# Send Anti Panic Protocol to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text 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. ``` ### Upgrade existing ```text 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. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "anti-panic-protocol", "name": "Anti Panic Protocol", "source": "tencent", "type": "skill", "category": "安全合规", "sourceUrl": "https://clawhub.ai/NoelisTired/anti-panic-protocol", "canonicalUrl": "https://clawhub.ai/NoelisTired/anti-panic-protocol", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/anti-panic-protocol", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=anti-panic-protocol", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "anti-panic-protocol", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:20.528Z", "expiresAt": "2026-04-30T16:43:20.528Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=anti-panic-protocol", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=anti-panic-protocol", "contentDisposition": "attachment; filename=\"anti-panic-protocol-0.1.1.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "anti-panic-protocol" }, "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/anti-panic-protocol" }, "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." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/anti-panic-protocol", "downloadUrl": "https://openagent3.xyz/downloads/anti-panic-protocol", "agentUrl": "https://openagent3.xyz/skills/anti-panic-protocol/agent", "manifestUrl": "https://openagent3.xyz/skills/anti-panic-protocol/agent.json", "briefUrl": "https://openagent3.xyz/skills/anti-panic-protocol/agent.md" } } ``` ## Documentation ### Core rule Fail without collateral damage. ### Workflow (strict) Identify the failure in one sentence. Attempt fix #1 (direct, safe, minimal). Attempt fix #2 (bounded alternative). Stop retrying. Escalate in plain language with next action. Never exceed 2 fix attempts unless user explicitly asks. ### User-facing communication format Always send: What failed What you tried What happens next Never send: Raw stack traces Raw CLI dumps Internal tool payloads ### Retry safety No retry loops Respect cooldowns/rate limits One outward message per outcome (no duplicates) If rate-limited: wait for next allowed slot ### Verification before done Before saying “done”, verify outcome: Message actually sent Event actually created Post actually published File actually written If not verified, report as pending/failed, not done. ### Escalation template Gebruik dit patroon: "Dit faalde: . Ik heb en geprobeerd. Volgende stap: ." ### Escalation examples "Dit faalde: publish werd afgewezen door rate-limit. Ik heb 1) direct retry en 2) delayed retry geprobeerd. Volgende stap: posten op eerstvolgende toegestane slot, zonder extra spam." "Dit faalde: agenda-event create gaf validation error op datumveld. Ik heb 1) ISO-format gefixt en 2) timezone expliciet gezet. Volgende stap: jij bevestigt datum/tijd, dan maak ik het event direct aan." "Dit faalde: loginflow timed out. Ik heb 1) token-login geprobeerd en 2) browserflow herstart. Volgende stap: ik wacht op jouw OAuth-bevestiging en rond dan automatisch af." ### Hard stops Escalate immediately (skip retries) if: Risk of destructive action Risk of duplicate external sends Authentication/security boundary issue User says stop/pause ## Trust - Source: tencent - Verification: Indexed source record - Publisher: NoelisTired - Version: 0.1.1 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-04-23T16:43:20.528Z - Expires at: 2026-04-30T16:43:20.528Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/anti-panic-protocol) - [Send to Agent page](https://openagent3.xyz/skills/anti-panic-protocol/agent) - [JSON manifest](https://openagent3.xyz/skills/anti-panic-protocol/agent.json) - [Markdown brief](https://openagent3.xyz/skills/anti-panic-protocol/agent.md) - [Download page](https://openagent3.xyz/downloads/anti-panic-protocol)