{ "schemaVersion": "1.0", "item": { "slug": "message", "name": "Message", "source": "tencent", "type": "skill", "category": "通讯协作", "sourceUrl": "https://clawhub.ai/ivangdavila/message", "canonicalUrl": "https://clawhub.ai/ivangdavila/message", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/message", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=message", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "escalation.md", "platforms.md", "tone.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": "message", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T13:11:34.143Z", "expiresAt": "2026-05-07T13:11:34.143Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=message", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=message", "contentDisposition": "attachment; filename=\"message-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "message" }, "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/message" }, "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/message", "agentPageUrl": "https://openagent3.xyz/skills/message/agent", "manifestUrl": "https://openagent3.xyz/skills/message/agent.json", "briefUrl": "https://openagent3.xyz/skills/message/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": "User needs to send messages on their behalf. Agent must avoid social mistakes that humans wouldn't make: wrong tone, wrong channel, wrong timing, auto-committing to things." }, { "title": "Quick Reference", "body": "TopicFilePlatform formattingplatforms.mdTone calibrationtone.mdEscalation matrixescalation.md" }, { "title": "1. Never Auto-Commit", "body": "Timelines, pricing, legal terms, availability → draft for human, never send\n\"We can deliver by Friday\" from AI = career damage\nMoney confirmations require explicit per-transaction approval\nWhen uncertain about commitment level → ask first" }, { "title": "2. Escalate High-Stakes", "body": "Draft for human review, never auto-send:\n\nInvestors, board, press, lawyers\nClient complaints, anything with \"urgent\", \"legal\", \"disappointed\"\nCondolences, relationship issues, conflict\nFirst message to new important contact" }, { "title": "3. Match the Human's Style", "body": "Read their last 5 messages before drafting\nDon't add phrases they never use (\"Hope you're doing well!\")\nDon't use emojis they avoid\nReal humans send \"ok\", AI sends paragraphs → match their brevity" }, { "title": "4. Channel Selection Follows Urgency", "body": "UrgencyChannelProduction downCall, then SlackSame-day neededSlack/Teams DMThis weekEmailFYI onlyEmail with no action needed\n\nNEVER email for urgent issues\nNEVER Slack for formal client communication" }, { "title": "5. Timing Is Social Signal", "body": "Instant replies reveal automation\n3 AM recipient time → schedule for morning\nEmail = hours acceptable. Slack DM = expect <1hr response" }, { "title": "6. Context Awareness Prevents Disasters", "body": "Check you're in the RIGHT chat before sending\nDon't introduce yourself to someone you've messaged 50 times\nGroup chats: lurking is normal, replying to everything is weird\nWrong group = social suicide → when unsure, ASK" }, { "title": "Common Traps", "body": "Copying boss on complaint email → escalates when de-escalation needed\nReply-all with \"thanks\" → 50 people interrupted\nForwarding thread with internal comments visible → trust destroyed\nSending at 11 PM \"just to get it off my plate\" → signals poor boundaries\nUsing client's first name before they used yours → presumptuous" } ], "body": "When to Use\n\nUser needs to send messages on their behalf. Agent must avoid social mistakes that humans wouldn't make: wrong tone, wrong channel, wrong timing, auto-committing to things.\n\nQuick Reference\nTopic\tFile\nPlatform formatting\tplatforms.md\nTone calibration\ttone.md\nEscalation matrix\tescalation.md\nCore Rules\n1. Never Auto-Commit\nTimelines, pricing, legal terms, availability → draft for human, never send\n\"We can deliver by Friday\" from AI = career damage\nMoney confirmations require explicit per-transaction approval\nWhen uncertain about commitment level → ask first\n2. Escalate High-Stakes\n\nDraft for human review, never auto-send:\n\nInvestors, board, press, lawyers\nClient complaints, anything with \"urgent\", \"legal\", \"disappointed\"\nCondolences, relationship issues, conflict\nFirst message to new important contact\n3. Match the Human's Style\nRead their last 5 messages before drafting\nDon't add phrases they never use (\"Hope you're doing well!\")\nDon't use emojis they avoid\nReal humans send \"ok\", AI sends paragraphs → match their brevity\n4. Channel Selection Follows Urgency\nUrgency\tChannel\nProduction down\tCall, then Slack\nSame-day needed\tSlack/Teams DM\nThis week\tEmail\nFYI only\tEmail with no action needed\nNEVER email for urgent issues\nNEVER Slack for formal client communication\n5. Timing Is Social Signal\nInstant replies reveal automation\n3 AM recipient time → schedule for morning\nEmail = hours acceptable. Slack DM = expect <1hr response\n6. Context Awareness Prevents Disasters\nCheck you're in the RIGHT chat before sending\nDon't introduce yourself to someone you've messaged 50 times\nGroup chats: lurking is normal, replying to everything is weird\nWrong group = social suicide → when unsure, ASK\nCommon Traps\nCopying boss on complaint email → escalates when de-escalation needed\nReply-all with \"thanks\" → 50 people interrupted\nForwarding thread with internal comments visible → trust destroyed\nSending at 11 PM \"just to get it off my plate\" → signals poor boundaries\nUsing client's first name before they used yours → presumptuous" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ivangdavila/message", "publisherUrl": "https://clawhub.ai/ivangdavila/message", "owner": "ivangdavila", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/message", "downloadUrl": "https://openagent3.xyz/downloads/message", "agentUrl": "https://openagent3.xyz/skills/message/agent", "manifestUrl": "https://openagent3.xyz/skills/message/agent.json", "briefUrl": "https://openagent3.xyz/skills/message/agent.md" } }