{ "schemaVersion": "1.0", "item": { "slug": "ted-talk", "name": "TED Talk", "source": "tencent", "type": "skill", "category": "内容创作", "sourceUrl": "https://clawhub.ai/leegitw/ted-talk", "canonicalUrl": "https://clawhub.ai/leegitw/ted-talk", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/ted-talk", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ted-talk", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.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/ted-talk" }, "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/ted-talk", "agentPageUrl": "https://openagent3.xyz/skills/ted-talk/agent", "manifestUrl": "https://openagent3.xyz/skills/ted-talk/agent.json", "briefUrl": "https://openagent3.xyz/skills/ted-talk/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": "ted-talk (話)", "body": "Transform technical conversations and insights into full-length TED-style talks.\nCreates comprehensive 40-50 minute presentations with hooks, concrete examples,\nbroader implications, and Q&A preparation.\n\nTrigger: 明示呼出 (explicit invocation) or when deep technical insight emerges\n\nCore insight: \"The best technical talks don't just explain what — they reveal why\nit matters, with examples concrete enough to apply and implications broad enough to inspire.\"" }, { "title": "Installation", "body": "openclaw install leegitw/ted-talk\n\nDependencies: None (standalone creative skill)\n\nData handling: This skill synthesizes content from user-supplied input or the current\nconversation context (default). It does NOT read files from the workspace or access project\nartifacts directly. Results are returned to the invoking agent, who decides how to use them." }, { "title": "What This Solves", "body": "Technical insights often stay trapped in conversations. A well-structured talk\nmakes them teachable and shareable. This skill:\n\nExpands technical conversations into comprehensive narratives\nGrounds abstract insights in concrete, real-world examples\nPrepares for audience questions and objections\n\nThe insight: A 50-minute talk forces you to truly understand something — if you\ncan't explain the why, address objections, and connect to broader implications,\nyou don't fully understand it." }, { "title": "Usage", "body": "/ted [topic]" }, { "title": "Arguments", "body": "ArgumentRequiredDescriptiontopicNoTopic focus (default: synthesize current conversation)" }, { "title": "Pre-Requisites", "body": "Before creating a TED talk, ensure:\n\nSufficient conversation depth — Surface-level topics make shallow talks\nClear narrative arc — Problem → Discovery → Solution → Impact\nMain work documented — Save current progress first if mid-task\nConcrete context available — Real problems, real decisions, real outcomes" }, { "title": "Context Understanding Checklist", "body": "You must be able to answer:\n\nQuestionWhat It MeansCore insight?Not \"we talked about X\" but \"we discovered X solves Y\"Problem solved?The pain point, not just the topicWhy, not just what?The reasoning, not just the outcomeConcrete examples?Specific details from the context providedBroader implications?Why does this matter beyond the immediate context?" }, { "title": "Red Flags (Don't Create)", "body": "Surface-level summary of conversation\nDon't understand why a decision was made\nNo concrete examples to draw from\nInsight doesn't have broader implications\nWould be padding the talk with generic content" }, { "title": "TED Talk Structure", "body": "## TED Talk: \"[Talk Title]\"\n\n### Opening (0:00-2:00)\n[Hook with relatable problem]\n\n### Setup: Why This Matters (2:00-6:00)\n[Context, stakes, personal connection]\n\n### The Problem (6:00-12:00)\n[Deep dive into the pain point]\n\n### Core Concept (12:00-25:00)\n[Explain the insight thoroughly]\n\n### Real-World Examples (25:00-38:00)\n[Concrete applications with specifics]\n\n### Broader Implications (38:00-45:00)\n[Why this matters beyond immediate context]\n\n### Closing (45:00-48:00)\n[Call to action or reflection]\n\n### Q&A Preparation (48:00-50:00)\n[Common objections and responses]" }, { "title": "Talk Rules", "body": "RuleDescriptionFull 40-50 minutesNOT a summary — comprehensive contentHook with problemStart with relatable pain, not abstract conceptConcrete examplesSpecific, real details — not hypothetical scenariosAddress objectionsQ&A section anticipates pushbackNo fillerEvery section should teach somethingAccessible but not condescendingTechnical depth without jargon overload" }, { "title": "Example: Section Length Guide", "body": "SectionDurationPurposeOpening2 minHook with relatable problemSetup4 minWhy this matters, stakesProblem6 minDeep dive into pain pointCore Concept13 minThe main insight, thoroughly explainedExamples13 minReal-world applicationsImplications7 minBroader impactClosing3 minCall to actionQ&A Prep2 minObjections and responses" }, { "title": "Step 1: Synthesize Conversation", "body": "Read full conversation context\nIdentify key decisions, \"aha\" moments\nExtract core insight or pattern\nNote concrete details from the context provided" }, { "title": "Step 2: Identify Narrative Arc", "body": "ElementQuestionProblemWhat was broken/painful?DiscoveryWhat did we learn?SolutionWhat pattern emerged?ImpactWhy does this matter?" }, { "title": "Step 3: Expand to Talk", "body": "For each section:\n\nOpening: What relatable problem hooks the audience?\nSetup: Why should they care? What's at stake?\nProblem: Deep dive — make them feel the pain\nConcept: Explain thoroughly, with analogies if helpful\nExamples: Specific, concrete, from real work\nImplications: Connect to broader context\nClosing: What should they do with this knowledge?\nQ&A: What will skeptics ask?" }, { "title": "Step 4: Ground in Reality", "body": "TED talks resonate when they're specific, not hypothetical. Draw from:\n\nReal problems encountered (not abstract scenarios)\nActual decisions and their reasoning\nSpecific outcomes and what changed\nStories with concrete details the audience can visualize\n\nUse what the user provides — don't invent specifics or assume access to files." }, { "title": "Input: Bootstrap Observability Insight", "body": "Context: Discovered reproduce-to-debug problem. Introduced Bootstrap → Learn → Enforce phases." }, { "title": "Output Excerpt", "body": "Title: \"Bootstrap Before You Break: Why Greenfield Systems Need to Learn What Normal Looks Like\"" }, { "title": "Opening (0:00-2:00)", "body": "It's 3 AM. Your pager goes off. The system is on fire — users are complaining,\nsomething is clearly wrong. You pull up your logs and... nothing. Metrics?\nFlat lines. Traces? What traces?\n\nYou're debugging blind.\n\nAnd the worst part? You built this system. You know every line of code.\nBut you have no idea what's happening.\n\nThis happened to me six months ago. And the solution we found changed how\nI think about every system I'll ever build." }, { "title": "Setup: Why This Matters (2:00-6:00)", "body": "We've all been taught: instrument your code, add logging, set up dashboards.\nThe standard advice works great — for existing systems.\n\nBut what about greenfield? What about day one?\n\nHere's the thing nobody tells you: you can't set meaningful thresholds\nfor a system that's never run in production. What's a normal response time?\nWhat's an acceptable error rate? You don't know. You can't know. The system\nhasn't told you yet.\n\n[... continues for full 50 minutes ...]\n\nNote: Full TED talk outputs are 40-50 minutes of content. This excerpt demonstrates the opening sections." }, { "title": "Q&A Preparation", "body": "Q: \"This seems like overkill for small projects.\"\n\nA: Fair point. The full three-phase approach is designed for systems where\ndebugging cost is high — production services, distributed systems, anything\nwhere \"just add a log line and redeploy\" isn't an option. For a weekend\nproject, you probably don't need this. But the core insight — bootstrap\nbefore you enforce — scales down too. Even a simple log.Debug everywhere\nis a form of bootstrap phase.\n\nQ: \"How long should the bootstrap phase last?\"\n\nA: We found 7-14 days covers most patterns. You want at least one full\nbusiness cycle (weekly patterns), and ideally two. The key indicator is\nwhen your anomaly detection stops alerting on normal behavior." }, { "title": "Integration", "body": "Layer: Creative\nDepends on: None (standalone)\nUsed by: side-quests (combo skill)\nComplements: insight-song, visual-concept" }, { "title": "Failure Modes", "body": "ConditionBehaviorInsufficient contextAsk clarifying questions firstNo concrete contextAsk for specific details before proceedingSurface-level insightSuggest deeper exploration firstNo broader implicationsSuggest finding wider relevance" }, { "title": "Security Considerations", "body": "Input sources:\n\nUser-supplied context (if provided)\nCurrent conversation context (default)\n\nWhat this skill does NOT do:\n\nRead files from the workspace\nAccess project artifacts directly\nSend data to external services\nRecord or publish content\n\nOutput behavior:\nThis skill returns the full TED talk directly to the invoking agent. The agent can then\ndisplay, save, or pass the result to another skill as needed.\n\nNote on concrete details: The skill uses only what the user provides in the conversation\nor as explicit input. It does not access workspace files. Review output before sharing\nexternally to ensure no sensitive information is included.\n\nProvenance note:\nThis skill is developed by Live Neon (https://github.com/live-neon/skills) and published\nto ClawHub under the leegitw account. Both refer to the same maintainer." }, { "title": "Quality Checklist", "body": "Can explain core insight in one sentence\n Opening hooks with relatable problem\n Full 40-50 minutes of substantial content\n Concrete details from provided context included\n Broader implications explored\n Q&A addresses likely objections\n No filler or generic padding\n Accessible to non-experts but not condescending" }, { "title": "Acceptance Criteria", "body": "/ted synthesizes input or conversation into full-length talk\n Output includes all sections (opening through Q&A)\n Talk is 40-50 minutes of substantial content\n Concrete details from input/conversation included\n Q&A section addresses common objections\n Result returned to invoking agent\n\nPart of the Live Neon Creative Suite." } ], "body": "ted-talk (話)\n\nTransform technical conversations and insights into full-length TED-style talks. Creates comprehensive 40-50 minute presentations with hooks, concrete examples, broader implications, and Q&A preparation.\n\nTrigger: 明示呼出 (explicit invocation) or when deep technical insight emerges\n\nCore insight: \"The best technical talks don't just explain what — they reveal why it matters, with examples concrete enough to apply and implications broad enough to inspire.\"\n\nInstallation\nopenclaw install leegitw/ted-talk\n\n\nDependencies: None (standalone creative skill)\n\nData handling: This skill synthesizes content from user-supplied input or the current conversation context (default). It does NOT read files from the workspace or access project artifacts directly. Results are returned to the invoking agent, who decides how to use them.\n\nWhat This Solves\n\nTechnical insights often stay trapped in conversations. A well-structured talk makes them teachable and shareable. This skill:\n\nExpands technical conversations into comprehensive narratives\nGrounds abstract insights in concrete, real-world examples\nPrepares for audience questions and objections\n\nThe insight: A 50-minute talk forces you to truly understand something — if you can't explain the why, address objections, and connect to broader implications, you don't fully understand it.\n\nUsage\n/ted [topic]\n\nArguments\nArgument\tRequired\tDescription\ntopic\tNo\tTopic focus (default: synthesize current conversation)\nPre-Requisites\n\nBefore creating a TED talk, ensure:\n\nSufficient conversation depth — Surface-level topics make shallow talks\nClear narrative arc — Problem → Discovery → Solution → Impact\nMain work documented — Save current progress first if mid-task\nConcrete context available — Real problems, real decisions, real outcomes\nContext Understanding Checklist\n\nYou must be able to answer:\n\nQuestion\tWhat It Means\nCore insight?\tNot \"we talked about X\" but \"we discovered X solves Y\"\nProblem solved?\tThe pain point, not just the topic\nWhy, not just what?\tThe reasoning, not just the outcome\nConcrete examples?\tSpecific details from the context provided\nBroader implications?\tWhy does this matter beyond the immediate context?\nRed Flags (Don't Create)\nSurface-level summary of conversation\nDon't understand why a decision was made\nNo concrete examples to draw from\nInsight doesn't have broader implications\nWould be padding the talk with generic content\nOutput Format\nTED Talk Structure\n## TED Talk: \"[Talk Title]\"\n\n### Opening (0:00-2:00)\n[Hook with relatable problem]\n\n### Setup: Why This Matters (2:00-6:00)\n[Context, stakes, personal connection]\n\n### The Problem (6:00-12:00)\n[Deep dive into the pain point]\n\n### Core Concept (12:00-25:00)\n[Explain the insight thoroughly]\n\n### Real-World Examples (25:00-38:00)\n[Concrete applications with specifics]\n\n### Broader Implications (38:00-45:00)\n[Why this matters beyond immediate context]\n\n### Closing (45:00-48:00)\n[Call to action or reflection]\n\n### Q&A Preparation (48:00-50:00)\n[Common objections and responses]\n\nTalk Rules\nRule\tDescription\nFull 40-50 minutes\tNOT a summary — comprehensive content\nHook with problem\tStart with relatable pain, not abstract concept\nConcrete examples\tSpecific, real details — not hypothetical scenarios\nAddress objections\tQ&A section anticipates pushback\nNo filler\tEvery section should teach something\nAccessible but not condescending\tTechnical depth without jargon overload\nExample: Section Length Guide\nSection\tDuration\tPurpose\nOpening\t2 min\tHook with relatable problem\nSetup\t4 min\tWhy this matters, stakes\nProblem\t6 min\tDeep dive into pain point\nCore Concept\t13 min\tThe main insight, thoroughly explained\nExamples\t13 min\tReal-world applications\nImplications\t7 min\tBroader impact\nClosing\t3 min\tCall to action\nQ&A Prep\t2 min\tObjections and responses\nCore Logic\nStep 1: Synthesize Conversation\nRead full conversation context\nIdentify key decisions, \"aha\" moments\nExtract core insight or pattern\nNote concrete details from the context provided\nStep 2: Identify Narrative Arc\nElement\tQuestion\nProblem\tWhat was broken/painful?\nDiscovery\tWhat did we learn?\nSolution\tWhat pattern emerged?\nImpact\tWhy does this matter?\nStep 3: Expand to Talk\n\nFor each section:\n\nOpening: What relatable problem hooks the audience?\nSetup: Why should they care? What's at stake?\nProblem: Deep dive — make them feel the pain\nConcept: Explain thoroughly, with analogies if helpful\nExamples: Specific, concrete, from real work\nImplications: Connect to broader context\nClosing: What should they do with this knowledge?\nQ&A: What will skeptics ask?\nStep 4: Ground in Reality\n\nTED talks resonate when they're specific, not hypothetical. Draw from:\n\nReal problems encountered (not abstract scenarios)\nActual decisions and their reasoning\nSpecific outcomes and what changed\nStories with concrete details the audience can visualize\n\nUse what the user provides — don't invent specifics or assume access to files.\n\nExample\nInput: Bootstrap Observability Insight\n\nContext: Discovered reproduce-to-debug problem. Introduced Bootstrap → Learn → Enforce phases.\n\nOutput Excerpt\n\nTitle: \"Bootstrap Before You Break: Why Greenfield Systems Need to Learn What Normal Looks Like\"\n\nOpening (0:00-2:00)\n\nIt's 3 AM. Your pager goes off. The system is on fire — users are complaining, something is clearly wrong. You pull up your logs and... nothing. Metrics? Flat lines. Traces? What traces?\n\nYou're debugging blind.\n\nAnd the worst part? You built this system. You know every line of code. But you have no idea what's happening.\n\nThis happened to me six months ago. And the solution we found changed how I think about every system I'll ever build.\n\nSetup: Why This Matters (2:00-6:00)\n\nWe've all been taught: instrument your code, add logging, set up dashboards. The standard advice works great — for existing systems.\n\nBut what about greenfield? What about day one?\n\nHere's the thing nobody tells you: you can't set meaningful thresholds for a system that's never run in production. What's a normal response time? What's an acceptable error rate? You don't know. You can't know. The system hasn't told you yet.\n\n[... continues for full 50 minutes ...]\n\nNote: Full TED talk outputs are 40-50 minutes of content. This excerpt demonstrates the opening sections.\n\nQ&A Preparation\n\nQ: \"This seems like overkill for small projects.\"\n\nA: Fair point. The full three-phase approach is designed for systems where debugging cost is high — production services, distributed systems, anything where \"just add a log line and redeploy\" isn't an option. For a weekend project, you probably don't need this. But the core insight — bootstrap before you enforce — scales down too. Even a simple log.Debug everywhere is a form of bootstrap phase.\n\nQ: \"How long should the bootstrap phase last?\"\n\nA: We found 7-14 days covers most patterns. You want at least one full business cycle (weekly patterns), and ideally two. The key indicator is when your anomaly detection stops alerting on normal behavior.\n\nIntegration\nLayer: Creative\nDepends on: None (standalone)\nUsed by: side-quests (combo skill)\nComplements: insight-song, visual-concept\nFailure Modes\nCondition\tBehavior\nInsufficient context\tAsk clarifying questions first\nNo concrete context\tAsk for specific details before proceeding\nSurface-level insight\tSuggest deeper exploration first\nNo broader implications\tSuggest finding wider relevance\nSecurity Considerations\n\nInput sources:\n\nUser-supplied context (if provided)\nCurrent conversation context (default)\n\nWhat this skill does NOT do:\n\nRead files from the workspace\nAccess project artifacts directly\nSend data to external services\nRecord or publish content\n\nOutput behavior: This skill returns the full TED talk directly to the invoking agent. The agent can then display, save, or pass the result to another skill as needed.\n\nNote on concrete details: The skill uses only what the user provides in the conversation or as explicit input. It does not access workspace files. Review output before sharing externally to ensure no sensitive information is included.\n\nProvenance note: This skill is developed by Live Neon (https://github.com/live-neon/skills) and published to ClawHub under the leegitw account. Both refer to the same maintainer.\n\nQuality Checklist\n Can explain core insight in one sentence\n Opening hooks with relatable problem\n Full 40-50 minutes of substantial content\n Concrete details from provided context included\n Broader implications explored\n Q&A addresses likely objections\n No filler or generic padding\n Accessible to non-experts but not condescending\nAcceptance Criteria\n /ted synthesizes input or conversation into full-length talk\n Output includes all sections (opening through Q&A)\n Talk is 40-50 minutes of substantial content\n Concrete details from input/conversation included\n Q&A section addresses common objections\n Result returned to invoking agent\n\nPart of the Live Neon Creative Suite." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/leegitw/ted-talk", "publisherUrl": "https://clawhub.ai/leegitw/ted-talk", "owner": "leegitw", "version": "1.0.2", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/ted-talk", "downloadUrl": "https://openagent3.xyz/downloads/ted-talk", "agentUrl": "https://openagent3.xyz/skills/ted-talk/agent", "manifestUrl": "https://openagent3.xyz/skills/ted-talk/agent.json", "briefUrl": "https://openagent3.xyz/skills/ted-talk/agent.md" } }