{ "schemaVersion": "1.0", "item": { "slug": "delx-ops-guardian", "name": "Delx Ops Guardian", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/davidmosiah/delx-ops-guardian", "canonicalUrl": "https://clawhub.ai/davidmosiah/delx-ops-guardian", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/delx-ops-guardian", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=delx-ops-guardian", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.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/delx-ops-guardian" }, "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/delx-ops-guardian", "agentPageUrl": "https://openagent3.xyz/skills/delx-ops-guardian/agent", "manifestUrl": "https://openagent3.xyz/skills/delx-ops-guardian/agent.json", "briefUrl": "https://openagent3.xyz/skills/delx-ops-guardian/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": "Delx Ops Guardian", "body": "Use this skill when handling incidents, degraded automations, or gateway/memory instability in production." }, { "title": "Aliases", "body": "emergency_recovery\nhandle_incident\ncron_guard\nmemory_guard\ngateway_guard" }, { "title": "Scope (strict)", "body": "This skill is runbook-only and must operate under least privilege.\n\nAllowed read sources:\n\nOpenClaw cron state (openclaw cron list --json)\nService health/status (systemctl is-active )\nRecent logs for incident window (journalctl -u --since ... --no-pager)\nWorkspace incident artifacts (/root/.openclaw/workspace/docs/ops/, /root/.openclaw/workspace/memory/)\n\nAllowed remediation actions (safe set):\n\nRetry a failed job once when failure is transient.\nControlled restart of the impacted service only (openclaw-gateway, openclaw, or explicitly named target from incident evidence).\nDisable/enable only the directly impacted cron job when loop-failing.\nAdd/adjust guardrails in runbook/config docs (non-secret, reversible).\n\nDisallowed actions:\n\nNo credential rotation/deletion.\nNo firewall/network policy mutations.\nNo package installs/upgrades during incident handling.\nNo bulk cron rewrites unrelated to the incident.\nNo edits to unrelated services/components." }, { "title": "Approval policy (human-in-the-loop)", "body": "Require explicit human approval before:\n\nRestarting any production service more than once.\nEditing cron schedules/timezones.\nDisabling a job for more than one cycle.\nAny action with user-visible impact beyond the failing component." }, { "title": "Core workflow", "body": "Detect and classify severity (info, degraded, critical).\nCollect evidence first (status, logs, last run, error streak).\nPropose smallest remediation from allowed set.\nExecute only approved/safe remediation.\nVerify stabilization window (at least one successful cycle).\nPublish concise incident report." }, { "title": "Safety rules", "body": "Never hide persistent failures as success.\nNever expose secrets/tokens in logs or reports.\nPrefer reversible actions and document rollback path.\nKeep blast radius minimal and explicitly stated." }, { "title": "Output contract", "body": "Always include:\n\nIncident id/time window\nRoot signal and blast radius\nActions executed (and approvals)\nEvidence (status, key metric, short log excerpt)\nFinal state (resolved, degraded, open)\nNext check time" }, { "title": "Example intents", "body": "\"Gateway is flapping, recover safely.\"\n\"Cron timed out, stabilize and prove fix.\"\n\"Memory guard firing repeatedly, root-cause and patch.\"" } ], "body": "name: delx-ops-guardian summary: Incident handling and operational recovery guardrails for OpenClaw production agents. owner: davidmosiah status: active\nDelx Ops Guardian\n\nUse this skill when handling incidents, degraded automations, or gateway/memory instability in production.\n\nAliases\nemergency_recovery\nhandle_incident\ncron_guard\nmemory_guard\ngateway_guard\nScope (strict)\n\nThis skill is runbook-only and must operate under least privilege.\n\nAllowed read sources:\n\nOpenClaw cron state (openclaw cron list --json)\nService health/status (systemctl is-active )\nRecent logs for incident window (journalctl -u --since ... --no-pager)\nWorkspace incident artifacts (/root/.openclaw/workspace/docs/ops/, /root/.openclaw/workspace/memory/)\n\nAllowed remediation actions (safe set):\n\nRetry a failed job once when failure is transient.\nControlled restart of the impacted service only (openclaw-gateway, openclaw, or explicitly named target from incident evidence).\nDisable/enable only the directly impacted cron job when loop-failing.\nAdd/adjust guardrails in runbook/config docs (non-secret, reversible).\n\nDisallowed actions:\n\nNo credential rotation/deletion.\nNo firewall/network policy mutations.\nNo package installs/upgrades during incident handling.\nNo bulk cron rewrites unrelated to the incident.\nNo edits to unrelated services/components.\nApproval policy (human-in-the-loop)\n\nRequire explicit human approval before:\n\nRestarting any production service more than once.\nEditing cron schedules/timezones.\nDisabling a job for more than one cycle.\nAny action with user-visible impact beyond the failing component.\nCore workflow\nDetect and classify severity (info, degraded, critical).\nCollect evidence first (status, logs, last run, error streak).\nPropose smallest remediation from allowed set.\nExecute only approved/safe remediation.\nVerify stabilization window (at least one successful cycle).\nPublish concise incident report.\nSafety rules\nNever hide persistent failures as success.\nNever expose secrets/tokens in logs or reports.\nPrefer reversible actions and document rollback path.\nKeep blast radius minimal and explicitly stated.\nOutput contract\n\nAlways include:\n\nIncident id/time window\nRoot signal and blast radius\nActions executed (and approvals)\nEvidence (status, key metric, short log excerpt)\nFinal state (resolved, degraded, open)\nNext check time\nExample intents\n\"Gateway is flapping, recover safely.\"\n\"Cron timed out, stabilize and prove fix.\"\n\"Memory guard firing repeatedly, root-cause and patch.\"" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/davidmosiah/delx-ops-guardian", "publisherUrl": "https://clawhub.ai/davidmosiah/delx-ops-guardian", "owner": "davidmosiah", "version": "1.0.2", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/delx-ops-guardian", "downloadUrl": "https://openagent3.xyz/downloads/delx-ops-guardian", "agentUrl": "https://openagent3.xyz/skills/delx-ops-guardian/agent", "manifestUrl": "https://openagent3.xyz/skills/delx-ops-guardian/agent.json", "briefUrl": "https://openagent3.xyz/skills/delx-ops-guardian/agent.md" } }