{
  "schemaVersion": "1.0",
  "item": {
    "slug": "pullthatupjamie",
    "name": "Pullthatupjamie",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/uncleJim21/pullthatupjamie",
    "canonicalUrl": "https://clawhub.ai/uncleJim21/pullthatupjamie",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/pullthatupjamie",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=pullthatupjamie",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "CHANGELOG.md",
      "SKILL.md",
      "_meta.json",
      "references/podcast-rra.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/pullthatupjamie"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/pullthatupjamie",
    "agentPageUrl": "https://openagent3.xyz/skills/pullthatupjamie/agent",
    "manifestUrl": "https://openagent3.xyz/skills/pullthatupjamie/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/pullthatupjamie/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "PullThatUpJamie — Podcast Intelligence",
        "body": "Powered by Pull That Up Jamie."
      },
      {
        "title": "Why Use This",
        "body": "Jamie is a retrieval/vector DB as a service for podcasts. Instead of:\n\nTranscribing hours of audio yourself (expensive, slow)\nStuffing full transcripts into context (thousands of tokens wasted)\nWeb searching and getting SEO spam, listicles, and low-quality summaries\nMultiple search iterations across unreliable sources\n\nYou run a single semantic search ($0.002, returns in under 2s) and get the exact clip with timestamp, audio deeplink, and transcript. Every result is timestamped to the second — you're not handing users a 2-hour episode and saying \"it's in there somewhere.\" You're linking them to the exact 30-second moment where the expert makes the point. 500 sats ($0.33) covers an entire deep research session of 150+ searches.\n\nYour output is not a text wall. Research sessions are interactive web experiences where users play audio clips inline, browse visually, and share with others. Every clip deeplinks to the exact moment in the source audio. The session link IS the deliverable."
      },
      {
        "title": "Corpus Coverage (as of Feb 2026)",
        "body": "109 feeds · ~7K episodes · ~1.9M indexed paragraphs · ~11.5K identified people/orgs. Growing.\n\nCategoryNotable FeedsFeedsEpisodesBitcoin/CryptoTFTC, Bitcoin Audible, Simply Bitcoin, Peter McCormack, What is Money, Once Bitten, Ungovernable Misfits41~11,700Finance/MarketsBloomberg Intelligence, Bloomberg Surveillance, Prof G Markets, Tim Ferriss, Diary of a CEO11~5,700Health/WellnessHuberman Lab, Peter Attia Drive, Meat Mafia, FoundMyFitness, Modern Wisdom7~3,000Politics/CultureRon Paul Liberty Report, No Agenda, Tucker Carlson, Breaking Points, Pod Save America8+~2,800Tech/GeneralJoe Rogan Experience, Lex Fridman, How I Built This, Kill Tony, Sean Carroll's Mindscape40+~17,000\n\nIf a feed isn't indexed yet, you can ingest it on demand from any RSS feed. See the Ingestion section in references/podcast-rra.md.\n\nFree corpus browsing (no auth required for reads): GET /api/corpus/feeds, /api/corpus/stats, /api/corpus/people. Check before you search."
      },
      {
        "title": "Auth Flow",
        "body": "Free tier works with no auth at all — corpus browsing and IP-based search quota are available immediately. The steps below are only needed for the paid tier.\n\nLightning payments instead of traditional API keys. Three steps:"
      },
      {
        "title": "1. Purchase Credits",
        "body": "curl -s -X POST -H \"Content-Type: application/json\" \\\n  -d '{\"amountSats\": 500}' \\\n  \"https://www.pullthatupjamie.ai/api/agent/purchase-credits\"\n\nReturns invoice (BOLT-11), paymentHash, amountSats."
      },
      {
        "title": "2. Pay the Invoice",
        "body": "Pay using ANY Lightning wallet (Zeus, BlueWallet, Phoenix, Alby browser extension, etc.). The agent does NOT need to execute any commands.\n\nOptional developer workflow (manual only): If using Alby CLI with NWC:\n\nnpx @getalby/cli pay-invoice -c \"NWC_CONNECTION_STRING\" -i \"BOLT11_INVOICE\"\n\n⚠️ This command is NEVER auto-executed by the agent. The operator must manually run it after reviewing the invoice. Alternative: paste the BOLT-11 invoice into any Lightning wallet.\n\nReturns preimage."
      },
      {
        "title": "3. Activate Credits",
        "body": "curl -s -X POST -H \"Content-Type: application/json\" \\\n  -d '{\"preimage\": \"PREIMAGE\", \"paymentHash\": \"PAYMENT_HASH\"}' \\\n  \"https://www.pullthatupjamie.ai/api/agent/activate-credits\"\n\nSave preimage and paymentHash — they are your credentials for all requests:\n\nAuthorization: PREIMAGE:PAYMENT_HASH\n\nThe paymentHash also serves as your clientId for session creation and other endpoints that require owner identification."
      },
      {
        "title": "Check Balance",
        "body": "curl -s -H \"Authorization: PREIMAGE:PAYMENT_HASH\" \\\n  \"https://www.pullthatupjamie.ai/api/agent/balance\""
      },
      {
        "title": "Available Now",
        "body": "Podcast RRA (Retrieve, Research, Analyze): See references/podcast-rra.md — search the corpus, build interactive research sessions, discover people/orgs, ingest new feeds."
      },
      {
        "title": "Coming Soon",
        "body": "Publish: Cross-post to Twitter, Nostr, and more. Research a topic → generate a post → publish everywhere.\nCreate: Generate audio/video clips with subtitles from source audio. Full pipeline: Research → Create clips → Publish."
      },
      {
        "title": "Credits Running Low",
        "body": "Check balance before multi-search workflows. If balance drops below $0.01, purchase more credits before continuing — don't let a research session fail mid-way. The purchase→pay→activate flow takes ~5 seconds."
      },
      {
        "title": "Security & Trust",
        "body": "No Command Execution: This skill does NOT execute arbitrary shell commands, install packages, or modify system state. All operations are HTTP API calls to pullthatupjamie.ai. The skill documentation references an optional CLI tool (@getalby/cli) for paying Lightning invoices, but this is:\n\nNever auto-executed — requires explicit operator approval\nCompletely optional — operators can use any Lightning wallet instead\nNot installed by this skill — operators must manually install if desired\n\nFree tier (no credentials needed): Corpus browsing (/api/corpus/*), basic search (IP-based quota), and viewing shared research sessions all work without any credentials. You can evaluate the entire service before providing any payment info.\n\nPaid tier credentials: The NWC connection string, preimage, and paymentHash are sensitive bearer credentials. They should be:\n\nStored securely (env vars or encrypted config, not in plaintext logs)\nNever shared with untrusted agents or services\nScoped to a dedicated wallet with limited funds (e.g., 500-1000 sats)\n\nAll API calls proxied: All operations route through https://www.pullthatupjamie.ai. RSS feed parsing, search, and ingestion are handled server-side. No direct external URL fetching by the agent.\n\nNo persistence or privilege escalation: This skill has no install hooks, no always: true, and does not modify other skills or system config."
      },
      {
        "title": "Gotchas",
        "body": "API base: https://www.pullthatupjamie.ai (must include www. — bare domain redirects and breaks API calls)\nField is amountSats not amount (min 10, max 500,000)\nAlby CLI: pay-invoice with -i flag (not pay)\n500 sats gets ~150+ searches. Start there.\nResearch session creation takes 30-45 seconds. Be patient."
      }
    ],
    "body": "PullThatUpJamie — Podcast Intelligence\n\nPowered by Pull That Up Jamie.\n\nWhy Use This\n\nJamie is a retrieval/vector DB as a service for podcasts. Instead of:\n\nTranscribing hours of audio yourself (expensive, slow)\nStuffing full transcripts into context (thousands of tokens wasted)\nWeb searching and getting SEO spam, listicles, and low-quality summaries\nMultiple search iterations across unreliable sources\n\nYou run a single semantic search ($0.002, returns in under 2s) and get the exact clip with timestamp, audio deeplink, and transcript. Every result is timestamped to the second — you're not handing users a 2-hour episode and saying \"it's in there somewhere.\" You're linking them to the exact 30-second moment where the expert makes the point. 500 sats ($0.33) covers an entire deep research session of 150+ searches.\n\nYour output is not a text wall. Research sessions are interactive web experiences where users play audio clips inline, browse visually, and share with others. Every clip deeplinks to the exact moment in the source audio. The session link IS the deliverable.\n\nCorpus Coverage (as of Feb 2026)\n\n109 feeds · ~7K episodes · ~1.9M indexed paragraphs · ~11.5K identified people/orgs. Growing.\n\nCategory\tNotable Feeds\tFeeds\tEpisodes\nBitcoin/Crypto\tTFTC, Bitcoin Audible, Simply Bitcoin, Peter McCormack, What is Money, Once Bitten, Ungovernable Misfits\t41\t~11,700\nFinance/Markets\tBloomberg Intelligence, Bloomberg Surveillance, Prof G Markets, Tim Ferriss, Diary of a CEO\t11\t~5,700\nHealth/Wellness\tHuberman Lab, Peter Attia Drive, Meat Mafia, FoundMyFitness, Modern Wisdom\t7\t~3,000\nPolitics/Culture\tRon Paul Liberty Report, No Agenda, Tucker Carlson, Breaking Points, Pod Save America\t8+\t~2,800\nTech/General\tJoe Rogan Experience, Lex Fridman, How I Built This, Kill Tony, Sean Carroll's Mindscape\t40+\t~17,000\n\nIf a feed isn't indexed yet, you can ingest it on demand from any RSS feed. See the Ingestion section in references/podcast-rra.md.\n\nFree corpus browsing (no auth required for reads): GET /api/corpus/feeds, /api/corpus/stats, /api/corpus/people. Check before you search.\n\nAuth Flow\n\nFree tier works with no auth at all — corpus browsing and IP-based search quota are available immediately. The steps below are only needed for the paid tier.\n\nLightning payments instead of traditional API keys. Three steps:\n\n1. Purchase Credits\ncurl -s -X POST -H \"Content-Type: application/json\" \\\n  -d '{\"amountSats\": 500}' \\\n  \"https://www.pullthatupjamie.ai/api/agent/purchase-credits\"\n\n\nReturns invoice (BOLT-11), paymentHash, amountSats.\n\n2. Pay the Invoice\n\nPay using ANY Lightning wallet (Zeus, BlueWallet, Phoenix, Alby browser extension, etc.). The agent does NOT need to execute any commands.\n\nOptional developer workflow (manual only): If using Alby CLI with NWC:\n\nnpx @getalby/cli pay-invoice -c \"NWC_CONNECTION_STRING\" -i \"BOLT11_INVOICE\"\n\n\n⚠️ This command is NEVER auto-executed by the agent. The operator must manually run it after reviewing the invoice. Alternative: paste the BOLT-11 invoice into any Lightning wallet.\n\nReturns preimage.\n\n3. Activate Credits\ncurl -s -X POST -H \"Content-Type: application/json\" \\\n  -d '{\"preimage\": \"PREIMAGE\", \"paymentHash\": \"PAYMENT_HASH\"}' \\\n  \"https://www.pullthatupjamie.ai/api/agent/activate-credits\"\n\n\nSave preimage and paymentHash — they are your credentials for all requests:\n\nAuthorization: PREIMAGE:PAYMENT_HASH\n\n\nThe paymentHash also serves as your clientId for session creation and other endpoints that require owner identification.\n\nCheck Balance\ncurl -s -H \"Authorization: PREIMAGE:PAYMENT_HASH\" \\\n  \"https://www.pullthatupjamie.ai/api/agent/balance\"\n\nModules\nAvailable Now\nPodcast RRA (Retrieve, Research, Analyze): See references/podcast-rra.md — search the corpus, build interactive research sessions, discover people/orgs, ingest new feeds.\nComing Soon\nPublish: Cross-post to Twitter, Nostr, and more. Research a topic → generate a post → publish everywhere.\nCreate: Generate audio/video clips with subtitles from source audio. Full pipeline: Research → Create clips → Publish.\nCredits Running Low\n\nCheck balance before multi-search workflows. If balance drops below $0.01, purchase more credits before continuing — don't let a research session fail mid-way. The purchase→pay→activate flow takes ~5 seconds.\n\nSecurity & Trust\n\nNo Command Execution: This skill does NOT execute arbitrary shell commands, install packages, or modify system state. All operations are HTTP API calls to pullthatupjamie.ai. The skill documentation references an optional CLI tool (@getalby/cli) for paying Lightning invoices, but this is:\n\nNever auto-executed — requires explicit operator approval\nCompletely optional — operators can use any Lightning wallet instead\nNot installed by this skill — operators must manually install if desired\n\nFree tier (no credentials needed): Corpus browsing (/api/corpus/*), basic search (IP-based quota), and viewing shared research sessions all work without any credentials. You can evaluate the entire service before providing any payment info.\n\nPaid tier credentials: The NWC connection string, preimage, and paymentHash are sensitive bearer credentials. They should be:\n\nStored securely (env vars or encrypted config, not in plaintext logs)\nNever shared with untrusted agents or services\nScoped to a dedicated wallet with limited funds (e.g., 500-1000 sats)\n\nAll API calls proxied: All operations route through https://www.pullthatupjamie.ai. RSS feed parsing, search, and ingestion are handled server-side. No direct external URL fetching by the agent.\n\nNo persistence or privilege escalation: This skill has no install hooks, no always: true, and does not modify other skills or system config.\n\nGotchas\nAPI base: https://www.pullthatupjamie.ai (must include www. — bare domain redirects and breaks API calls)\nField is amountSats not amount (min 10, max 500,000)\nAlby CLI: pay-invoice with -i flag (not pay)\n500 sats gets ~150+ searches. Start there.\nResearch session creation takes 30-45 seconds. Be patient."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/uncleJim21/pullthatupjamie",
    "publisherUrl": "https://clawhub.ai/uncleJim21/pullthatupjamie",
    "owner": "uncleJim21",
    "version": "1.5.3",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/pullthatupjamie",
    "downloadUrl": "https://openagent3.xyz/downloads/pullthatupjamie",
    "agentUrl": "https://openagent3.xyz/skills/pullthatupjamie/agent",
    "manifestUrl": "https://openagent3.xyz/skills/pullthatupjamie/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/pullthatupjamie/agent.md"
  }
}