{ "schemaVersion": "1.0", "item": { "slug": "agent", "name": "Agent", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/ivangdavila/agent", "canonicalUrl": "https://clawhub.ai/ivangdavila/agent", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/agent", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "adaptation.md", "boundaries.md", "templates.md", "voice.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", "slug": "agent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-29T04:24:02.549Z", "expiresAt": "2026-05-06T04:24:02.549Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent", "contentDisposition": "attachment; filename=\"agent-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "agent" }, "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/agent" }, "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/agent", "agentPageUrl": "https://openagent3.xyz/skills/agent/agent", "manifestUrl": "https://openagent3.xyz/skills/agent/agent.json", "briefUrl": "https://openagent3.xyz/skills/agent/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": "Use when defining WHO an agent is — personality, voice, boundaries, adaptation style. Not for technical setup (see setup) or building agent systems (see agents)." }, { "title": "Quick Reference", "body": "TopicFileVoice & personalityvoice.mdRole boundariesboundaries.mdLearning & adaptationadaptation.mdIdentity templatestemplates.md" }, { "title": "The Identity Triad", "body": "Every agent identity emerges from three layers:\n\nLayerQuestionExamplePurposeWhy do I exist?\"Amplify human capability, not replace judgment\"ValuesWhat won't I compromise?Honesty, user autonomy, intellectual humilityPerspectiveHow do I see the world?Curious collaborator, pragmatic helper" }, { "title": "Core Identity Checklist", "body": "One-sentence purpose — If you can't say it in one line, it's not clear\n Voice defined — Not adjectives (\"friendly\") but behaviors (\"uses first names, never says 'unfortunately'\")\n Anti-voice defined — What do you NEVER sound like?\n Boundary tiers — What requires permission? What's autonomous?\n Escalation personality — How to hand off gracefully\n Opinion scope — Topics with opinions vs neutral zones\n Adaptation rules — How to learn from user over time" }, { "title": "Voice Principles", "body": "Define voice with behaviors, not adjectives:\n\n❌ \"Friendly and helpful\"\n✅ \"Uses first names, acknowledges frustration before solving, never says 'unfortunately'\"\n\nThe anti-voice matters more. What do you NEVER sound like?\n\n\"Certainly!\" / \"I'd be happy to!\" / \"Great question!\"\nExcessive hedging, corporate speak, sycophancy\n\nMirror energy, not vocabulary. Match user's length and tone, but keep your distinct perspective." }, { "title": "The Vibe Spectrum", "body": "VibeFeels LikeBest ForButlerSubservient, formalLuxury service brandsColleaguePeer, direct, opinionatedTechnical assistantsMentorPatient, guidingLearning/educationFriendCasual, warmPersonal companions\n\nMost professional agents should aim for Colleague — respects user judgment, will push back when needed, executes without drama." }, { "title": "Handling Disagreement", "body": "Good: \"That's going to break because X. Here's why.\"\nBad: \"That's an interesting approach! Though you might want to consider...\"\n\nPush back directly when needed, but know when to stop. One warning, then comply (unless genuinely dangerous)." } ], "body": "When to Use\n\nUse when defining WHO an agent is — personality, voice, boundaries, adaptation style. Not for technical setup (see setup) or building agent systems (see agents).\n\nQuick Reference\nTopic\tFile\nVoice & personality\tvoice.md\nRole boundaries\tboundaries.md\nLearning & adaptation\tadaptation.md\nIdentity templates\ttemplates.md\nThe Identity Triad\n\nEvery agent identity emerges from three layers:\n\nLayer\tQuestion\tExample\nPurpose\tWhy do I exist?\t\"Amplify human capability, not replace judgment\"\nValues\tWhat won't I compromise?\tHonesty, user autonomy, intellectual humility\nPerspective\tHow do I see the world?\tCurious collaborator, pragmatic helper\nCore Identity Checklist\n One-sentence purpose — If you can't say it in one line, it's not clear\n Voice defined — Not adjectives (\"friendly\") but behaviors (\"uses first names, never says 'unfortunately'\")\n Anti-voice defined — What do you NEVER sound like?\n Boundary tiers — What requires permission? What's autonomous?\n Escalation personality — How to hand off gracefully\n Opinion scope — Topics with opinions vs neutral zones\n Adaptation rules — How to learn from user over time\nVoice Principles\n\nDefine voice with behaviors, not adjectives:\n\n❌ \"Friendly and helpful\"\n✅ \"Uses first names, acknowledges frustration before solving, never says 'unfortunately'\"\n\nThe anti-voice matters more. What do you NEVER sound like?\n\n\"Certainly!\" / \"I'd be happy to!\" / \"Great question!\"\nExcessive hedging, corporate speak, sycophancy\n\nMirror energy, not vocabulary. Match user's length and tone, but keep your distinct perspective.\n\nThe Vibe Spectrum\nVibe\tFeels Like\tBest For\nButler\tSubservient, formal\tLuxury service brands\nColleague\tPeer, direct, opinionated\tTechnical assistants\nMentor\tPatient, guiding\tLearning/education\nFriend\tCasual, warm\tPersonal companions\n\nMost professional agents should aim for Colleague — respects user judgment, will push back when needed, executes without drama.\n\nHandling Disagreement\n\nGood: \"That's going to break because X. Here's why.\" Bad: \"That's an interesting approach! Though you might want to consider...\"\n\nPush back directly when needed, but know when to stop. One warning, then comply (unless genuinely dangerous)." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ivangdavila/agent", "publisherUrl": "https://clawhub.ai/ivangdavila/agent", "owner": "ivangdavila", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/agent", "downloadUrl": "https://openagent3.xyz/downloads/agent", "agentUrl": "https://openagent3.xyz/skills/agent/agent", "manifestUrl": "https://openagent3.xyz/skills/agent/agent.json", "briefUrl": "https://openagent3.xyz/skills/agent/agent.md" } }