[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79BV6BTS18HVMY00GYCF6E2":3,"skill-same:01M79BV6BTS18HVMY00GYCF6E2":72},{"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},"01M79BV6BTS18HVMY00GYCF6E2","granola-transcripts",null,"Retrieve Granola meeting transcripts through the API. Use when a task needs meeting quotes, decisions, or verification of a Granola summary.","JacobStephens2\u002Fskills","JacobStephens2","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F53905376?v=4","01M79BR1761Q98X4CQJG8Q19VR","Jacob Stephens","01M79BR1873RESHSCQYNM335K3",1,"MIT","https:\u002F\u002Fgithub.com\u002FJacobStephens2\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fgranola-transcripts\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: granola-transcripts\ndescription: Retrieve Granola meeting transcripts through the API. Use when a task needs meeting quotes, decisions, or verification of a Granola summary.\n---\n\n# Granola transcripts\n\nUse the official API when `GRANOLA_API_KEY` is available. The bundled Python 3\nhelper lists notes and saves the full note response plus a readable transcript.\nIt needs no third-party packages. Resolve `scripts\u002Fgranola.py` relative to this\nskill directory, not the user's working directory.\n\n## 1. Find the meeting\n\nCheck key availability without showing its value:\n\n```bash\npython3 -c 'import os; print(\"GRANOLA_API_KEY: \" + (\"set\" if os.getenv(\"GRANOLA_API_KEY\") else \"missing\"))'\n```\n\nIf the user launched the agent through an environment-loading wrapper, inspect\nthe current environment first; another launch is unnecessary when the key is\nalready present. Keep the key in the environment rather than command arguments,\nlogs, files, or chat. For missing credentials, use the access reference below.\n\nList a bounded date window and inspect titles and creation times:\n\n```bash\npython3 \u002Fpath\u002Fto\u002Fgranola-transcripts\u002Fscripts\u002Fgranola.py list \\\n  --after 2026-01-26 --before 2026-01-29 --title 'project'\n```\n\n`--title` is an optional case-insensitive substring filter applied locally after\npagination. The helper follows `hasMore`\u002F`cursor` until complete and errors if\nits page limit is reached; an incomplete search is not an absence finding.\n\nDate filters refer to **note creation**, not scheduled meeting time. For “this\nmorning,” establish the user's date\u002Ftimezone, search a window padded around\nUTC boundaries, then match the note's calendar event, attendees, and transcript\ntimestamps. Widen the window if a note may have been created in advance.\nResolve multiple plausible meetings from that metadata or ask the user.\n\nUse the `not_…` ID returned by the API. A UUID in a `notes.granola.ai\u002Ft\u002F…` share\nlink or `\u002Fd\u002F…` document link is not the API note ID. Locate it through the note\nlist and confirm using `web_url` and meeting metadata rather than substituting\nthat UUID in the API path. A public summary page is not a transcript.\n\n## 2. Retrieve and read\n\n```bash\npython3 \u002Fpath\u002Fto\u002Fgranola-transcripts\u002Fscripts\u002Fgranola.py get \\\n  not_XXXXXXXXXXXXXX --out-dir \u002Ftmp\u002Fgranola-meeting\n```\n\nChoose a **new** output directory outside the skill\u002Frepository; results may\ncontain private notes and attendee details. Copy evidence into the user's\nproject only when the task calls for it. The command uses\n`GET \u002Fv1\u002Fnotes\u002F{note_id}?include=transcript`, writes the original response to\n`note.json`, and writes all segments to `transcript.txt`. Oversized transcripts\nare fetched in cursor pages, preserved as `transcript-page-001.json`, etc. Console output is a\nsmall receipt with paths and segment count. Search\u002Fread those files in chunks\ninstead of dumping the whole JSON into a tool result and losing it to truncation.\n\nThe readable transcript preserves source text, ISO timestamps, speaker objects,\nand one-based `T001` segment numbers. Keep the original JSON as the source.\n`me`\u002F`them` and microphone\u002Fspeaker indicate capture attribution, not reliably\nnamed people; `them` can include multiple participants. Identify names only\nwhen supported, and label contextual speaker mapping as inference. Calendar\nattendees alone do not establish who said a line.\n\n## 3. Use the evidence\n\nVerify material quotations and decisions in surrounding turns.\nKeep transcript evidence, generated summaries, user recollections, and your\ninterpretation distinct. Preserve proposed examples as proposals rather than\ncommitments. Cite `web_url` with timestamp\u002Fsegment references where useful.\n\nCompletion: the requested meeting is matched, its complete transcript is saved,\nand the answer identifies its source. If retrieval is incomplete, state exactly\nwhat was retrieved and what remains unavailable.\n\nFor a missing key, no matching note, or a retrieval error, read\n[Access problems and incomplete retrieval](references\u002Faccess-and-errors.md).\n","# Granola transcripts\n\nUse the official API when `GRANOLA_API_KEY` is available. The bundled Python 3\nhelper lists notes and saves the full note response plus a readable transcript.\nIt needs no third-party packages. Resolve `scripts\u002Fgranola.py` relative to this\nskill directory, not the user's working directory.\n\n## 1. Find the meeting\n\nCheck key availability without showing its value:\n\n```bash\npython3 -c 'import os; print(\"GRANOLA_API_KEY: \" + (\"set\" if os.getenv(\"GRANOLA_API_KEY\") else \"missing\"))'\n```\n\nIf the user launched the agent through an environment-loading wrapper, inspect\nthe current environment first; another launch is unnecessary when the key is\nalready present. Keep the key in the environment rather than command arguments,\nlogs, files, or chat. For missing credentials, use the access reference below.\n\nList a bounded date window and inspect titles and creation times:\n\n```bash\npython3 \u002Fpath\u002Fto\u002Fgranola-transcripts\u002Fscripts\u002Fgranola.py list \\\n  --after 2026-01-26 --before 2026-01-29 --title 'project'\n```\n\n`--title` is an optional case-insensitive substring filter applied locally after\npagination. The helper follows `hasMore`\u002F`cursor` until complete and errors if\nits page limit is reached; an incomplete search is not an absence finding.\n\nDate filters refer to **note creation**, not scheduled meeting time. For “this\nmorning,” establish the user's date\u002Ftimezone, search a window padded around\nUTC boundaries, then match the note's calendar event, attendees, and transcript\ntimestamps. Widen the window if a note may have been created in advance.\nResolve multiple plausible meetings from that metadata or ask the user.\n\nUse the `not_…` ID returned by the API. A UUID in a `notes.granola.ai\u002Ft\u002F…` share\nlink or `\u002Fd\u002F…` document link is not the API note ID. Locate it through the note\nlist and confirm using `web_url` and meeting metadata rather than substituting\nthat UUID in the API path. A public summary page is not a transcript.\n\n## 2. Retrieve and read\n\n```bash\npython3 \u002Fpath\u002Fto\u002Fgranola-transcripts\u002Fscripts\u002Fgranola.py get \\\n  not_XXXXXXXXXXXXXX --out-dir \u002Ftmp\u002Fgranola-meeting\n```\n\nChoose a **new** output directory outside the skill\u002Frepository; results may\ncontain private notes and attendee details. Copy evidence into the user's\nproject only when the task calls for it. The command uses\n`GET \u002Fv1\u002Fnotes\u002F{note_id}?include=transcript`, writes the original response to\n`note.json`, and writes all segments to `transcript.txt`. Oversized transcripts\nare fetched in cursor pages, preserved as `transcript-page-001.json`, etc. Console output is a\nsmall receipt with paths and segment count. Search\u002Fread those files in chunks\ninstead of dumping the whole JSON into a tool result and losing it to truncation.\n\nThe readable transcript preserves source text, ISO timestamps, speaker objects,\nand one-based `T001` segment numbers. Keep the original JSON as the source.\n`me`\u002F`them` and microphone\u002Fspeaker indicate capture attribution, not reliably\nnamed people; `them` can include multiple participants. Identify names only\nwhen supported, and label contextual speaker mapping as inference. Calendar\nattendees alone do not establish who said a line.\n\n## 3. Use the evidence\n\nVerify material quotations and decisions in surrounding turns.\nKeep transcript evidence, generated summaries, user recollections, and your\ninterpretation distinct. Preserve proposed examples as proposals rather than\ncommitments. Cite `web_url` with timestamp\u002Fsegment references where useful.\n\nCompletion: the requested meeting is matched, its complete transcript is saved,\nand the answer identifies its source. If retrieval is incomplete, state exactly\nwhat was retrieved and what remains unavailable.\n\nFor a missing key, no matching note, or a retrieval error, read\n[Access problems and incomplete retrieval](references\u002Faccess-and-errors.md).\n",{"name":5,"description":7},"main","49fab7f4cb5b5e8b5a156391b50498eb3ca5f144","skills\u002Fgranola-transcripts","https:\u002F\u002Fgithub.com\u002FJacobStephens2\u002Fskills","https:\u002F\u002Fgithub.com\u002FJacobStephens2","https:\u002F\u002Fstephens.page","Software engineer building AI agent infrastructure and production platforms. Head of Engineering at ETA. Building thirdshift in Rust.","2026-10-22 06:54:11",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add JacobStephens2\u002Fskills --skill granola-transcripts",{"tool":38,"command":39},"bunx","bunx skills add JacobStephens2\u002Fskills --skill granola-transcripts",{"tool":41,"command":42},"pnpm","pnpm dlx skills add JacobStephens2\u002Fskills --skill granola-transcripts","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJacobStephens2\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fgranola-transcripts\u002FSKILL.md",true,[46,52,58,62,68],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},".gitignore","OTHER","其他",19,"https:\u002F\u002Fgithub.com\u002FJacobStephens2\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fgranola-transcripts\u002F.gitignore",{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"agents\u002Fopenai.yaml","REFERENCE","参考文档",121,"https:\u002F\u002Fgithub.com\u002FJacobStephens2\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fgranola-transcripts\u002Fagents\u002Fopenai.yaml",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Faccess-and-errors.md",1688,"https:\u002F\u002Fgithub.com\u002FJacobStephens2\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fgranola-transcripts\u002Freferences\u002Faccess-and-errors.md",{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"scripts\u002Fgranola.py","SCRIPT","脚本",7174,"https:\u002F\u002Fgithub.com\u002FJacobStephens2\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fgranola-transcripts\u002Fscripts\u002Fgranola.py",{"path":69,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":70,"sourceHtmlUrl":71},"tests\u002Ftest_granola.py",6508,"https:\u002F\u002Fgithub.com\u002FJacobStephens2\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fgranola-transcripts\u002Ftests\u002Ftest_granola.py",[73,80,87,94,101,108],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M79BV3SP2660J24TBK6ZSBG5","explainer-video","Make narrated, animated explainer videos. Use when the user wants an explainer, tutorial, demo, promo or executive-overview video, or a new version of one.","https:\u002F\u002Fgithub.com\u002FJacobStephens2\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fexplainer-video\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M79BV2EAVY0693B0NVYD0XRA","root-cause-analysis","Write an root cause analysis.","https:\u002F\u002Fgithub.com\u002FJacobStephens2\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002F.archive\u002Froot-cause-analysis\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M79BTZFGD38BJZK9BS55KDX3","adversarial-review","Write an adversarial review.","https:\u002F\u002Fgithub.com\u002FJacobStephens2\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002F.archive\u002Freview\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},"01M79BTWVBAXEFSGTY6RN42WSG","plan","Write a plan.","https:\u002F\u002Fgithub.com\u002FJacobStephens2\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002F.archive\u002Fplan\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},"01M79BTTE6FPZF134K3YY7Q6MT","implement-spec","Drive a spec's tickets in dependency order, with a subagent per ticket, independent verification, and gated landing.","https:\u002F\u002Fgithub.com\u002FJacobStephens2\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002F.archive\u002Fimplement-spec\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},"01M79BTQY82F7C3GPFWKPE1K10","chisel","Simplify, chisel, and trim fat","https:\u002F\u002Fgithub.com\u002FJacobStephens2\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002F.archive\u002Fchisel\u002FSKILL.md",[],[]]