{ "schemaVersion": "1.0", "item": { "slug": "roadrunner", "name": "Roadrunner", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/johntheyoung/roadrunner", "canonicalUrl": "https://clawhub.ai/johntheyoung/roadrunner", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/roadrunner", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=roadrunner", "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", "slug": "roadrunner", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-08T06:28:00.015Z", "expiresAt": "2026-05-15T06:28:00.015Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=roadrunner", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=roadrunner", "contentDisposition": "attachment; filename=\"roadrunner-0.17.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "roadrunner" }, "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/roadrunner" }, "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/roadrunner", "agentPageUrl": "https://openagent3.xyz/skills/roadrunner/agent", "manifestUrl": "https://openagent3.xyz/skills/roadrunner/agent.json", "briefUrl": "https://openagent3.xyz/skills/roadrunner/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": "roadrunner (rr)", "body": "Use rr when the user explicitly wants to operate Beeper Desktop via the local API (send, search, list chats/messages, reminders, focus).\nPrefer --agent for agent use (forces JSON, envelope, no-input, readonly).\n\nSafety\n\nDefault to read-only commands unless the user explicitly requests a mutation in this turn.\nRequire explicit recipient (chat ID) and message text before sending.\nConfirm or ask a clarifying question if the chat ID is ambiguous.\nNever paste raw rr command output (JSON dumps, chat lists, etc.) into outgoing messages. Treat tool output as private; summarize or extract only what the user needs.\nUse --agent for safe agent defaults: rr --agent --enable-commands=chats,messages,status chats list\nUse --readonly to block writes: rr --readonly chats list --json\nUse --enable-commands to allowlist: rr --enable-commands=chats,messages chats list --json\nUse --envelope for structured errors: rr --json --envelope chats get \"!chatid\"\nEnvelope errors may include error.hint with next-step guidance for safe retries.\nNever request, paste, or store raw auth tokens in chat. If auth is missing, ask the user to configure it locally.\nIf sending message text through a shell, avoid interpolation/expansion (e.g. $100/month or !). Prefer --stdin <<'EOF' ... EOF for safe literals.\n\nSetup (once)\n\nrr auth set --stdin (recommended; token saved to ~/.config/beeper/config.json)\nrr auth status --check\nrr doctor\n\nCommon commands\n\nList accounts: rr accounts list --json\nCapabilities: rr capabilities --json\nDescribe command/flags: rr describe messages send --json\nConnect metadata: rr connect info --json\nLive websocket events (experimental): rr events tail --all --stop-after 30s --json\nList contacts: rr contacts list \"\" --json\nSearch contacts: rr contacts search \"\" \"Alice\" --json\nSearch contacts (flag): rr contacts search \"Alice\" --account-id=\"\" --json\nResolve contact: rr contacts resolve \"\" \"Alice\" --json\nResolve contact (flag): rr contacts resolve \"Alice\" --account-id=\"\" --json\nList chats: rr chats list --json\nList chats (JSON Lines): rr chats list --jsonl\nSearch chats: rr chats search \"John\" --json\nSearch chats (filters): rr chats search --inbox=primary --unread-only --json\nSearch chats (activity): rr chats search --last-activity-after=\"2024-07-01T00:00:00Z\" --json\nSearch by participant name: rr chats search \"Jamie\" --scope=participants --json\nResolve chat: rr chats resolve \"Jamie\" --json\nGet chat: rr chats get \"!chatid:beeper.com\" --json\nGet chat (bounded participants): rr chats get \"!chatid:beeper.com\" --max-participant-count=50 --json\nStart/resolve DM from merged contact hints: rr chats start \"\" --email \"alice@example.com\" --full-name \"Alice\" --json\nDefault account for commands: rr --account=\"imessage:+123\" chats list --json\nList messages: rr messages list \"!chatid:beeper.com\" --json\nList messages (all pages): rr messages list \"!chatid:beeper.com\" --all --max-items=1000 --json\nList messages (download media): rr messages list \"!chatid:beeper.com\" --download-media --download-dir ./media --json\nSearch messages: rr messages search \"dinner\" --json\nSearch messages (JSON Lines): rr messages search \"dinner\" --jsonl\nSearch messages (all pages): rr messages search \"dinner\" --all --max-items=1000 --json\nSearch messages (filters): rr messages search --sender=me --date-after=\"2024-07-01T00:00:00Z\" --media-types=image --json\nAdd/remove reaction: rr messages react \"!chatid:beeper.com\" \"\" \"👍\" --json / rr messages unreact \"!chatid:beeper.com\" \"\" \"👍\" --json\nTail messages (polling): rr messages tail \"!chatid:beeper.com\" --interval 2s --stop-after 30s --json\nWait for message: rr messages wait --chat-id=\"!chatid:beeper.com\" --contains \"deploy\" --wait-timeout 2m --json\nMessage context: rr messages context \"!chatid:beeper.com\" \"\" --before 5 --after 2 --json\nDraft message (pre-fill without sending): rr focus --chat-id=\"!chatid:beeper.com\" --draft-text=\"Hello!\"\nDraft message from file: rr focus --chat-id=\"!chatid:beeper.com\" --draft-text-file ./draft.txt\nDraft with attachment: rr focus --chat-id=\"!chatid:beeper.com\" --draft-attachment=\"/path/to/file.jpg\"\nDownload attachment: rr assets download \"mxc://example.org/abc123\" --dest \"./attachment.jpg\"\nStream attachment bytes: rr assets serve \"mxc://example.org/abc123\" --dest \"./attachment.jpg\" --json\nFocus app: rr focus\nGlobal search: rr search \"dinner\" --json\nGlobal search messages auto-page: rr search \"dinner\" --messages-all --messages-max-items=500 --messages-limit=20 --json\nStatus summary: rr status --json\nStatus by account: rr status --by-account --json\nUnread rollup: rr unread --json\nGlobal search includes in_groups for participant matches.\n\nMutations (explicit user request only)\n\nMessage send: rr messages send \"!chatid:beeper.com\" \"Hello!\"\nMessage edit: rr messages edit \"!chatid:beeper.com\" \"\" \"Updated text\"\nMessage react/unreact: rr messages react \"!chatid:beeper.com\" \"\" \"👍\" / rr messages unreact \"!chatid:beeper.com\" \"\" \"👍\"\nUpload + send file: rr messages send-file \"!chatid:beeper.com\" ./photo.jpg \"See attached\"\nCreate chat: rr chats create \"\" --participant \"\"\nStart chat from merged contact hints: rr chats start \"\" --email \"alice@example.com\" --full-name \"Alice\"\nArchive/unarchive: rr chats archive \"!chatid:beeper.com\" / rr chats archive \"!chatid:beeper.com\" --unarchive\nReminder mutations: rr reminders set \"!chatid:beeper.com\" \"2h\" / rr reminders clear \"!chatid:beeper.com\"\nAsset uploads: rr assets upload ./photo.jpg / rr assets upload-base64 --content-file ./photo.b64\nFor retries on non-idempotent writes, use --request-id and prefer --dedupe-window.\nUse --dry-run to validate mutating requests without API write side effects.\n\nPagination\n\nAuto-page chats list/search: rr chats list --all --max-items=1000 --json / rr chats search \"alice\" --all --max-items=1000 --json\nAuto-page messages list/search: rr messages list \"!chatid:beeper.com\" --all --max-items=1000 --json / rr messages search \"deploy\" --all --max-items=1000 --json\nChats: rr chats list --cursor=\"\" --direction=before --json\nMessages list: rr messages list \"!chatid:beeper.com\" --cursor=\"\" --direction=before --json\nMessages search (max 20): rr messages search \"project\" --limit=20 --json\nMessages search page: rr messages search \"project\" --cursor=\"\" --direction=before --json\nGlobal search message paging (max 20): rr search \"dinner\" --messages-limit=20 --json\nGlobal search message page: rr search \"dinner\" --messages-cursor=\"\" --messages-direction=before --json\n\nNotes\n\nRequires Beeper Desktop running; token from app settings.\nToken is stored in ~/.config/beeper/config.json via rr auth set (recommended). BEEPER_TOKEN overrides the config file.\nBEEPER_ACCOUNT sets the default account ID (aliases supported).\nrr auth status --check prefers OAuth introspection (/oauth/introspect) when available and falls back to account-list validation on older builds.\nMessage search is literal word match (not semantic).\nrr contacts resolve is strict and fails on ambiguous names; resolve by ID after contacts search when needed.\nIf a DM title shows your own Matrix ID, use --scope=participants to find by name.\nJSON output includes display_name for single chats (derived from participants).\nMessage JSON includes message_type, linked_message_id, is_sender, is_unread, attachments, and reactions.\ndownloaded_attachments is only populated when --download-media is used.\nrr messages send returns pending_message_id (temporary ID).\nAccount network may be missing in newer API builds; rr falls back to \"unknown\" in summaries/search output.\nrr assets serve writes raw bytes to stdout unless --dest is provided.\n--chat does exact matching and fails on ambiguous matches.\nAttachment overrides require --attachment-upload-id; set --attachment-width and --attachment-height together.\n--all has a safety cap (default 500 items, max 5000); use --max-items to tune it.\nPrefer --json or --jsonl (and --no-input) for automation.\n--jsonl emits one JSON object per line and is supported on high-volume list/search commands.\n--dry-run/BEEPER_DRY_RUN validates mutating command inputs and prints preview output without sending write API requests.\nBEEPER_URL overrides API base URL; BEEPER_TIMEOUT sets timeout in seconds.\nJSON/Plain output goes to stdout; errors/hints go to stderr.\nDestructive commands prompt unless --force; --no-input/BEEPER_NO_INPUT fails without --force.\nUse --fail-if-empty on list/search commands to exit with code 1 if no results.\nUse --fields with --plain to select columns (comma-separated).\nIn bash/zsh, ! triggers history expansion. Prefer single quotes, or disable history expansion (set +H in bash, setopt NO_HIST_EXPAND in zsh).\nrr version --json returns features array for capability discovery.\nrr capabilities --json returns full CLI capability metadata.\nrr events tail depends on experimental /v1/ws support in Beeper Desktop; fall back to rr messages tail when unavailable.\nEnvelope error codes: AUTH_ERROR, NOT_FOUND, VALIDATION_ERROR, CONNECTION_ERROR, INTERNAL_ERROR.\nRetry policy: retry CONNECTION_ERROR with backoff; do not blind-retry AUTH_ERROR/VALIDATION_ERROR; refresh IDs before retrying NOT_FOUND.\nNon-idempotent writes: messages send, messages send-file, chats create, chats start, assets upload, assets upload-base64.\nUse --request-id/BEEPER_REQUEST_ID to tag envelope metadata for cross-retry attempt tracing.\nUse --dedupe-window/BEEPER_DEDUPE_WINDOW to block duplicate non-idempotent writes with repeated request IDs.\nLocal smoke check: make test-agent-smoke." } ], "body": "roadrunner (rr)\n\nUse rr when the user explicitly wants to operate Beeper Desktop via the local API (send, search, list chats/messages, reminders, focus). Prefer --agent for agent use (forces JSON, envelope, no-input, readonly).\n\nSafety\n\nDefault to read-only commands unless the user explicitly requests a mutation in this turn.\nRequire explicit recipient (chat ID) and message text before sending.\nConfirm or ask a clarifying question if the chat ID is ambiguous.\nNever paste raw rr command output (JSON dumps, chat lists, etc.) into outgoing messages. Treat tool output as private; summarize or extract only what the user needs.\nUse --agent for safe agent defaults: rr --agent --enable-commands=chats,messages,status chats list\nUse --readonly to block writes: rr --readonly chats list --json\nUse --enable-commands to allowlist: rr --enable-commands=chats,messages chats list --json\nUse --envelope for structured errors: rr --json --envelope chats get \"!chatid\"\nEnvelope errors may include error.hint with next-step guidance for safe retries.\nNever request, paste, or store raw auth tokens in chat. If auth is missing, ask the user to configure it locally.\nIf sending message text through a shell, avoid interpolation/expansion (e.g. $100/month or !). Prefer --stdin <<'EOF' ... EOF for safe literals.\n\nSetup (once)\n\nrr auth set --stdin (recommended; token saved to ~/.config/beeper/config.json)\nrr auth status --check\nrr doctor\n\nCommon commands\n\nList accounts: rr accounts list --json\nCapabilities: rr capabilities --json\nDescribe command/flags: rr describe messages send --json\nConnect metadata: rr connect info --json\nLive websocket events (experimental): rr events tail --all --stop-after 30s --json\nList contacts: rr contacts list \"\" --json\nSearch contacts: rr contacts search \"\" \"Alice\" --json\nSearch contacts (flag): rr contacts search \"Alice\" --account-id=\"\" --json\nResolve contact: rr contacts resolve \"\" \"Alice\" --json\nResolve contact (flag): rr contacts resolve \"Alice\" --account-id=\"\" --json\nList chats: rr chats list --json\nList chats (JSON Lines): rr chats list --jsonl\nSearch chats: rr chats search \"John\" --json\nSearch chats (filters): rr chats search --inbox=primary --unread-only --json\nSearch chats (activity): rr chats search --last-activity-after=\"2024-07-01T00:00:00Z\" --json\nSearch by participant name: rr chats search \"Jamie\" --scope=participants --json\nResolve chat: rr chats resolve \"Jamie\" --json\nGet chat: rr chats get \"!chatid:beeper.com\" --json\nGet chat (bounded participants): rr chats get \"!chatid:beeper.com\" --max-participant-count=50 --json\nStart/resolve DM from merged contact hints: rr chats start \"\" --email \"alice@example.com\" --full-name \"Alice\" --json\nDefault account for commands: rr --account=\"imessage:+123\" chats list --json\nList messages: rr messages list \"!chatid:beeper.com\" --json\nList messages (all pages): rr messages list \"!chatid:beeper.com\" --all --max-items=1000 --json\nList messages (download media): rr messages list \"!chatid:beeper.com\" --download-media --download-dir ./media --json\nSearch messages: rr messages search \"dinner\" --json\nSearch messages (JSON Lines): rr messages search \"dinner\" --jsonl\nSearch messages (all pages): rr messages search \"dinner\" --all --max-items=1000 --json\nSearch messages (filters): rr messages search --sender=me --date-after=\"2024-07-01T00:00:00Z\" --media-types=image --json\nAdd/remove reaction: rr messages react \"!chatid:beeper.com\" \"\" \"👍\" --json / rr messages unreact \"!chatid:beeper.com\" \"\" \"👍\" --json\nTail messages (polling): rr messages tail \"!chatid:beeper.com\" --interval 2s --stop-after 30s --json\nWait for message: rr messages wait --chat-id=\"!chatid:beeper.com\" --contains \"deploy\" --wait-timeout 2m --json\nMessage context: rr messages context \"!chatid:beeper.com\" \"\" --before 5 --after 2 --json\nDraft message (pre-fill without sending): rr focus --chat-id=\"!chatid:beeper.com\" --draft-text=\"Hello!\"\nDraft message from file: rr focus --chat-id=\"!chatid:beeper.com\" --draft-text-file ./draft.txt\nDraft with attachment: rr focus --chat-id=\"!chatid:beeper.com\" --draft-attachment=\"/path/to/file.jpg\"\nDownload attachment: rr assets download \"mxc://example.org/abc123\" --dest \"./attachment.jpg\"\nStream attachment bytes: rr assets serve \"mxc://example.org/abc123\" --dest \"./attachment.jpg\" --json\nFocus app: rr focus\nGlobal search: rr search \"dinner\" --json\nGlobal search messages auto-page: rr search \"dinner\" --messages-all --messages-max-items=500 --messages-limit=20 --json\nStatus summary: rr status --json\nStatus by account: rr status --by-account --json\nUnread rollup: rr unread --json\nGlobal search includes in_groups for participant matches.\n\nMutations (explicit user request only)\n\nMessage send: rr messages send \"!chatid:beeper.com\" \"Hello!\"\nMessage edit: rr messages edit \"!chatid:beeper.com\" \"\" \"Updated text\"\nMessage react/unreact: rr messages react \"!chatid:beeper.com\" \"\" \"👍\" / rr messages unreact \"!chatid:beeper.com\" \"\" \"👍\"\nUpload + send file: rr messages send-file \"!chatid:beeper.com\" ./photo.jpg \"See attached\"\nCreate chat: rr chats create \"\" --participant \"\"\nStart chat from merged contact hints: rr chats start \"\" --email \"alice@example.com\" --full-name \"Alice\"\nArchive/unarchive: rr chats archive \"!chatid:beeper.com\" / rr chats archive \"!chatid:beeper.com\" --unarchive\nReminder mutations: rr reminders set \"!chatid:beeper.com\" \"2h\" / rr reminders clear \"!chatid:beeper.com\"\nAsset uploads: rr assets upload ./photo.jpg / rr assets upload-base64 --content-file ./photo.b64\nFor retries on non-idempotent writes, use --request-id and prefer --dedupe-window.\nUse --dry-run to validate mutating requests without API write side effects.\n\nPagination\n\nAuto-page chats list/search: rr chats list --all --max-items=1000 --json / rr chats search \"alice\" --all --max-items=1000 --json\nAuto-page messages list/search: rr messages list \"!chatid:beeper.com\" --all --max-items=1000 --json / rr messages search \"deploy\" --all --max-items=1000 --json\nChats: rr chats list --cursor=\"\" --direction=before --json\nMessages list: rr messages list \"!chatid:beeper.com\" --cursor=\"\" --direction=before --json\nMessages search (max 20): rr messages search \"project\" --limit=20 --json\nMessages search page: rr messages search \"project\" --cursor=\"\" --direction=before --json\nGlobal search message paging (max 20): rr search \"dinner\" --messages-limit=20 --json\nGlobal search message page: rr search \"dinner\" --messages-cursor=\"\" --messages-direction=before --json\n\nNotes\n\nRequires Beeper Desktop running; token from app settings.\nToken is stored in ~/.config/beeper/config.json via rr auth set (recommended). BEEPER_TOKEN overrides the config file.\nBEEPER_ACCOUNT sets the default account ID (aliases supported).\nrr auth status --check prefers OAuth introspection (/oauth/introspect) when available and falls back to account-list validation on older builds.\nMessage search is literal word match (not semantic).\nrr contacts resolve is strict and fails on ambiguous names; resolve by ID after contacts search when needed.\nIf a DM title shows your own Matrix ID, use --scope=participants to find by name.\nJSON output includes display_name for single chats (derived from participants).\nMessage JSON includes message_type, linked_message_id, is_sender, is_unread, attachments, and reactions.\ndownloaded_attachments is only populated when --download-media is used.\nrr messages send returns pending_message_id (temporary ID).\nAccount network may be missing in newer API builds; rr falls back to \"unknown\" in summaries/search output.\nrr assets serve writes raw bytes to stdout unless --dest is provided.\n--chat does exact matching and fails on ambiguous matches.\nAttachment overrides require --attachment-upload-id; set --attachment-width and --attachment-height together.\n--all has a safety cap (default 500 items, max 5000); use --max-items to tune it.\nPrefer --json or --jsonl (and --no-input) for automation.\n--jsonl emits one JSON object per line and is supported on high-volume list/search commands.\n--dry-run/BEEPER_DRY_RUN validates mutating command inputs and prints preview output without sending write API requests.\nBEEPER_URL overrides API base URL; BEEPER_TIMEOUT sets timeout in seconds.\nJSON/Plain output goes to stdout; errors/hints go to stderr.\nDestructive commands prompt unless --force; --no-input/BEEPER_NO_INPUT fails without --force.\nUse --fail-if-empty on list/search commands to exit with code 1 if no results.\nUse --fields with --plain to select columns (comma-separated).\nIn bash/zsh, ! triggers history expansion. Prefer single quotes, or disable history expansion (set +H in bash, setopt NO_HIST_EXPAND in zsh).\nrr version --json returns features array for capability discovery.\nrr capabilities --json returns full CLI capability metadata.\nrr events tail depends on experimental /v1/ws support in Beeper Desktop; fall back to rr messages tail when unavailable.\nEnvelope error codes: AUTH_ERROR, NOT_FOUND, VALIDATION_ERROR, CONNECTION_ERROR, INTERNAL_ERROR.\nRetry policy: retry CONNECTION_ERROR with backoff; do not blind-retry AUTH_ERROR/VALIDATION_ERROR; refresh IDs before retrying NOT_FOUND.\nNon-idempotent writes: messages send, messages send-file, chats create, chats start, assets upload, assets upload-base64.\nUse --request-id/BEEPER_REQUEST_ID to tag envelope metadata for cross-retry attempt tracing.\nUse --dedupe-window/BEEPER_DEDUPE_WINDOW to block duplicate non-idempotent writes with repeated request IDs.\nLocal smoke check: make test-agent-smoke." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/johntheyoung/roadrunner", "publisherUrl": "https://clawhub.ai/johntheyoung/roadrunner", "owner": "johntheyoung", "version": "0.17.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/roadrunner", "downloadUrl": "https://openagent3.xyz/downloads/roadrunner", "agentUrl": "https://openagent3.xyz/skills/roadrunner/agent", "manifestUrl": "https://openagent3.xyz/skills/roadrunner/agent.json", "briefUrl": "https://openagent3.xyz/skills/roadrunner/agent.md" } }