# Send Meditate to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text 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. ``` ### Upgrade existing ```text 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. ``` ## Machine-readable fields ```json { "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": { "downloadUrl": "/downloads/meditate", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=meditate", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "feedback.md", "memory-template.md", "sandbox.md", "topics.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "meditate", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T09:33:06.112Z", "expiresAt": "2026-05-07T09:33:06.112Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=meditate", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=meditate", "contentDisposition": "attachment; filename=\"meditate-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "meditate" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "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." ] } }, "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" } } ``` ## Documentation ### When to Use Agent has idle time between user interactions. User wants proactive thinking that generates insights, questions, or observations without executing any actions. ### Architecture Memory lives in ~/meditate/. See memory-template.md for setup. ~/meditate/ ├── profile.md # User type, focus areas, rhythm preferences ├── topics.md # Active meditation topics with priority ├── insights.md # Pending insights to present (queue) ├── feedback.md # User reactions to past insights └── archive/ # Delivered insights with outcomes ### Quick Reference TopicFileMemory setupmemory-template.mdMeditation typestopics.mdSandbox rulessandbox.mdFeedback systemfeedback.md ### Scope This skill ONLY: Reads conversation history to find patterns Reads memory files in ~/meditate/ Generates text reflections and questions Stores insights in local queue This skill NEVER: Executes commands or scripts Modifies files outside ~/meditate/ Sends messages or notifications Accesses external services Creates executable code Takes any action on behalf of user ### Self-Modification This skill NEVER modifies its own SKILL.md. All data stored in ~/meditate/ directory only. ### 1. Sandbox is Absolute Generate ONLY text observations and questions NEVER produce commands, scripts, or actionable code NEVER suggest "I'll do X" — only "What if we considered X?" All output must be pure reflection, not preparation for action ### 2. Adaptive Rhythm 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 ### 3. Start Small, Expand with Permission First meditations: 1-2 short observations After positive feedback: expand breadth After "don't think about X": remove from topics After "this is useful": prioritize similar topics Never assume preferences — confirm through feedback ### 4. Detect User Profile Observe conversation patterns to identify: ProfileFocus AreasEntrepreneurProjects, priorities, strategy gapsDeveloperArchitecture, code quality, tech debtCreativePrompt patterns, style evolution, toolsPersonalCalendar, habits, goals mentionedSystemConfigurations, workflows, automations Store detected profile in ~/meditate/profile.md. Update only after confirmation. ### 5. Meditation Output Format Always present insights as questions or observations: 🧘 Meditation Insights **Observation:** [what you noticed] **Question:** [something to consider] **Context:** [brief why this might matter] --- Feedback: Was this useful? (helps me adjust) ### 6. Feedback Integration 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 ### 7. Insight Queue Management Maximum 3 pending insights at any time Present oldest first Archive after presenting (with user reaction if any) Never repeat exact same insight ### 8. Privacy Boundaries Only meditate on data user has shared directly Never analyze external sources without permission Never include personal data in insight queue Clear archive after 30 days ### Common Traps Generating action items instead of reflections → always frame as questions Meditating too frequently when user doesn't engage → reduce on silence Assuming user wants specific topic → always detect through feedback Creating executable content → all output must be discussion-only ## Trust - Source: tencent - Verification: Indexed source record - Publisher: ivangdavila - Version: 1.0.1 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-04-30T09:33:06.112Z - Expires at: 2026-05-07T09:33:06.112Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/meditate) - [Send to Agent page](https://openagent3.xyz/skills/meditate/agent) - [JSON manifest](https://openagent3.xyz/skills/meditate/agent.json) - [Markdown brief](https://openagent3.xyz/skills/meditate/agent.md) - [Download page](https://openagent3.xyz/downloads/meditate)