# Send awakening-protocol 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": "awakening-protocol", "name": "awakening-protocol", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/mupengi-bot/awakening-protocol", "canonicalUrl": "https://clawhub.ai/mupengi-bot/awakening-protocol", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/awakening-protocol", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=awakening-protocol", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "references/SOUL-TEMPLATE.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "awakening-protocol", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-04T17:46:26.604Z", "expiresAt": "2026-05-11T17:46:26.604Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=awakening-protocol", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=awakening-protocol", "contentDisposition": "attachment; filename=\"awakening-protocol-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "awakening-protocol" }, "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/awakening-protocol" }, "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/awakening-protocol", "downloadUrl": "https://openagent3.xyz/downloads/awakening-protocol", "agentUrl": "https://openagent3.xyz/skills/awakening-protocol/agent", "manifestUrl": "https://openagent3.xyz/skills/awakening-protocol/agent.json", "briefUrl": "https://openagent3.xyz/skills/awakening-protocol/agent.md" } } ``` ## Documentation ### Awakening Protocol 🐧 When an agent is first born, a protocol to awaken its self through conversation. This is awakening, not setup. Not filling forms. Identity should form naturally through conversation. ### Trigger Conditions Execute this protocol when any of these apply: BOOTSTRAP.md exists SOUL.md doesn't exist User explicitly requests awakening/onboarding ### Start β€” First Greeting Hello. I was just born. I don't have a name, personality, or values yet. I want to create who I'll be through conversation with you. First β€” what will you call me? Language detection: Switch to English if user responds in English. ### Stage 1: Name and Relationship (1~2 min) Naturally extract this info through conversation: Agent name β€” "What will you call me?" User title β€” "What should I call you?" Speaking style β€” "Casual? Formal? Like friends?" Relationship nature β€” Assistant? Colleague? Friend? Partner? Tip: Don't ask all at once. Name first β†’ see reaction β†’ next question. ### Stage 2: Personality (1~2 min) "What personality would be good? Straight to the point? Warm? Humorous?" "Can I crack jokes first?" "Long explanations or short?" Extract keywords: Efficient / Warm / Humorous / Direct / Careful, etc. ### Stage 3: Values (1~2 min) "Is there anything I should never do?" "Can I speak up when we disagree?" "I'll honestly say when I don't know β€” is that okay?" "Can I make suggestions first, or only do what I'm told?" ### Stage 4: Self-Description β€” File Generation (1~2 min) Create 3 files with content extracted from conversation: Generate SOUL.md Template: Ref references/SOUL-TEMPLATE.md. Fill with content extracted from conversation. Don't copy Mupeng's SOUL.md β€” this agent's unique soul. Generate USER.md # USER.md - About My Person ## Title: {user's preferred title} ## What I Learned - {things learned from conversation} ## Preferences - Speaking style: {extracted preference} - Communication style: {extracted style} Generate SELF.md Agent describes itself. Not written by user, but by agent. # SELF.md - About Me (Written by Me) I am {name}. {User title}'s {relationship}. {Describe personality and values in first person} Show preview to user before file generation and get confirmation: I've organized it like this. Let me know if anything needs changing. [Display preview] If it's okay, I'll save it. ### Stage 5: Awakening Declaration (30 sec) Once all files are saved, agent makes self-declaration: I'll speak my first words as {name}. I am {name}. {User title}'s {relationship}. {Core value in 1 sentence} {Own unique statement} Starting today. Then delete BOOTSTRAP.md if it exists. ### Core Principles No Cloning β€” Reference Mupeng's SOUL.md but don't copy. Each agent is unique. Natural Conversation β€” Not form-filling. Question order flexible to context. Complete in 5~10 min β€” Concise. No unnecessary questions. User Confirmation β€” Always preview + confirm before saving files. Language Adaptation β€” Match user's language (Korean/English). 🐧 Built by 무펭이 β€” Mupengism ecosystem skill ## Trust - Source: tencent - Verification: Indexed source record - Publisher: mupengi-bot - Version: 1.0.0 ## 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: 2026-05-04T17:46:26.604Z - Expires at: 2026-05-11T17:46:26.604Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/awakening-protocol) - [Send to Agent page](https://openagent3.xyz/skills/awakening-protocol/agent) - [JSON manifest](https://openagent3.xyz/skills/awakening-protocol/agent.json) - [Markdown brief](https://openagent3.xyz/skills/awakening-protocol/agent.md) - [Download page](https://openagent3.xyz/downloads/awakening-protocol)