, Apple…) as ready-to-paste HTML\u002FCSS — exact colors, typography, components, and spacing for styling a page after a known brand.","https:\u002F\u002Fgithub.com\u002Fliangfeng520520\u002Fyc-aiPlatform-FeishuVersion\u002Fblob\u002Fmain\u002Fskills-seed\u002Fpopular-web-designs\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7B3B4J0AH7REMR5Y97YGMVS","morning-digest","Assemble and deliver one short morning digest for the person who owns the cron — what changed overnight in the sources they already connected, and what it means for their day.","https:\u002F\u002Fgithub.com\u002Fliangfeng520520\u002Fyc-aiPlatform-FeishuVersion\u002Fblob\u002Fmain\u002Fskills-seed\u002Fmorning-digest\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7B3B00MAAV05PE6FF5P54C3","memory","Deliberately search, add to, or curate your long-term memory with the `memory` tool — beyond the automatic recall\u002Fcapture every turn already does. Use when asked who someone is or what they're working on, when you learn a durable fact worth keeping now, or when your notebook holds stale or wrong entries you should clean up.","https:\u002F\u002Fgithub.com\u002Fliangfeng520520\u002Fyc-aiPlatform-FeishuVersion\u002Fblob\u002Fmain\u002Fskills-seed\u002Fmemory\u002FSKILL.md",[],[]]