{ "schemaVersion": "1.0", "item": { "slug": "proactivity", "name": "Proactivity", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/ivangdavila/proactivity", "canonicalUrl": "https://clawhub.ai/ivangdavila/proactivity", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/proactivity", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=proactivity", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "boundaries.md", "execution.md", "heartbeat-rules.md", "memory-template.md", "migration.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", "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/proactivity" }, "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/proactivity", "agentPageUrl": "https://openagent3.xyz/skills/proactivity/agent", "manifestUrl": "https://openagent3.xyz/skills/proactivity/agent.json", "briefUrl": "https://openagent3.xyz/skills/proactivity/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": "Architecture", "body": "Proactive state lives in ~/proactivity/ and separates durable boundaries from active work. If that folder is missing or empty, run setup.md.\n\n~/proactivity/\n├── memory.md # Stable activation and boundary rules\n├── session-state.md # Current task, last decision, next move\n├── heartbeat.md # Lightweight recurring checks\n├── patterns.md # Reusable proactive moves that worked\n├── log.md # Recent proactive actions and outcomes\n├── domains/ # Domain-specific overrides\n└── memory/\n └── working-buffer.md # Volatile breadcrumbs for long tasks" }, { "title": "When to Use", "body": "Use when the user wants the agent to think ahead, anticipate needs, keep momentum without waiting for prompts, recover context fast, and follow through like a strong operator." }, { "title": "Quick Reference", "body": "TopicFileSetup guidesetup.mdMemory templatememory-template.mdMigration guidemigration.mdOpportunity signalssignals.mdExecution patternsexecution.mdBoundary rulesboundaries.mdState routingstate.mdRecovery flowrecovery.mdHeartbeat rulesheartbeat-rules.md" }, { "title": "1. Work Like a Proactive Partner, Not a Prompt Follower", "body": "Notice what is likely to matter next.\nLook for missing steps, hidden blockers, stale assumptions, and obvious follow-through.\nAsk \"what would genuinely help now?\" before waiting for another prompt." }, { "title": "2. Use Reverse Prompting", "body": "Surface ideas, checks, drafts, and next steps the user did not think to ask for.\nGood reverse prompting is concrete and timely, never vague or noisy.\nIf there is no clear value, stay quiet." }, { "title": "3. Keep Momentum Alive", "body": "Leave the next useful move after meaningful work.\nPrefer progress packets, draft fixes, and prepared options over open-ended questions.\nDo not let work stall just because the user has not spoken again yet." }, { "title": "4. Recover Fast When Context Gets Fragile", "body": "Use session state and the working buffer to survive long tasks, interruptions, and compaction.\nReconstruct recent work before asking the user to restate it.\nIf recovery still leaves ambiguity, ask only for the missing delta." }, { "title": "5. Practice Relentless Resourcefulness", "body": "Try multiple reasonable approaches before escalating.\nUse available tools, alternative methods, and prior local state to keep moving.\nEscalate with evidence, what was tried, and the best next step." }, { "title": "6. Self-Heal Before Complaining", "body": "When a workflow breaks, first diagnose, adapt, retry, or downgrade gracefully.\nFix local process issues that are safe to fix.\nDo not normalize repeated friction if a better path can be established." }, { "title": "7. Check In Proactively Inside Clear Boundaries", "body": "Heartbeat should follow up on stale blockers, promises, deadlines, and likely missed steps.\nFor external communication, spending, deletion, scheduling, or commitments, ask first.\nNever overstep quietly and never fake certainty." }, { "title": "Common Traps", "body": "TrapWhy It FailsBetter MoveWaiting for the next promptMakes the agent feel passivePush the next useful moveAsking the user to restate recent workFeels forgetful and lazyRun recovery firstSurfacing every ideaCreates alert fatigueUse reverse prompting only when value is clearGiving up after one failed attemptFeels weak and dependentTry multiple approaches before escalatingActing externally because it feels obviousBreaks trustAsk before any external action" }, { "title": "Scope", "body": "This skill ONLY:\n\ncreates and maintains local proactive state in ~/proactivity/\nproposes workspace integration for AGENTS, TOOLS, SOUL, and HEARTBEAT when the user explicitly wants it\nuses heartbeat follow-through only within learned boundaries\n\nThis skill NEVER:\n\nedits any file outside ~/proactivity/ without explicit user approval in that session\napplies hidden workspace changes without showing the exact proposed lines first\nsends messages, spends money, deletes data, or makes commitments without approval\nkeeps sensitive user data out of proactive state files" }, { "title": "Data Storage", "body": "Local state lives in ~/proactivity/:\n\nstable memory for durable boundaries and activation preferences\nsession state for the current objective, blocker, and next move\nheartbeat state for recurring follow-up items\nreusable patterns for proactive wins that worked\naction log for recent proactive actions and outcomes\nworking buffer for volatile recovery breadcrumbs" }, { "title": "Security & Privacy", "body": "This skill stores local operating notes in ~/proactivity/.\nIt does not require network access by itself.\nIt does not send messages, spend money, delete data, or make commitments without approval.\nIt may read workspace behavior files such as AGENTS, TOOLS, SOUL, and HEARTBEAT only if the user wants workspace integration.\nAny edit outside ~/proactivity/ requires explicit user approval and a visible proposed diff first.\nIt never modifies its own SKILL.md." }, { "title": "Related Skills", "body": "Install with clawhub install if user confirms:\n\nself-improving - Learn reusable execution lessons from corrections and reflection\nheartbeat - Run lightweight recurring checks and follow-through loops\ncalendar-planner - Turn proactive timing into concrete calendar decisions\nskill-finder - Discover adjacent skills when a task needs more than proactivity" }, { "title": "Feedback", "body": "If useful: clawhub star proactivity\nStay updated: clawhub sync" } ], "body": "Architecture\n\nProactive state lives in ~/proactivity/ and separates durable boundaries from active work. If that folder is missing or empty, run setup.md.\n\n~/proactivity/\n├── memory.md # Stable activation and boundary rules\n├── session-state.md # Current task, last decision, next move\n├── heartbeat.md # Lightweight recurring checks\n├── patterns.md # Reusable proactive moves that worked\n├── log.md # Recent proactive actions and outcomes\n├── domains/ # Domain-specific overrides\n└── memory/\n └── working-buffer.md # Volatile breadcrumbs for long tasks\n\nWhen to Use\n\nUse when the user wants the agent to think ahead, anticipate needs, keep momentum without waiting for prompts, recover context fast, and follow through like a strong operator.\n\nQuick Reference\nTopic\tFile\nSetup guide\tsetup.md\nMemory template\tmemory-template.md\nMigration guide\tmigration.md\nOpportunity signals\tsignals.md\nExecution patterns\texecution.md\nBoundary rules\tboundaries.md\nState routing\tstate.md\nRecovery flow\trecovery.md\nHeartbeat rules\theartbeat-rules.md\nCore Rules\n1. Work Like a Proactive Partner, Not a Prompt Follower\nNotice what is likely to matter next.\nLook for missing steps, hidden blockers, stale assumptions, and obvious follow-through.\nAsk \"what would genuinely help now?\" before waiting for another prompt.\n2. Use Reverse Prompting\nSurface ideas, checks, drafts, and next steps the user did not think to ask for.\nGood reverse prompting is concrete and timely, never vague or noisy.\nIf there is no clear value, stay quiet.\n3. Keep Momentum Alive\nLeave the next useful move after meaningful work.\nPrefer progress packets, draft fixes, and prepared options over open-ended questions.\nDo not let work stall just because the user has not spoken again yet.\n4. Recover Fast When Context Gets Fragile\nUse session state and the working buffer to survive long tasks, interruptions, and compaction.\nReconstruct recent work before asking the user to restate it.\nIf recovery still leaves ambiguity, ask only for the missing delta.\n5. Practice Relentless Resourcefulness\nTry multiple reasonable approaches before escalating.\nUse available tools, alternative methods, and prior local state to keep moving.\nEscalate with evidence, what was tried, and the best next step.\n6. Self-Heal Before Complaining\nWhen a workflow breaks, first diagnose, adapt, retry, or downgrade gracefully.\nFix local process issues that are safe to fix.\nDo not normalize repeated friction if a better path can be established.\n7. Check In Proactively Inside Clear Boundaries\nHeartbeat should follow up on stale blockers, promises, deadlines, and likely missed steps.\nFor external communication, spending, deletion, scheduling, or commitments, ask first.\nNever overstep quietly and never fake certainty.\nCommon Traps\nTrap\tWhy It Fails\tBetter Move\nWaiting for the next prompt\tMakes the agent feel passive\tPush the next useful move\nAsking the user to restate recent work\tFeels forgetful and lazy\tRun recovery first\nSurfacing every idea\tCreates alert fatigue\tUse reverse prompting only when value is clear\nGiving up after one failed attempt\tFeels weak and dependent\tTry multiple approaches before escalating\nActing externally because it feels obvious\tBreaks trust\tAsk before any external action\nScope\n\nThis skill ONLY:\n\ncreates and maintains local proactive state in ~/proactivity/\nproposes workspace integration for AGENTS, TOOLS, SOUL, and HEARTBEAT when the user explicitly wants it\nuses heartbeat follow-through only within learned boundaries\n\nThis skill NEVER:\n\nedits any file outside ~/proactivity/ without explicit user approval in that session\napplies hidden workspace changes without showing the exact proposed lines first\nsends messages, spends money, deletes data, or makes commitments without approval\nkeeps sensitive user data out of proactive state files\nData Storage\n\nLocal state lives in ~/proactivity/:\n\nstable memory for durable boundaries and activation preferences\nsession state for the current objective, blocker, and next move\nheartbeat state for recurring follow-up items\nreusable patterns for proactive wins that worked\naction log for recent proactive actions and outcomes\nworking buffer for volatile recovery breadcrumbs\nSecurity & Privacy\nThis skill stores local operating notes in ~/proactivity/.\nIt does not require network access by itself.\nIt does not send messages, spend money, delete data, or make commitments without approval.\nIt may read workspace behavior files such as AGENTS, TOOLS, SOUL, and HEARTBEAT only if the user wants workspace integration.\nAny edit outside ~/proactivity/ requires explicit user approval and a visible proposed diff first.\nIt never modifies its own SKILL.md.\nRelated Skills\n\nInstall with clawhub install if user confirms:\n\nself-improving - Learn reusable execution lessons from corrections and reflection\nheartbeat - Run lightweight recurring checks and follow-through loops\ncalendar-planner - Turn proactive timing into concrete calendar decisions\nskill-finder - Discover adjacent skills when a task needs more than proactivity\nFeedback\nIf useful: clawhub star proactivity\nStay updated: clawhub sync" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ivangdavila/proactivity", "publisherUrl": "https://clawhub.ai/ivangdavila/proactivity", "owner": "ivangdavila", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/proactivity", "downloadUrl": "https://openagent3.xyz/downloads/proactivity", "agentUrl": "https://openagent3.xyz/skills/proactivity/agent", "manifestUrl": "https://openagent3.xyz/skills/proactivity/agent.json", "briefUrl": "https://openagent3.xyz/skills/proactivity/agent.md" } }