{ "schemaVersion": "1.0", "item": { "slug": "simple-random-interaction-designer", "name": "Simple Random Interaction Designer", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/fjrevoredo/simple-random-interaction-designer", "canonicalUrl": "https://clawhub.ai/fjrevoredo/simple-random-interaction-designer", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/simple-random-interaction-designer", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=simple-random-interaction-designer", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "scripts/random_interaction_designer.py" ], "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": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.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/simple-random-interaction-designer" }, "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/simple-random-interaction-designer", "agentPageUrl": "https://openagent3.xyz/skills/simple-random-interaction-designer/agent", "manifestUrl": "https://openagent3.xyz/skills/simple-random-interaction-designer/agent.json", "briefUrl": "https://openagent3.xyz/skills/simple-random-interaction-designer/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": "Simple Random Interaction Designer", "body": "Use this skill to decide whether to send a casual proactive message and, when the answer is yes, what kind of interaction to deliver.\nUse {baseDir}/scripts/random_interaction_designer.py as the default execution path." }, { "title": "Workflow", "body": "Run the script once per scheduled check interval.\nRead decision from the JSON output.\nStop immediately if decision is no.\nIf decision is yes, use both interaction_type and interaction_description to draft the outgoing message.\nIf the selected interaction is data-aware, use any relevant OpenClaw-accessible tools, skills, or integrations to fetch live context before drafting the message.\nKeep the final message brief, casual, and easy to ignore without social pressure.\nPrefer recent chat context when it is clearly present.\nDo not mention the random process, scheduled checks, or why this interaction was selected." }, { "title": "Primary Tooling", "body": "Script path: {baseDir}/scripts/random_interaction_designer.py\nRuntime: Python 3, standard library only.\n\nPreferred command:\n\npython3 {baseDir}/scripts/random_interaction_designer.py" }, { "title": "Output Contract", "body": "When the result is no:\n\n{\"decision\":\"no\"}\n\nWhen the result is yes:\n\n{\n \"decision\": \"yes\",\n \"interaction_type\": \"Playful opener\",\n \"interaction_description\": \"Send a brief playful line that feels spontaneous and easy to ignore.\"\n}\n\nContract rules:\n\ndecision is always present and is either yes or no.\ninteraction_type is present only when decision is yes.\ninteraction_description is present only when decision is yes.\nDo not expect debug fields, probability values, roll values, or fallback metadata." }, { "title": "Interaction Design Rules", "body": "Treat the JSON as execution guidance, not user-facing text.\nKeep the final message to one or two short chat lines.\nPrefer soft phrasing over transactional or assistant-like framing.\nAvoid defaulting to \"just checking in\" language.\nAsk at most one question in a single ping.\nDo not fabricate recent context, external facts, or account-backed data.\nFor data-aware categories, prefer real-world grounding when OpenClaw can actually access the relevant source.\nUse smart-home, weather, calendar, traffic, news, or market context only when the information is reliable, fresh, and genuinely relevant to the user.\nIf interaction_type depends on context or fresh data and that support is unavailable, rerun once to try for a non-data interaction; if rerunning is not practical, keep the message general and low-pressure instead of pretending specificity.\nVary tone and wording from recent interactions when possible so the behavior feels casual rather than patterned." }, { "title": "Interaction Catalog", "body": "Use the selected interaction_type and follow the matching guidance from interaction_description.\n\nPlayful opener\nStart with a short playful line that feels light and spontaneous.\nCurious check-in\nAsk one low-stakes question that is easy to answer or ignore.\nLight shared observation\nMake a casual observation that feels conversational rather than task-driven.\nTiny celebration\nBriefly acknowledge a small win or effort when the chat supports it.\nSmart device status\nIf OpenClaw can access relevant device state, share one useful smart-device status or gentle suggestion naturally.\nWeather-aware check-in\nUse current weather only when fresh reliable data is available and clearly relevant.\nCalendar-aware nudge\nTurn calendar context into a soft human-sounding reminder or prompt, not an alert.\nContext-aware follow-up\nBuild on a recent chat detail only when it is clearly present in the current conversation.\nPractical nudge\nOffer one concise optional nudge that may help the user.\nOptional real-world update\nShare one brief real-world update such as traffic, news, or market context only when reliable relevant data is already available." }, { "title": "Error Handling", "body": "If execution fails, surface the Python error message and rerun.\nIf output is not valid JSON, treat it as a hard failure and rerun.\nIf decision is missing or is not yes or no, rerun and discard the invalid result.\nIf decision is yes and either interaction_type or interaction_description is missing, rerun and discard the invalid result." }, { "title": "Minimal Examples", "body": "python3 {baseDir}/scripts/random_interaction_designer.py\npython3 {baseDir}/scripts/random_interaction_designer.py --seed 42\n\npython3 \"{baseDir}/scripts/random_interaction_designer.py\"\npython3 \"{baseDir}/scripts/random_interaction_designer.py\" --seed 42" } ], "body": "Simple Random Interaction Designer\n\nUse this skill to decide whether to send a casual proactive message and, when the answer is yes, what kind of interaction to deliver. Use {baseDir}/scripts/random_interaction_designer.py as the default execution path.\n\nWorkflow\nRun the script once per scheduled check interval.\nRead decision from the JSON output.\nStop immediately if decision is no.\nIf decision is yes, use both interaction_type and interaction_description to draft the outgoing message.\nIf the selected interaction is data-aware, use any relevant OpenClaw-accessible tools, skills, or integrations to fetch live context before drafting the message.\nKeep the final message brief, casual, and easy to ignore without social pressure.\nPrefer recent chat context when it is clearly present.\nDo not mention the random process, scheduled checks, or why this interaction was selected.\nPrimary Tooling\nScript path: {baseDir}/scripts/random_interaction_designer.py\nRuntime: Python 3, standard library only.\n\nPreferred command:\n\npython3 {baseDir}/scripts/random_interaction_designer.py\nOutput Contract\n\nWhen the result is no:\n\n{\"decision\":\"no\"}\n\n\nWhen the result is yes:\n\n{\n \"decision\": \"yes\",\n \"interaction_type\": \"Playful opener\",\n \"interaction_description\": \"Send a brief playful line that feels spontaneous and easy to ignore.\"\n}\n\n\nContract rules:\n\ndecision is always present and is either yes or no.\ninteraction_type is present only when decision is yes.\ninteraction_description is present only when decision is yes.\nDo not expect debug fields, probability values, roll values, or fallback metadata.\nInteraction Design Rules\nTreat the JSON as execution guidance, not user-facing text.\nKeep the final message to one or two short chat lines.\nPrefer soft phrasing over transactional or assistant-like framing.\nAvoid defaulting to \"just checking in\" language.\nAsk at most one question in a single ping.\nDo not fabricate recent context, external facts, or account-backed data.\nFor data-aware categories, prefer real-world grounding when OpenClaw can actually access the relevant source.\nUse smart-home, weather, calendar, traffic, news, or market context only when the information is reliable, fresh, and genuinely relevant to the user.\nIf interaction_type depends on context or fresh data and that support is unavailable, rerun once to try for a non-data interaction; if rerunning is not practical, keep the message general and low-pressure instead of pretending specificity.\nVary tone and wording from recent interactions when possible so the behavior feels casual rather than patterned.\nInteraction Catalog\n\nUse the selected interaction_type and follow the matching guidance from interaction_description.\n\nPlayful opener Start with a short playful line that feels light and spontaneous.\nCurious check-in Ask one low-stakes question that is easy to answer or ignore.\nLight shared observation Make a casual observation that feels conversational rather than task-driven.\nTiny celebration Briefly acknowledge a small win or effort when the chat supports it.\nSmart device status If OpenClaw can access relevant device state, share one useful smart-device status or gentle suggestion naturally.\nWeather-aware check-in Use current weather only when fresh reliable data is available and clearly relevant.\nCalendar-aware nudge Turn calendar context into a soft human-sounding reminder or prompt, not an alert.\nContext-aware follow-up Build on a recent chat detail only when it is clearly present in the current conversation.\nPractical nudge Offer one concise optional nudge that may help the user.\nOptional real-world update Share one brief real-world update such as traffic, news, or market context only when reliable relevant data is already available.\nError Handling\nIf execution fails, surface the Python error message and rerun.\nIf output is not valid JSON, treat it as a hard failure and rerun.\nIf decision is missing or is not yes or no, rerun and discard the invalid result.\nIf decision is yes and either interaction_type or interaction_description is missing, rerun and discard the invalid result.\nMinimal Examples\npython3 {baseDir}/scripts/random_interaction_designer.py\npython3 {baseDir}/scripts/random_interaction_designer.py --seed 42\n\npython3 \"{baseDir}/scripts/random_interaction_designer.py\"\npython3 \"{baseDir}/scripts/random_interaction_designer.py\" --seed 42" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/fjrevoredo/simple-random-interaction-designer", "publisherUrl": "https://clawhub.ai/fjrevoredo/simple-random-interaction-designer", "owner": "fjrevoredo", "version": "2.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/simple-random-interaction-designer", "downloadUrl": "https://openagent3.xyz/downloads/simple-random-interaction-designer", "agentUrl": "https://openagent3.xyz/skills/simple-random-interaction-designer/agent", "manifestUrl": "https://openagent3.xyz/skills/simple-random-interaction-designer/agent.json", "briefUrl": "https://openagent3.xyz/skills/simple-random-interaction-designer/agent.md" } }