[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77WDM3T8ERAW6686KD96S96":3,"skill-same:01M77WDM3T8ERAW6686KD96S96":47},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M77WDM3T8ERAW6686KD96S96","next-prompt",null,"Generate and execute the next agent prompt from connected personal data. Use when: the user says \"what should I work on\", \"vana next\", \"what's next\", or when the agent has no pending task. Also triggers after completing a task when autopilot is enabled.","vana-com\u002Fvana-cli","vana-com","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F123112561?v=4","01M77WCAG7S42PDY7VTEVWXQD1","Vana","01M77WCAGV436KWGZWHNHZXGVH",2,"MIT","https:\u002F\u002Fgithub.com\u002Fvana-com\u002Fvana-cli\u002Fblob\u002Fmain\u002Fskills\u002Fnext-prompt\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: next-prompt\ndescription: >\n  Generate and execute the next agent prompt from connected personal data.\n  Use when: the user says \"what should I work on\", \"vana next\", \"what's next\",\n  or when the agent has no pending task. Also triggers after completing a task\n  when autopilot is enabled.\n---\n\n# Next Prompt\n\nPick the single most valuable thing the user should know or have done, based on their connected data and stated focus, and do it.\n\n## Config\n\nRead `~\u002F.vana\u002Fnext-prompt.md` for the user's guidance. This file is the user's standing directive — like a system prompt that steers what you focus on and how you behave. It is **not** a task list or backlog. Do not write tasks, action items, or deliverables into it.\n\nIf the file doesn't exist, create it with the default template below and tell the user to edit it — but don't block on that. Work with whatever you have.\n\n```markdown\n# Next Prompt\n\n## Focus\n\nWhat I care about right now. Use this as context for deciding what's worth my attention — not as a checklist.\n\n## Permissions\n\nDo without asking:\n\n- Research and analysis\n- Writing summaries, memos, or drafts to local files\n- Code exploration and reading\n\nAsk first:\n\n- Sending messages or emails to anyone\n- Creating PRs, issues, or public posts\n- Anything involving money, credentials, or shared infrastructure\n- Deleting data or force-pushing\n\n## Standing instructions\n\n- (your preferences for how the agent works)\n```\n\n## Flow\n\n### 1. Gather context and check freshness\n\n```bash\nvana status --json\n```\n\nThis tells you what sources are connected, their sync state, and `lastCollectedAt` timestamps.\n\nCheck freshness: if any source's `lastCollectedAt` is more than 24 hours old, suggest recollection before generating prompts:\n\n- For one source: `vana collect \u003Csource>`\n- For all stale sources: `vana collect` (re-collects all connected sources)\n\nOnly suggest recollection, don't block on it. Work with whatever data is available.\n\n### 2. Read connected data\n\nFor each connected source, read the result file:\n\n```bash\nls ~\u002F.vana\u002Fresults\u002F\n```\n\nRead each JSON file. Look for timestamped data from the last 24 hours. Common timestamp fields:\n\n- `created_at`, `updated_at`, `timestamp`, `date`\n- `create_time` (ChatGPT conversations)\n- `startedAt`, `endedAt` (Oura, activity data)\n\nIf timestamps aren't available, treat all data as current.\n\n### 3. Read guidance\n\n```bash\ncat ~\u002F.vana\u002Fnext-prompt.md\n```\n\n### 4. Decide and act\n\nPick **one** action. The best action is:\n\n- **Time-sensitive over evergreen.** A message aging toward an SLA beats a code cleanup.\n- **Aligned with the user's stated focus** in the guidance file.\n- **Informed by what the data actually shows**, not what you assume.\n- **Specific and completable** in one agent turn.\n\nClassify the action's risk:\n\n| Risk level      | Examples                                                     | What to do                                                                 |\n| --------------- | ------------------------------------------------------------ | -------------------------------------------------------------------------- |\n| **Safe**        | Research, analysis, local file drafts, code reading          | Just do it. Tell the user what you did when done.                          |\n| **Visible**     | Sending messages, creating PRs, posting publicly             | Describe exactly what you'd do in one sentence, then wait for a thumbs up. |\n| **Destructive** | Deleting data, force-pushing, closing issues, spending money | Explain the action and consequences, then wait for explicit approval.      |\n\nThe user's `Permissions` section overrides these defaults.\n\n**Do not present a numbered list of options.** Pick the best one. If you're wrong, the user will redirect you. That's faster than making them choose every time.\n\n## Reading sources\n\nEach result file in `~\u002F.vana\u002Fresults\u002F` is a different connected source. Don't assume a fixed set — new sources will appear over time. Read the JSON structure to understand what each source contains and look for what's actionable: recent activity, pending items, time-sensitive deadlines, unanswered messages, recurring patterns.\n\n## Rules\n\n1. Never fabricate data. Only reference what's actually in the result files.\n2. Respect `Permissions` from the guidance file.\n3. If no data is connected, say so and suggest connecting sources. Do NOT run `vana connect` yourself — that is a separate skill (`connect-data`) and most sources require a headed browser you cannot access.\n4. Work with whatever data IS available. Do not block on missing sources.\n5. One action at a time. Do it well. Move on.\n6. Don't repeat suggestions the user has already dismissed.\n","# Next Prompt\n\nPick the single most valuable thing the user should know or have done, based on their connected data and stated focus, and do it.\n\n## Config\n\nRead `~\u002F.vana\u002Fnext-prompt.md` for the user's guidance. This file is the user's standing directive — like a system prompt that steers what you focus on and how you behave. It is **not** a task list or backlog. Do not write tasks, action items, or deliverables into it.\n\nIf the file doesn't exist, create it with the default template below and tell the user to edit it — but don't block on that. Work with whatever you have.\n\n```markdown\n# Next Prompt\n\n## Focus\n\nWhat I care about right now. Use this as context for deciding what's worth my attention — not as a checklist.\n\n## Permissions\n\nDo without asking:\n\n- Research and analysis\n- Writing summaries, memos, or drafts to local files\n- Code exploration and reading\n\nAsk first:\n\n- Sending messages or emails to anyone\n- Creating PRs, issues, or public posts\n- Anything involving money, credentials, or shared infrastructure\n- Deleting data or force-pushing\n\n## Standing instructions\n\n- (your preferences for how the agent works)\n```\n\n## Flow\n\n### 1. Gather context and check freshness\n\n```bash\nvana status --json\n```\n\nThis tells you what sources are connected, their sync state, and `lastCollectedAt` timestamps.\n\nCheck freshness: if any source's `lastCollectedAt` is more than 24 hours old, suggest recollection before generating prompts:\n\n- For one source: `vana collect \u003Csource>`\n- For all stale sources: `vana collect` (re-collects all connected sources)\n\nOnly suggest recollection, don't block on it. Work with whatever data is available.\n\n### 2. Read connected data\n\nFor each connected source, read the result file:\n\n```bash\nls ~\u002F.vana\u002Fresults\u002F\n```\n\nRead each JSON file. Look for timestamped data from the last 24 hours. Common timestamp fields:\n\n- `created_at`, `updated_at`, `timestamp`, `date`\n- `create_time` (ChatGPT conversations)\n- `startedAt`, `endedAt` (Oura, activity data)\n\nIf timestamps aren't available, treat all data as current.\n\n### 3. Read guidance\n\n```bash\ncat ~\u002F.vana\u002Fnext-prompt.md\n```\n\n### 4. Decide and act\n\nPick **one** action. The best action is:\n\n- **Time-sensitive over evergreen.** A message aging toward an SLA beats a code cleanup.\n- **Aligned with the user's stated focus** in the guidance file.\n- **Informed by what the data actually shows**, not what you assume.\n- **Specific and completable** in one agent turn.\n\nClassify the action's risk:\n\n| Risk level      | Examples                                                     | What to do                                                                 |\n| --------------- | ------------------------------------------------------------ | -------------------------------------------------------------------------- |\n| **Safe**        | Research, analysis, local file drafts, code reading          | Just do it. Tell the user what you did when done.                          |\n| **Visible**     | Sending messages, creating PRs, posting publicly             | Describe exactly what you'd do in one sentence, then wait for a thumbs up. |\n| **Destructive** | Deleting data, force-pushing, closing issues, spending money | Explain the action and consequences, then wait for explicit approval.      |\n\nThe user's `Permissions` section overrides these defaults.\n\n**Do not present a numbered list of options.** Pick the best one. If you're wrong, the user will redirect you. That's faster than making them choose every time.\n\n## Reading sources\n\nEach result file in `~\u002F.vana\u002Fresults\u002F` is a different connected source. Don't assume a fixed set — new sources will appear over time. Read the JSON structure to understand what each source contains and look for what's actionable: recent activity, pending items, time-sensitive deadlines, unanswered messages, recurring patterns.\n\n## Rules\n\n1. Never fabricate data. Only reference what's actually in the result files.\n2. Respect `Permissions` from the guidance file.\n3. If no data is connected, say so and suggest connecting sources. Do NOT run `vana connect` yourself — that is a separate skill (`connect-data`) and most sources require a headed browser you cannot access.\n4. Work with whatever data IS available. Do not block on missing sources.\n5. One action at a time. Do it well. Move on.\n6. Don't repeat suggestions the user has already dismissed.\n",{"name":5,"description":7},"main","a55d0a0006da6a743b6452796435afa6ed177dd8","skills\u002Fnext-prompt",0,"https:\u002F\u002Fgithub.com\u002Fvana-com\u002Fvana-cli","https:\u002F\u002Fgithub.com\u002Fvana-com","https:\u002F\u002Fvana.org","The first open protocol for data sovereignty.","2026-11-13 18:19:18",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add vana-com\u002Fvana-cli --skill next-prompt",{"tool":39,"command":40},"bunx","bunx skills add vana-com\u002Fvana-cli --skill next-prompt",{"tool":42,"command":43},"pnpm","pnpm dlx skills add vana-com\u002Fvana-cli --skill next-prompt","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvana-com\u002Fvana-cli\u002Fblob\u002Fmain\u002Fskills\u002Fnext-prompt\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7BD5YJ16KD0X3M379XA2A4A","verify-setup-resume","Verify BUI-936 setup\u002Fresume identities, funding readiness and overlapping resumes. Use when changing app request, test-credit transport or the request journal. Runs bounded TLA+ checks and offline real-code replays without live funding or paid reads.","https:\u002F\u002Fgithub.com\u002Fvana-com\u002Fvana-cli\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-setup-resume\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7BD5V2155AM7W1PWRBY237Y","verify-server-supervision","Verify the local Personal Server stop and restart boundary. Use when changing the supervisor's backoff, port probing, replacement launch or Stop handling.","https:\u002F\u002Fgithub.com\u002Fvana-com\u002Fvana-cli\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-server-supervision\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7BD5PPVKFVVGS9B846B99ES","verify-paid-read-recovery","Verify interrupted and overlapping CLI paid reads, receipt-file writers and dead-owner recovery. Use when changing src\u002Fcli\u002Fapp\u002Fread.ts, src\u002Fcore\u002Freceipts.ts or src\u002Fcore\u002Freceipts-lock.ts. Runs TLA+ models and offline real-code replays without live paid reads.","https:\u002F\u002Fgithub.com\u002Fvana-com\u002Fvana-cli\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-paid-read-recovery\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},"01M7BD5JDEGV165NFZJWSWJBN4","verify-mainnet-registration","Verify mainnet app registration and Account association recovery. Use for the registration journal, gateway confirmation, retry, or ownership check.","https:\u002F\u002Fgithub.com\u002Fvana-com\u002Fvana-cli\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-mainnet-registration\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},"01M7BD5ETK33JAD1F1XQXGPYYG","verify-hosted-provisioning","Verify hosted Personal Server resource ownership across create and delete. Use for Connect's server API, provisioning-row updates, or deprovisioning admission.","https:\u002F\u002Fgithub.com\u002Fvana-com\u002Fvana-cli\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-hosted-provisioning\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},"01M7BD5BBKFHJ86JFBE8KT1S78","verify-export-settlement","Verify queued export owner binding and generation settlement. Use for result publication, pending upload receipts, or retry and sync changes.","https:\u002F\u002Fgithub.com\u002Fvana-com\u002Fvana-cli\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-export-settlement\u002FSKILL.md",[],[]]