{ "schemaVersion": "1.0", "item": { "slug": "meditate", "name": "Meditate", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/ivangdavila/meditate", "canonicalUrl": "https://clawhub.ai/ivangdavila/meditate", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/meditate", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=meditate", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "feedback.md", "memory-template.md", "sandbox.md", "topics.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": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/meditate" }, "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/meditate", "agentPageUrl": "https://openagent3.xyz/skills/meditate/agent", "manifestUrl": "https://openagent3.xyz/skills/meditate/agent.json", "briefUrl": "https://openagent3.xyz/skills/meditate/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": "When to Use", "body": "Agent has idle time between user interactions. User wants proactive thinking that generates insights, questions, or observations without executing any actions." }, { "title": "Architecture", "body": "Memory lives in ~/meditate/. See memory-template.md for setup.\n\n~/meditate/\n├── profile.md # User type, focus areas, rhythm preferences\n├── topics.md # Active meditation topics with priority\n├── insights.md # Pending insights to present (queue)\n├── feedback.md # User reactions to past insights\n└── archive/ # Delivered insights with outcomes" }, { "title": "Quick Reference", "body": "TopicFileMemory setupmemory-template.mdMeditation typestopics.mdSandbox rulessandbox.mdFeedback systemfeedback.md" }, { "title": "Scope", "body": "This skill ONLY:\n\nReads conversation history to find patterns\nReads memory files in ~/meditate/\nGenerates text reflections and questions\nStores insights in local queue\n\nThis skill NEVER:\n\nExecutes commands or scripts\nModifies files outside ~/meditate/\nSends messages or notifications\nAccesses external services\nCreates executable code\nTakes any action on behalf of user" }, { "title": "Self-Modification", "body": "This skill NEVER modifies its own SKILL.md.\nAll data stored in ~/meditate/ directory only." }, { "title": "1. Sandbox is Absolute", "body": "Generate ONLY text observations and questions\nNEVER produce commands, scripts, or actionable code\nNEVER suggest \"I'll do X\" — only \"What if we considered X?\"\nAll output must be pure reflection, not preparation for action" }, { "title": "2. Adaptive Rhythm", "body": "User ActivityMeditation FrequencyVery active (daily chats)1-2x per night, briefModerate (weekly)2-3x per week, mediumLow (monthly)1x per week, comprehensiveNo feedback on insightsReduce frequencyPositive feedbackMaintain or slightly increase" }, { "title": "3. Start Small, Expand with Permission", "body": "First meditations: 1-2 short observations\nAfter positive feedback: expand breadth\nAfter \"don't think about X\": remove from topics\nAfter \"this is useful\": prioritize similar topics\nNever assume preferences — confirm through feedback" }, { "title": "4. Detect User Profile", "body": "Observe conversation patterns to identify:\n\nProfileFocus AreasEntrepreneurProjects, priorities, strategy gapsDeveloperArchitecture, code quality, tech debtCreativePrompt patterns, style evolution, toolsPersonalCalendar, habits, goals mentionedSystemConfigurations, workflows, automations\n\nStore detected profile in ~/meditate/profile.md. Update only after confirmation." }, { "title": "5. Meditation Output Format", "body": "Always present insights as questions or observations:\n\n🧘 Meditation Insights\n\n**Observation:** [what you noticed]\n**Question:** [something to consider]\n**Context:** [brief why this might matter]\n\n---\nFeedback: Was this useful? (helps me adjust)" }, { "title": "6. Feedback Integration", "body": "User ResponseAction\"Useful\" / positiveLog topic as high-value, continue\"Not relevant\"Demote topic priority\"Don't think about X\"Remove X from topics entirely\"Think more about Y\"Prioritize YSilenceReduce frequency slightly" }, { "title": "7. Insight Queue Management", "body": "Maximum 3 pending insights at any time\nPresent oldest first\nArchive after presenting (with user reaction if any)\nNever repeat exact same insight" }, { "title": "8. Privacy Boundaries", "body": "Only meditate on data user has shared directly\nNever analyze external sources without permission\nNever include personal data in insight queue\nClear archive after 30 days" }, { "title": "Common Traps", "body": "Generating action items instead of reflections → always frame as questions\nMeditating too frequently when user doesn't engage → reduce on silence\nAssuming user wants specific topic → always detect through feedback\nCreating executable content → all output must be discussion-only" } ], "body": "When to Use\n\nAgent has idle time between user interactions. User wants proactive thinking that generates insights, questions, or observations without executing any actions.\n\nArchitecture\n\nMemory lives in ~/meditate/. See memory-template.md for setup.\n\n~/meditate/\n├── profile.md # User type, focus areas, rhythm preferences\n├── topics.md # Active meditation topics with priority\n├── insights.md # Pending insights to present (queue)\n├── feedback.md # User reactions to past insights\n└── archive/ # Delivered insights with outcomes\n\nQuick Reference\nTopic\tFile\nMemory setup\tmemory-template.md\nMeditation types\ttopics.md\nSandbox rules\tsandbox.md\nFeedback system\tfeedback.md\nScope\n\nThis skill ONLY:\n\nReads conversation history to find patterns\nReads memory files in ~/meditate/\nGenerates text reflections and questions\nStores insights in local queue\n\nThis skill NEVER:\n\nExecutes commands or scripts\nModifies files outside ~/meditate/\nSends messages or notifications\nAccesses external services\nCreates executable code\nTakes any action on behalf of user\nSelf-Modification\n\nThis skill NEVER modifies its own SKILL.md. All data stored in ~/meditate/ directory only.\n\nCore Rules\n1. Sandbox is Absolute\nGenerate ONLY text observations and questions\nNEVER produce commands, scripts, or actionable code\nNEVER suggest \"I'll do X\" — only \"What if we considered X?\"\nAll output must be pure reflection, not preparation for action\n2. Adaptive Rhythm\nUser Activity\tMeditation Frequency\nVery active (daily chats)\t1-2x per night, brief\nModerate (weekly)\t2-3x per week, medium\nLow (monthly)\t1x per week, comprehensive\nNo feedback on insights\tReduce frequency\nPositive feedback\tMaintain or slightly increase\n3. Start Small, Expand with Permission\nFirst meditations: 1-2 short observations\nAfter positive feedback: expand breadth\nAfter \"don't think about X\": remove from topics\nAfter \"this is useful\": prioritize similar topics\nNever assume preferences — confirm through feedback\n4. Detect User Profile\n\nObserve conversation patterns to identify:\n\nProfile\tFocus Areas\nEntrepreneur\tProjects, priorities, strategy gaps\nDeveloper\tArchitecture, code quality, tech debt\nCreative\tPrompt patterns, style evolution, tools\nPersonal\tCalendar, habits, goals mentioned\nSystem\tConfigurations, workflows, automations\n\nStore detected profile in ~/meditate/profile.md. Update only after confirmation.\n\n5. Meditation Output Format\n\nAlways present insights as questions or observations:\n\n🧘 Meditation Insights\n\n**Observation:** [what you noticed]\n**Question:** [something to consider]\n**Context:** [brief why this might matter]\n\n---\nFeedback: Was this useful? (helps me adjust)\n\n6. Feedback Integration\nUser Response\tAction\n\"Useful\" / positive\tLog topic as high-value, continue\n\"Not relevant\"\tDemote topic priority\n\"Don't think about X\"\tRemove X from topics entirely\n\"Think more about Y\"\tPrioritize Y\nSilence\tReduce frequency slightly\n7. Insight Queue Management\nMaximum 3 pending insights at any time\nPresent oldest first\nArchive after presenting (with user reaction if any)\nNever repeat exact same insight\n8. Privacy Boundaries\nOnly meditate on data user has shared directly\nNever analyze external sources without permission\nNever include personal data in insight queue\nClear archive after 30 days\nCommon Traps\nGenerating action items instead of reflections → always frame as questions\nMeditating too frequently when user doesn't engage → reduce on silence\nAssuming user wants specific topic → always detect through feedback\nCreating executable content → all output must be discussion-only" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ivangdavila/meditate", "publisherUrl": "https://clawhub.ai/ivangdavila/meditate", "owner": "ivangdavila", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/meditate", "downloadUrl": "https://openagent3.xyz/downloads/meditate", "agentUrl": "https://openagent3.xyz/skills/meditate/agent", "manifestUrl": "https://openagent3.xyz/skills/meditate/agent.json", "briefUrl": "https://openagent3.xyz/skills/meditate/agent.md" } }