[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71DZP5KP173KVCJ6PYWSGBB":3,"skill-same:01M71DZP5KP173KVCJ6PYWSGBB":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":23,"publishedAt":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M71DZP5KP173KVCJ6PYWSGBB","meeting-notes",null,"Read HQ-native meeting notes, transcripts, recaps, and sources for a company.","indigoai-us\u002Fhq-core","indigoai-us","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F122242446?v=4","01M71DTQ5NGD10GT1Z7E6XKWC5","HQ","01M71DTQ6BKSYYBNC9RAKT3YDK",94,"MIT","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fmeeting-notes\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34],"notes","meeting","meeting notes","sources","native","for","read","company","grep","transcripts","Bash","2026-11-10 10:12:30",false,"---\nname: meeting-notes\ndescription: Read HQ-native meeting notes, transcripts, recaps, and sources for a company.\nallowed-tools: Bash, Read, Grep, Glob\n---\n\n# \u002Fmeeting-notes — Read HQ-native meeting notes\n\nMeeting notes are an **HQ-native, per-company store** populated by the HQ meeting bot (Recall.ai). This skill is the generic, multi-company reader — it works for **every** company, not just ones that ship their own namespaced meeting flows.\n\n**Canonical store:** `companies\u002F{co}\u002Fsources\u002Fmeetings\u002F{uuid}.md` (+ `{uuid}.raw.json`), date index `companies\u002F{co}\u002Fsources\u002F_index\u002F{YYYY-MM-DD}.json`.\n**Generic CLI reader:** `hq meetings list|get|notes|transcript|search --company {slug}`.\n**Mechanism\u002Fschema detail (read once if needed):** `core\u002Fknowledge\u002Fpublic\u002Fhq-core\u002Fnative-knowledge-stores.md`.\n\n## Hard rule\n\nHQ-native first. **Never** default to email search or a third-party notetaker (Fireflies, Otter, Granola, Fathom, Zoom AI) to answer a \"meeting notes\" request. Only use email\u002Fexternal if the company's preference is *explicitly* set to it (see resolution below). If the native store is empty or unactivated, **steer the user to activate it** — do not silently fall back to scraping inboxes.\n\n## Resolution (run every time)\n\n1. **Resolve company.** `bash core\u002Fscripts\u002Fhq-session.sh get company_slug`. If unset, infer from cwd \u002F `companies\u002Fmanifest.yaml`; if still ambiguous, ask the user which company.\n2. **Load preference (company over global, per-field merge).** Read, if present:\n   - `companies\u002F{co}\u002Fsettings\u002Fknowledge\u002Fpreferences.yaml` (override)\n   - `personal\u002Fsettings\u002Fknowledge-preferences.yaml` (global default)\n   - Built-in default when neither sets it: `meeting_notes_source: hq-native`, `notetaker: recall`.\n3. **Branch on `meeting_notes_source`:**\n   - `hq-native` (default) → read the native store (below).\n   - `email` \u002F `external` → use that source per the user's stated preference; otherwise honor native.\n4. **Term aliases.** Treat \"standup notes\", \"recap\", \"call notes\", \"meeting recap\" (plus any `aliases.meeting_notes` in the preference file) as meeting-notes requests.\n\n## Reading the native store (`hq-native`)\n\nPrefer the CLI; fall back to direct reads.\n\n- **Latest \u002F list:** `hq meetings list --company {co}` (most recent meetings, titles, dates, bot status). For a specific one: `hq meetings notes --company {co} --id {uuid}` or `hq meetings transcript ...`.\n- **Direct fallback:** newest files in `companies\u002F{co}\u002Fsources\u002Fmeetings\u002F` (sort by `scheduled_start_time`\u002F`ingested_at` in frontmatter, or use the `_index\u002F{date}.json`). Each `.md` carries frontmatter (`title`, `origin: recall.ai`, `meeting_platform`, `bot_status`, `scheduled_start_time`) and a `## Transcript` body.\n- Pick the meeting the user means (latest, by title, by date). Summarize from the transcript\u002Fnotes; quote sparingly.\n\n## Empty \u002F not-activated branch\n\nIf `hq meetings list` returns nothing and `companies\u002F{co}\u002Fsources\u002Fmeetings\u002F` is empty or absent, the company hasn't activated HQ meeting capture. Do **not** scrape email. Instead surface the turnkey ladder (full version in the knowledge doc + USER-GUIDE):\n\n1. Make the company cloud-backed → `\u002Fdesignate-team {co}` (`hq cloud provision company {co}`).\n2. Invite the HQ meeting bot to the call (Recall.ai via `hq meetings` + bot-invite API).\n3. Notes ingest automatically into `companies\u002F{co}\u002Fsources\u002Fmeetings\u002F`; read them here next time.\n4. Note: signals + ontology follow once provisioned; some of this runs on HQ cloud and **will require HQ Pro once billing ships (not yet — provisioned per-company today via `\u002Fdesignate-team`).**\n\nThen offer: if they want \"meeting notes\" to mean their **email** for this company instead, set `meeting_notes_source: email` in `companies\u002F{co}\u002Fsettings\u002Fknowledge\u002Fpreferences.yaml`.\n\n## Ambiguity → ask once, then persist\n\nIf the term is genuinely ambiguous (e.g. the user has both a populated native store and a history of email recaps) and no preference is recorded, ask **once** which source they mean, then write the answer to the resolved scope (`companies\u002F{co}\u002Fsettings\u002Fknowledge\u002Fpreferences.yaml` for company-specific, else `personal\u002Fsettings\u002Fknowledge-preferences.yaml`). Don't re-ask afterward.\n\n## Output\n\nQuiet, plain summary of the notes the user asked for. For signals\u002Fdecisions\u002Faction-items extracted from meetings, hand off to `\u002Fsignals` (the meeting intelligence store).\n\n## See also\n\n- `\u002Fsignals` — action items and decisions from meetings\n- `\u002Fontology` — the company knowledge graph\n","# \u002Fmeeting-notes — Read HQ-native meeting notes\n\nMeeting notes are an **HQ-native, per-company store** populated by the HQ meeting bot (Recall.ai). This skill is the generic, multi-company reader — it works for **every** company, not just ones that ship their own namespaced meeting flows.\n\n**Canonical store:** `companies\u002F{co}\u002Fsources\u002Fmeetings\u002F{uuid}.md` (+ `{uuid}.raw.json`), date index `companies\u002F{co}\u002Fsources\u002F_index\u002F{YYYY-MM-DD}.json`.\n**Generic CLI reader:** `hq meetings list|get|notes|transcript|search --company {slug}`.\n**Mechanism\u002Fschema detail (read once if needed):** `core\u002Fknowledge\u002Fpublic\u002Fhq-core\u002Fnative-knowledge-stores.md`.\n\n## Hard rule\n\nHQ-native first. **Never** default to email search or a third-party notetaker (Fireflies, Otter, Granola, Fathom, Zoom AI) to answer a \"meeting notes\" request. Only use email\u002Fexternal if the company's preference is *explicitly* set to it (see resolution below). If the native store is empty or unactivated, **steer the user to activate it** — do not silently fall back to scraping inboxes.\n\n## Resolution (run every time)\n\n1. **Resolve company.** `bash core\u002Fscripts\u002Fhq-session.sh get company_slug`. If unset, infer from cwd \u002F `companies\u002Fmanifest.yaml`; if still ambiguous, ask the user which company.\n2. **Load preference (company over global, per-field merge).** Read, if present:\n   - `companies\u002F{co}\u002Fsettings\u002Fknowledge\u002Fpreferences.yaml` (override)\n   - `personal\u002Fsettings\u002Fknowledge-preferences.yaml` (global default)\n   - Built-in default when neither sets it: `meeting_notes_source: hq-native`, `notetaker: recall`.\n3. **Branch on `meeting_notes_source`:**\n   - `hq-native` (default) → read the native store (below).\n   - `email` \u002F `external` → use that source per the user's stated preference; otherwise honor native.\n4. **Term aliases.** Treat \"standup notes\", \"recap\", \"call notes\", \"meeting recap\" (plus any `aliases.meeting_notes` in the preference file) as meeting-notes requests.\n\n## Reading the native store (`hq-native`)\n\nPrefer the CLI; fall back to direct reads.\n\n- **Latest \u002F list:** `hq meetings list --company {co}` (most recent meetings, titles, dates, bot status). For a specific one: `hq meetings notes --company {co} --id {uuid}` or `hq meetings transcript ...`.\n- **Direct fallback:** newest files in `companies\u002F{co}\u002Fsources\u002Fmeetings\u002F` (sort by `scheduled_start_time`\u002F`ingested_at` in frontmatter, or use the `_index\u002F{date}.json`). Each `.md` carries frontmatter (`title`, `origin: recall.ai`, `meeting_platform`, `bot_status`, `scheduled_start_time`) and a `## Transcript` body.\n- Pick the meeting the user means (latest, by title, by date). Summarize from the transcript\u002Fnotes; quote sparingly.\n\n## Empty \u002F not-activated branch\n\nIf `hq meetings list` returns nothing and `companies\u002F{co}\u002Fsources\u002Fmeetings\u002F` is empty or absent, the company hasn't activated HQ meeting capture. Do **not** scrape email. Instead surface the turnkey ladder (full version in the knowledge doc + USER-GUIDE):\n\n1. Make the company cloud-backed → `\u002Fdesignate-team {co}` (`hq cloud provision company {co}`).\n2. Invite the HQ meeting bot to the call (Recall.ai via `hq meetings` + bot-invite API).\n3. Notes ingest automatically into `companies\u002F{co}\u002Fsources\u002Fmeetings\u002F`; read them here next time.\n4. Note: signals + ontology follow once provisioned; some of this runs on HQ cloud and **will require HQ Pro once billing ships (not yet — provisioned per-company today via `\u002Fdesignate-team`).**\n\nThen offer: if they want \"meeting notes\" to mean their **email** for this company instead, set `meeting_notes_source: email` in `companies\u002F{co}\u002Fsettings\u002Fknowledge\u002Fpreferences.yaml`.\n\n## Ambiguity → ask once, then persist\n\nIf the term is genuinely ambiguous (e.g. the user has both a populated native store and a history of email recaps) and no preference is recorded, ask **once** which source they mean, then write the answer to the resolved scope (`companies\u002F{co}\u002Fsettings\u002Fknowledge\u002Fpreferences.yaml` for company-specific, else `personal\u002Fsettings\u002Fknowledge-preferences.yaml`). Don't re-ask afterward.\n\n## Output\n\nQuiet, plain summary of the notes the user asked for. For signals\u002Fdecisions\u002Faction-items extracted from meetings, hand off to `\u002Fsignals` (the meeting intelligence store).\n\n## See also\n\n- `\u002Fsignals` — action items and decisions from meetings\n- `\u002Fontology` — the company knowledge graph\n",{"name":5,"description":7,"allowed-tools":40},"Bash, Read, Grep, Glob","main","205cf61728a27ef15e9153aa38df5856fc8d82f5",".claude\u002Fskills\u002Fmeeting-notes",18,"https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core","https:\u002F\u002Fgithub.com\u002Findigoai-us","https:\u002F\u002Fhqforwork.com\u002F","The AI Context Layer for Teams","2026-11-09 23:36:37",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add indigoai-us\u002Fhq-core --skill meeting-notes",{"tool":56,"command":57},"bunx","bunx skills add indigoai-us\u002Fhq-core --skill meeting-notes",{"tool":59,"command":60},"pnpm","pnpm dlx skills add indigoai-us\u002Fhq-core --skill meeting-notes","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fmeeting-notes\u002FSKILL.md",true,[64],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"agents\u002Fopenai.yaml","REFERENCE","参考文档",129,"https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fmeeting-notes\u002Fagents\u002Fopenai.yaml",[71,90,120,144,155,165],{"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":35},"01M71E4MQ04WPK1EVDS7VKJ3E8","social-graphic","Generate 1080x1080 HTML social graphics for HQ update posts.","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002Fcore\u002Fworkers\u002Fpublic\u002Fsocial-strategist\u002Fskills\u002Fsocial-graphic\u002FSKILL.md",[],[78,79,34,80,81,82,30,83,84,85,86,87,88,29,89],"social","social graphic","html","edit","write","update","generate","graphics","browser","open","agent-browser","posts",{"skillNo":91,"name":88,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":103,"publishedAt":35},"01M71E4H33K4P5H5M7ENPTMFSC","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002Fcore\u002Fworkers\u002Fpublic\u002Fqa-tester\u002Fskills\u002Fagent-browser\u002FSKILL.md",[95,100],{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":101,"categoryName":102,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000023","Skill与智能体开发",[104,86,105,106,107,108,34,109,110,111,112,113,87,114,88,115,116,117,118,119],"agent browser","click","ai agents","app","scrape","when","apps","actions","extracting","take a screenshot","testing","programmatic","browser automation","website","cli","interaction",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":35},"01M71E4FDBD7J8Y45JJ9KMMYGN","work-mesh","Work Mesh Live — automatic presence via hq mesh daemon; context reconcile\u002Forganize; manual session task-status, blocked, and note only.","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fwork-mesh\u002FSKILL.md",[],[127,128,129,34,130,131,132,133,134,135,136,137,138,139,30,140,141,142,143],"work mesh","work","mesh","status","context","note","live","presence","automatic","reconcile","only","organize","task","session","manual","daemon","via",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":150,"publishedAt":35},"01M71E4EGHNAAGWAPV6KGBMQ9W","review","Parity worker review skill (materialization fixture).","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002Fcore\u002Fscripts\u002Ftests\u002Ffixtures\u002Fagent-session\u002Fworker-materialization\u002Fparity-worker\u002Fskills\u002Freview\u002FSKILL.md",[],[146,151,152,153,154],"review skill","fixture","parity","worker",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":35},"01M71E4D1FZDJPDC15DRERKX8Y","run","Run or list HQ workers (parity fixture).","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002Fcore\u002Fscripts\u002Ftests\u002Ffixtures\u002Fagent-session\u002Fskills\u002Frun\u002FSKILL.md",[],[157,162,163,153,164,152],"parity fixture","workers","list",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"publishedAt":35},"01M71E4BF4MV5SEWZJZ4T1QPQW","handoff","Preserve session state for a follow-up agent (parity fixture).","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002Fcore\u002Fscripts\u002Ftests\u002Ffixtures\u002Fagent-session\u002Fskills\u002Fhandoff\u002FSKILL.md",[],[167,162,172,173,140,174,29,153,175,176,152],"up","preserve","session state","follow-up","state"]