[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77WDEPQKKRPDADE0RDSVKQX":3,"skill-same:01M77WDEPQKKRPDADE0RDSVKQX":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},"01M77WDEPQKKRPDADE0RDSVKQX","connect-data",null,"Collect a person's own data with the Vana CLI. Use for requests such as \"use Vana to connect my data\", source collection or refresh, and inspection of collected results. Route a missing connector to create-connector.","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\u002Fconnect-data\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: connect-data\ndescription: >\n  Collect a person's own data with the Vana CLI. Use for requests such as\n  \"use Vana to connect my data\", source collection or refresh, and inspection\n  of collected results. Route a missing connector to create-connector.\n---\n\n# Connect personal data\n\nRead workflows with `vana skills show \u003Cid> --json`. The response includes full\ninstructions and required reference content; installation into the agent's\nharness is optional. Use `connect-data`, `create-connector` or `builder` as the\nrequested goal needs them.\n\nUse the Vana CLI for discovery, collection, owner identity and results. The\nperson completes provider sign-in and human checks in the browser when needed.\nApp access to collected data is a separate Builder workflow.\n\nStart from the person's data goal, such as \"Use Vana to collect my highlights\".\nSelect and load the required skills yourself. Continue through discovery,\nany necessary connector authoring, collection, and result inspection. The\nperson does not need to name a skill, choose a helper, or supply another\nimplementation prompt. Ask for account\u002Fdata choices and human authentication.\nThe public\n[walkthrough](https:\u002F\u002Fgithub.com\u002Fvana-com\u002Fvana-cli\u002Fblob\u002Fmain\u002Fskills\u002FREADME.md)\npairs the user's part with the commands.\n\n## Select the CLI and owner context\n\nCheck the available CLI:\n\n```bash\nvana --version\nvana --help\n```\n\nIf it is missing, use the [official installation instructions](https:\u002F\u002Fgithub.com\u002Fvana-com\u002Fvana-cli#readme).\nThe published package is `vana-cli`, with a `vana` binary.\n\nWhen testing local changes, run these from the actual `vana-cli` checkout:\n\n```bash\npnpm build\nnode dist\u002Fcli\u002Fbin.js --help\n```\n\nUse that checkout's absolute `dist\u002Fcli\u002Fbin.js` path in place of `vana` for the\nremaining commands. Keep the same entry point throughout the task.\n\nPreserve the selected `VANA_HOME`, Account deployment (`VANA_ENV` or\n`VANA_ACCOUNT_URL`) and network. Carry the same `--network` option through\ncommands when a network was explicitly selected. Check before collecting:\n\n```bash\nvana whoami --json\nvana status --json\nvana sources --json\nvana connectors list --json\n```\n\n`vana whoami` identifies the person. `vana app whoami` identifies an app and\ndoes not select the person's login. A Personal Server session alone is not an\nauthenticated Vana Account. Inspect the selected server and any servers listed\nunder other accounts before writing data.\n\nFor installation or runtime problems, inspect `vana doctor` and `vana logs`.\nIf the browser runtime is missing and collection needs it, run `vana setup --yes`.\nUse the CLI's recovery command with its environment and network intact.\n\n## Select the source\n\nUse `sources` for available sources and `connectors list` for saved checkout\npaths. Replace `\u003Csource>` with the selected key and inspect it:\n\n```bash\nvana sources \u003Csource> --json\n```\n\nWhen changing a local connector, read its manifest from the path reported by\n`connectors list`.\n\nIf the source is missing or needs a code change, read Create Connector:\n\n```bash\nvana skills show create-connector --json\n```\n\nRead its returned `instructions` and required `resources`. That skill owns the\ncurrent PDP-Connect authoring and local-checkout workflow. Check upstream's\nexisting connectors before deciding a provider needs a new implementation;\nan empty or unavailable catalog alone does not establish that.\n\nReuse discovery already completed in this task rather than repeating the same\nsearch. Connector creation returns a directory, connector key and selected\nstreams to this collection workflow; it does not require Vana sign-in.\n\n## Prepare Vana before collection\n\nOnce the connector is available, establish the Vana account and intended server\nBEFORE requesting source credentials or running the provider. Reuse a valid\nsession. If signed out, run `vana login --json`, relay the returned browser URI,\nand wait for the person to finish signing in there. No code is entered in the\nterminal. Then check `vana whoami --json` and `vana status --json` in the same\nhome, Account deployment and network. JSON login does not start a server or\napprove its CLI session. Follow the reported server-start or approval command;\nan existing server owned by another account is not this person's destination.\nIf `VANA_PS_URL` or `VANA_PERSONAL_SERVER_URL` explicitly selects a server, use\nthe collection command's reported sign-in remedy: it targets Account sign-in\nand preserves the selected server in the collection retry command.\n\nEvery collection entry checks readiness. Automated runs return `needs_input`\n(exit 7) for Vana sign-in or server approval, or `personal_server_unavailable`\n(exit 5) for an unavailable\u002Funverified destination, with `reason` and `remedy`.\nFollow the remedy, then retry the ORIGINAL collection command including `--from`,\n`--streams` and its context. These outcomes precede connector credential prompts\nand provider reads. A bare `VANA_SESSION_TOKEN` has no verified owner identity;\nuse a saved Account sign-in instead. Do not collect anonymously and try to\nassign the export to an account later.\n\n## Collect and handle human input\n\nFor an agent-controlled browser or protected local credential handoff, run\ncollection in a background process you can inspect while the person signs in:\n\n```bash\nvana connect \u003Csource> --json --ipc\n```\n\nFor a Collection Profile source, select only the requested manifest stream\nnames with `--streams \u003Cstream,stream>`. An explicit source is required.\nFor a local implementation, add `--from \u002Fabsolute\u002Fpath\u002Fto\u002Fdata-connectors`\nwithout registering a persistent override for a one-off trial.\n\nFor a person entering a token or password, give them the exact interactive\ncommand to run in their own terminal, with the real source\u002Fpath\u002Fstreams and\nselected network. Explain where to paste the secret and that hidden input\ndoes not echo. Verify secret fields have password metadata in the connector's\ninteraction schema. Keep the secret out of chat, command arguments, scripts,\nand logs. A credential form in the chat is not the local terminal prompt.\n\nKeep progress visible. In agent mode, relay meaningful stage\u002Fcount events;\nin human mode, leave the CLI's progress on the terminal. `vana connect`\ncollects and ingests in one run. The upstream developer runner is optional\ndiagnostics, not a prerequisite that collects from the provider a second time.\n\nRead the emitted events until the process finishes. A Collection Profile\nconnector can request browser sign-in through `headed-required` and then a\n`needs-input` event. Complete that handoff rather than treating every browser\nsource as unsupported by agents.\n\nFor `needs-input` events with `pendingInputPath` and `responseInputPath`:\n\n1. Read the exact pending file and its requested fields.\n2. Have the person complete browser sign-in or a human check. For secret\n   fields, use an available protected local input channel. If none is available,\n   stop\u002Fcancel this waiting run and hand over the interactive terminal command.\n3. Write the resulting JSON to the exact response path using a file API.\n   Restrict credential files to the current user; keep secrets out of chat,\n   shell arguments, and logs.\n4. For a Collection Profile manual action with no fields, write `{}` only\n   after the person confirms completion. To decline, write `{\"status\":\"cancelled\"}`.\n5. Continue reading events. Further prompts may follow, and input can expire.\n\nUse the running CLI's message for legacy connectors that require a manual\nterminal or browser handoff. An intermediate event is not a successful collection.\n\n`--no-input` refuses human prompts, but it can still collect and upload data\nwhen a session is available. Use `status` and `data` commands for inspection.\n\n## Verify the result\n\nDistinguish `connected_and_ingested` from `connected_local_only`. Local\ncollection does not prove Personal Server ingestion or delivery to an app.\nInspect the result and logs without starting another collection:\n\n```bash\nvana data list\nvana data show \u003Csource>\nvana data path \u003Csource>\nvana logs \u003Csource>\n```\n\nSummarize the requested records, any skipped streams, and whether ingestion\nsucceeded. Preserve saved results and follow the reported recovery action on\nfailure. Do not rerun automatically just to obtain a cleaner transcript.\nInspect private records locally and report counts\u002Fstatus instead of copying\npayloads into chat or a repository. Compare recognizable records and any\nindependent provider counts before claiming completeness.\n\nIf the person wants an app to consume the data, read\n`vana skills show builder --json` and follow its instructions and resources.\nKeep app identity, explicit\nconsent and paid app reads separate from owner-side collection.\n","# Connect personal data\n\nRead workflows with `vana skills show \u003Cid> --json`. The response includes full\ninstructions and required reference content; installation into the agent's\nharness is optional. Use `connect-data`, `create-connector` or `builder` as the\nrequested goal needs them.\n\nUse the Vana CLI for discovery, collection, owner identity and results. The\nperson completes provider sign-in and human checks in the browser when needed.\nApp access to collected data is a separate Builder workflow.\n\nStart from the person's data goal, such as \"Use Vana to collect my highlights\".\nSelect and load the required skills yourself. Continue through discovery,\nany necessary connector authoring, collection, and result inspection. The\nperson does not need to name a skill, choose a helper, or supply another\nimplementation prompt. Ask for account\u002Fdata choices and human authentication.\nThe public\n[walkthrough](https:\u002F\u002Fgithub.com\u002Fvana-com\u002Fvana-cli\u002Fblob\u002Fmain\u002Fskills\u002FREADME.md)\npairs the user's part with the commands.\n\n## Select the CLI and owner context\n\nCheck the available CLI:\n\n```bash\nvana --version\nvana --help\n```\n\nIf it is missing, use the [official installation instructions](https:\u002F\u002Fgithub.com\u002Fvana-com\u002Fvana-cli#readme).\nThe published package is `vana-cli`, with a `vana` binary.\n\nWhen testing local changes, run these from the actual `vana-cli` checkout:\n\n```bash\npnpm build\nnode dist\u002Fcli\u002Fbin.js --help\n```\n\nUse that checkout's absolute `dist\u002Fcli\u002Fbin.js` path in place of `vana` for the\nremaining commands. Keep the same entry point throughout the task.\n\nPreserve the selected `VANA_HOME`, Account deployment (`VANA_ENV` or\n`VANA_ACCOUNT_URL`) and network. Carry the same `--network` option through\ncommands when a network was explicitly selected. Check before collecting:\n\n```bash\nvana whoami --json\nvana status --json\nvana sources --json\nvana connectors list --json\n```\n\n`vana whoami` identifies the person. `vana app whoami` identifies an app and\ndoes not select the person's login. A Personal Server session alone is not an\nauthenticated Vana Account. Inspect the selected server and any servers listed\nunder other accounts before writing data.\n\nFor installation or runtime problems, inspect `vana doctor` and `vana logs`.\nIf the browser runtime is missing and collection needs it, run `vana setup --yes`.\nUse the CLI's recovery command with its environment and network intact.\n\n## Select the source\n\nUse `sources` for available sources and `connectors list` for saved checkout\npaths. Replace `\u003Csource>` with the selected key and inspect it:\n\n```bash\nvana sources \u003Csource> --json\n```\n\nWhen changing a local connector, read its manifest from the path reported by\n`connectors list`.\n\nIf the source is missing or needs a code change, read Create Connector:\n\n```bash\nvana skills show create-connector --json\n```\n\nRead its returned `instructions` and required `resources`. That skill owns the\ncurrent PDP-Connect authoring and local-checkout workflow. Check upstream's\nexisting connectors before deciding a provider needs a new implementation;\nan empty or unavailable catalog alone does not establish that.\n\nReuse discovery already completed in this task rather than repeating the same\nsearch. Connector creation returns a directory, connector key and selected\nstreams to this collection workflow; it does not require Vana sign-in.\n\n## Prepare Vana before collection\n\nOnce the connector is available, establish the Vana account and intended server\nBEFORE requesting source credentials or running the provider. Reuse a valid\nsession. If signed out, run `vana login --json`, relay the returned browser URI,\nand wait for the person to finish signing in there. No code is entered in the\nterminal. Then check `vana whoami --json` and `vana status --json` in the same\nhome, Account deployment and network. JSON login does not start a server or\napprove its CLI session. Follow the reported server-start or approval command;\nan existing server owned by another account is not this person's destination.\nIf `VANA_PS_URL` or `VANA_PERSONAL_SERVER_URL` explicitly selects a server, use\nthe collection command's reported sign-in remedy: it targets Account sign-in\nand preserves the selected server in the collection retry command.\n\nEvery collection entry checks readiness. Automated runs return `needs_input`\n(exit 7) for Vana sign-in or server approval, or `personal_server_unavailable`\n(exit 5) for an unavailable\u002Funverified destination, with `reason` and `remedy`.\nFollow the remedy, then retry the ORIGINAL collection command including `--from`,\n`--streams` and its context. These outcomes precede connector credential prompts\nand provider reads. A bare `VANA_SESSION_TOKEN` has no verified owner identity;\nuse a saved Account sign-in instead. Do not collect anonymously and try to\nassign the export to an account later.\n\n## Collect and handle human input\n\nFor an agent-controlled browser or protected local credential handoff, run\ncollection in a background process you can inspect while the person signs in:\n\n```bash\nvana connect \u003Csource> --json --ipc\n```\n\nFor a Collection Profile source, select only the requested manifest stream\nnames with `--streams \u003Cstream,stream>`. An explicit source is required.\nFor a local implementation, add `--from \u002Fabsolute\u002Fpath\u002Fto\u002Fdata-connectors`\nwithout registering a persistent override for a one-off trial.\n\nFor a person entering a token or password, give them the exact interactive\ncommand to run in their own terminal, with the real source\u002Fpath\u002Fstreams and\nselected network. Explain where to paste the secret and that hidden input\ndoes not echo. Verify secret fields have password metadata in the connector's\ninteraction schema. Keep the secret out of chat, command arguments, scripts,\nand logs. A credential form in the chat is not the local terminal prompt.\n\nKeep progress visible. In agent mode, relay meaningful stage\u002Fcount events;\nin human mode, leave the CLI's progress on the terminal. `vana connect`\ncollects and ingests in one run. The upstream developer runner is optional\ndiagnostics, not a prerequisite that collects from the provider a second time.\n\nRead the emitted events until the process finishes. A Collection Profile\nconnector can request browser sign-in through `headed-required` and then a\n`needs-input` event. Complete that handoff rather than treating every browser\nsource as unsupported by agents.\n\nFor `needs-input` events with `pendingInputPath` and `responseInputPath`:\n\n1. Read the exact pending file and its requested fields.\n2. Have the person complete browser sign-in or a human check. For secret\n   fields, use an available protected local input channel. If none is available,\n   stop\u002Fcancel this waiting run and hand over the interactive terminal command.\n3. Write the resulting JSON to the exact response path using a file API.\n   Restrict credential files to the current user; keep secrets out of chat,\n   shell arguments, and logs.\n4. For a Collection Profile manual action with no fields, write `{}` only\n   after the person confirms completion. To decline, write `{\"status\":\"cancelled\"}`.\n5. Continue reading events. Further prompts may follow, and input can expire.\n\nUse the running CLI's message for legacy connectors that require a manual\nterminal or browser handoff. An intermediate event is not a successful collection.\n\n`--no-input` refuses human prompts, but it can still collect and upload data\nwhen a session is available. Use `status` and `data` commands for inspection.\n\n## Verify the result\n\nDistinguish `connected_and_ingested` from `connected_local_only`. Local\ncollection does not prove Personal Server ingestion or delivery to an app.\nInspect the result and logs without starting another collection:\n\n```bash\nvana data list\nvana data show \u003Csource>\nvana data path \u003Csource>\nvana logs \u003Csource>\n```\n\nSummarize the requested records, any skipped streams, and whether ingestion\nsucceeded. Preserve saved results and follow the reported recovery action on\nfailure. Do not rerun automatically just to obtain a cleaner transcript.\nInspect private records locally and report counts\u002Fstatus instead of copying\npayloads into chat or a repository. Compare recognizable records and any\nindependent provider counts before claiming completeness.\n\nIf the person wants an app to consume the data, read\n`vana skills show builder --json` and follow its instructions and resources.\nKeep app identity, explicit\nconsent and paid app reads separate from owner-side collection.\n",{"name":5,"description":7},"main","a55d0a0006da6a743b6452796435afa6ed177dd8","skills\u002Fconnect-data",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 connect-data",{"tool":39,"command":40},"bunx","bunx skills add vana-com\u002Fvana-cli --skill connect-data",{"tool":42,"command":43},"pnpm","pnpm dlx skills add vana-com\u002Fvana-cli --skill connect-data","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvana-com\u002Fvana-cli\u002Fblob\u002Fmain\u002Fskills\u002Fconnect-data\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",[],[]]