{ "schemaVersion": "1.0", "item": { "slug": "lba", "name": "LBA", "source": "tencent", "type": "skill", "category": "通讯协作", "sourceUrl": "https://clawhub.ai/hassam-powerhouse/lba", "canonicalUrl": "https://clawhub.ai/hassam-powerhouse/lba", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/lba", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=lba", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "_meta.json", "SKILL.md", ".clawhub/origin.json", "references/workflows.md", "references/selectors-and-fallbacks.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": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/lba" }, "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/lba", "agentPageUrl": "https://openagent3.xyz/skills/lba/agent", "manifestUrl": "https://openagent3.xyz/skills/lba/agent.json", "briefUrl": "https://openagent3.xyz/skills/lba/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": "Linear Browser Automation", "body": "Automate Linear workflows through UI interactions in the OpenClaw-managed browser." }, { "title": "Execution mode", "body": "Always use browser profile: openclaw\nAlways run actions against host browser control\nReuse an already-open, logged-in Linear tab in the managed browser whenever available.\nDo not open a new Linear tab if an existing authenticated Linear tab can be reused.\nKeep actions in one tab unless explicitly opening a new tab is required by user request." }, { "title": "Standard workflow", "body": "Ensure managed browser is running (profile=\"openclaw\").\nCheck existing open tabs in managed browser and prefer a tab already on Linear.\nIf an existing Linear tab is found:\n\nfocus and reuse that tab\nsnapshot and detect auth state\n\n\nIf no Linear tab exists, open/navigate to https://linear.app/.\nIf on public landing page / unauthenticated state:\n\nautomatically navigate to /login\nshow a browser alert asking the user to log in to continue\nwait for authenticated dashboard/workspace state\n\n\nAfter login is complete and dashboard is visible, continue automatically from the same task context and same tab.\nResolve references from the snapshot.\nExecute deterministic actions (click/type/select/press).\nRe-snapshot and verify expected state before finishing." }, { "title": "Required-input policy (hard rule)", "body": "For all Linear actions, always collect and confirm required details in chat before executing." }, { "title": "1) Create issue", "body": "Required fields:\n\nTeam (or project context that implies team)\nTitle\n\nOptional fields (prompt if missing): description, priority, assignee, labels, due date.\n\nBefore submission, always present a summary block and ask:\n\nProceed? (yes/no)\n\nOnly proceed on explicit yes.\nAny other response (no/cancel/edit/silence) means do not submit." }, { "title": "2) Edit issue and comment on issue", "body": "Required fields:\n\nTeam name\nIssue number/identifier (e.g., POW-123)\n\nHard rule:\n\nDo not run these automations when either team name or issue number is missing.\nIf the user gives only title text or a partial reference, ask for the team name and issue number.\nResolve and open the exact issue from the provided team + issue number before making changes." }, { "title": "3) Move issue state", "body": "Non-negotiable required fields:\n\nTeam name\nIssue number/identifier (e.g., POW-123)\nNew state/status (e.g., Todo, In Progress, Done)\nComment text to add on the issue\n\nValid issue statuses (only these are accepted):\n\nBacklog\nTodo\nIn Progress\nDone\nCanceled\nDuplicate\n\nHard rule:\n\nDo not run move-state automation when any one of these is missing.\nIf state is not explicitly provided, ask for it and wait.\nIf comment text is not explicitly provided, ask for it and wait.\nReject any state value not in the valid-status list and ask user to pick one valid option.\nDo not infer or auto-pick a state unless user explicitly instructs you to choose one.\nResolve the exact issue from team + issue number first, then apply the requested new state and add the comment." }, { "title": "Priority validation rule", "body": "For any automation that sets or updates issue priority, only accept these values:\n\nUrgent\nHigh\nMedium\nLow\n\nHard rule:\n\nReject any other priority value and ask for one valid option." }, { "title": "Required-input conversation contract", "body": "When user requests a new issue:\n\nCheck whether required fields are already provided.\nAsk only for missing required fields first.\nAsk optional fields (or accept defaults).\nPresent final summary:\n\nTeam/Project\nTitle\nDescription\nPriority\nAssignee\nLabels\nDue date\n\n\nAsk Proceed? (yes/no).\nSubmit only after yes.\n\nWhen user requests edit/comment:\n\nCheck for team name and issue number first.\nAsk for whichever is missing.\nConfirm target in one line (e.g., Target issue: POW-123 (Powerhouse)).\nExecute only after target resolution is unambiguous.\n\nWhen user requests move-state:\n\nCheck for team name, issue number, explicit new state, and comment text.\nAsk for whichever is missing.\nConfirm target, destination, and comment in one line (e.g., Target issue: POW-123 (Powerhouse) → In Progress | Comment: ).\nExecute only after target resolution, new state, and comment are unambiguous." }, { "title": "Safety + reliability rules", "body": "Prefer stable selectors/refs from fresh snapshot before acting.\nRe-snapshot after major UI transitions.\nIf unauthenticated state appears, auto-navigate to login and trigger an in-browser alert instructing the user to log in.\nAfter user login completes and dashboard is detected, resume the task automatically.\nFor destructive actions (delete/archive), require explicit confirmation.\nIf team/project context is ambiguous, ask before acting." }, { "title": "Supported automations", "body": "Open Linear and verify dashboard loaded\nSearch/filter issues (team, assignee, state, label)\nCreate new issue (with required-input policy)\nEdit issue fields (title, description, priority, due date, labels)\nMove issue state (Backlog/In Progress/Done)\nAdd comments\nBulk triage (limited batch with confirmation)\nVisual verification (post-action snapshot checks)" }, { "title": "Example test prompts (one per supported automation)", "body": "Use these prompts verbatim (or with your own team/issue values) to test each supported automation." }, { "title": "1) Open Linear and verify dashboard loaded", "body": "\"Using the linear-browser-automation skill in the OpenClaw-managed browser, open Linear and verify the workspace dashboard is loaded for team . Return the current page URL, visible workspace/team name, and whether auth is active.\"" }, { "title": "2) Search/filter issues", "body": "\"Using the linear-browser-automation skill in the OpenClaw-managed browser, list issues for team filtered by assignee , state , and label . Return issue identifier, title, state, assignee, labels, due date, and URL. If no issues match, say No matching issues found.\"" }, { "title": "3) Create new issue", "body": "\"Using the linear-browser-automation skill in the OpenClaw-managed browser, create a new issue in team with title . Set priority , assignee , label , and due date . Show a summary and ask Proceed? (yes/no) before submitting.\"" }, { "title": "4) Edit issue fields", "body": "\"Using the linear-browser-automation skill in the OpenClaw-managed browser, edit issue in team . Update title to , set priority to , set due date to , and ensure label is applied. Return issue identifier, updated title, state, priority, assignee, labels, due date, and URL.\"" }, { "title": "5) Move issue state", "body": "\"Using the linear-browser-automation skill in the OpenClaw-managed browser, move issue in team to state and add this comment: . Return issue identifier, title, previous state, new state, assignee, labels, due date, comment posted, and URL.\"" }, { "title": "6) Add comments", "body": "\"Using the linear-browser-automation skill in the OpenClaw-managed browser, add this comment to issue in team : . Return issue identifier, title, assignee, current state, comment text posted, and URL.\"" }, { "title": "7) Bulk triage", "body": "\"Using the linear-browser-automation skill in the OpenClaw-managed browser, triage up to issues in team where state is and assignee is empty. For each selected issue, set priority to and add label . Show the candidate list first, ask for confirmation, then apply updates and return the changed issues with before/after fields.\"" }, { "title": "8) Visual verification", "body": "\"Using the linear-browser-automation skill in the OpenClaw-managed browser, open issue in team and perform visual verification only (no edits). Return what is visible for title, state, priority, assignee, labels, due date, and URL, and explicitly state whether each verification check passed or failed.\"" }, { "title": "Open Linear in managed profile", "body": "start browser (profile=\"openclaw\")\nopen https://linear.app/" }, { "title": "Reuse existing tab", "body": "navigate current targetId to target URL" }, { "title": "Interaction cycle", "body": "snapshot (refs=aria preferred)\nact (click/type/select/press)\nsnapshot and verify" }, { "title": "Failure handling", "body": "Missing element/ref:\n\nrefresh snapshot\nretry once with updated refs\n\n\nNavigation/login interruption:\n\npause and ask user to complete auth/MFA\n\n\nAmbiguous target:\n\nask for disambiguation (team/project/issue)\n\n\nMissing required issue fields:\n\nkeep prompting until provided or user cancels\n\n\nNo explicit yes on submit confirmation:\n\ndo not submit" }, { "title": "Completion report format", "body": "Return:\n\nactions performed\nitems changed (issue IDs/titles if visible)\nverification checks passed/failed\nany manual follow-up needed" } ], "body": "Linear Browser Automation\n\nAutomate Linear workflows through UI interactions in the OpenClaw-managed browser.\n\nExecution mode\nAlways use browser profile: openclaw\nAlways run actions against host browser control\nReuse an already-open, logged-in Linear tab in the managed browser whenever available.\nDo not open a new Linear tab if an existing authenticated Linear tab can be reused.\nKeep actions in one tab unless explicitly opening a new tab is required by user request.\nStandard workflow\nEnsure managed browser is running (profile=\"openclaw\").\nCheck existing open tabs in managed browser and prefer a tab already on Linear.\nIf an existing Linear tab is found:\nfocus and reuse that tab\nsnapshot and detect auth state\nIf no Linear tab exists, open/navigate to https://linear.app/.\nIf on public landing page / unauthenticated state:\nautomatically navigate to /login\nshow a browser alert asking the user to log in to continue\nwait for authenticated dashboard/workspace state\nAfter login is complete and dashboard is visible, continue automatically from the same task context and same tab.\nResolve references from the snapshot.\nExecute deterministic actions (click/type/select/press).\nRe-snapshot and verify expected state before finishing.\nRequired-input policy (hard rule)\n\nFor all Linear actions, always collect and confirm required details in chat before executing.\n\n1) Create issue\n\nRequired fields:\n\nTeam (or project context that implies team)\nTitle\n\nOptional fields (prompt if missing): description, priority, assignee, labels, due date.\n\nBefore submission, always present a summary block and ask:\n\nProceed? (yes/no)\n\nOnly proceed on explicit yes. Any other response (no/cancel/edit/silence) means do not submit.\n\n2) Edit issue and comment on issue\n\nRequired fields:\n\nTeam name\nIssue number/identifier (e.g., POW-123)\n\nHard rule:\n\nDo not run these automations when either team name or issue number is missing.\nIf the user gives only title text or a partial reference, ask for the team name and issue number.\nResolve and open the exact issue from the provided team + issue number before making changes.\n3) Move issue state\n\nNon-negotiable required fields:\n\nTeam name\nIssue number/identifier (e.g., POW-123)\nNew state/status (e.g., Todo, In Progress, Done)\nComment text to add on the issue\n\nValid issue statuses (only these are accepted):\n\nBacklog\nTodo\nIn Progress\nDone\nCanceled\nDuplicate\n\nHard rule:\n\nDo not run move-state automation when any one of these is missing.\nIf state is not explicitly provided, ask for it and wait.\nIf comment text is not explicitly provided, ask for it and wait.\nReject any state value not in the valid-status list and ask user to pick one valid option.\nDo not infer or auto-pick a state unless user explicitly instructs you to choose one.\nResolve the exact issue from team + issue number first, then apply the requested new state and add the comment.\nPriority validation rule\n\nFor any automation that sets or updates issue priority, only accept these values:\n\nUrgent\nHigh\nMedium\nLow\n\nHard rule:\n\nReject any other priority value and ask for one valid option.\nRequired-input conversation contract\n\nWhen user requests a new issue:\n\nCheck whether required fields are already provided.\nAsk only for missing required fields first.\nAsk optional fields (or accept defaults).\nPresent final summary:\nTeam/Project\nTitle\nDescription\nPriority\nAssignee\nLabels\nDue date\nAsk Proceed? (yes/no).\nSubmit only after yes.\n\nWhen user requests edit/comment:\n\nCheck for team name and issue number first.\nAsk for whichever is missing.\nConfirm target in one line (e.g., Target issue: POW-123 (Powerhouse)).\nExecute only after target resolution is unambiguous.\n\nWhen user requests move-state:\n\nCheck for team name, issue number, explicit new state, and comment text.\nAsk for whichever is missing.\nConfirm target, destination, and comment in one line (e.g., Target issue: POW-123 (Powerhouse) → In Progress | Comment: ).\nExecute only after target resolution, new state, and comment are unambiguous.\nSafety + reliability rules\nPrefer stable selectors/refs from fresh snapshot before acting.\nRe-snapshot after major UI transitions.\nIf unauthenticated state appears, auto-navigate to login and trigger an in-browser alert instructing the user to log in.\nAfter user login completes and dashboard is detected, resume the task automatically.\nFor destructive actions (delete/archive), require explicit confirmation.\nIf team/project context is ambiguous, ask before acting.\nSupported automations\nOpen Linear and verify dashboard loaded\nSearch/filter issues (team, assignee, state, label)\nCreate new issue (with required-input policy)\nEdit issue fields (title, description, priority, due date, labels)\nMove issue state (Backlog/In Progress/Done)\nAdd comments\nBulk triage (limited batch with confirmation)\nVisual verification (post-action snapshot checks)\nExample test prompts (one per supported automation)\n\nUse these prompts verbatim (or with your own team/issue values) to test each supported automation.\n\n1) Open Linear and verify dashboard loaded\n\n\"Using the linear-browser-automation skill in the OpenClaw-managed browser, open Linear and verify the workspace dashboard is loaded for team . Return the current page URL, visible workspace/team name, and whether auth is active.\"\n\n2) Search/filter issues\n\n\"Using the linear-browser-automation skill in the OpenClaw-managed browser, list issues for team filtered by assignee , state , and label . Return issue identifier, title, state, assignee, labels, due date, and URL. If no issues match, say No matching issues found.\"\n\n3) Create new issue\n\n\"Using the linear-browser-automation skill in the OpenClaw-managed browser, create a new issue in team with title . Set priority , assignee , label , and due date . Show a summary and ask Proceed? (yes/no) before submitting.\"\n\n4) Edit issue fields\n\n\"Using the linear-browser-automation skill in the OpenClaw-managed browser, edit issue in team . Update title to , set priority to , set due date to , and ensure label is applied. Return issue identifier, updated title, state, priority, assignee, labels, due date, and URL.\"\n\n5) Move issue state\n\n\"Using the linear-browser-automation skill in the OpenClaw-managed browser, move issue in team to state and add this comment: . Return issue identifier, title, previous state, new state, assignee, labels, due date, comment posted, and URL.\"\n\n6) Add comments\n\n\"Using the linear-browser-automation skill in the OpenClaw-managed browser, add this comment to issue in team : . Return issue identifier, title, assignee, current state, comment text posted, and URL.\"\n\n7) Bulk triage\n\n\"Using the linear-browser-automation skill in the OpenClaw-managed browser, triage up to issues in team where state is and assignee is empty. For each selected issue, set priority to and add label . Show the candidate list first, ask for confirmation, then apply updates and return the changed issues with before/after fields.\"\n\n8) Visual verification\n\n\"Using the linear-browser-automation skill in the OpenClaw-managed browser, open issue in team and perform visual verification only (no edits). Return what is visible for title, state, priority, assignee, labels, due date, and URL, and explicitly state whether each verification check passed or failed.\"\n\nSuggested command patterns (agent-side)\nOpen Linear in managed profile\nstart browser (profile=\"openclaw\")\nopen https://linear.app/\nReuse existing tab\nnavigate current targetId to target URL\nInteraction cycle\nsnapshot (refs=aria preferred)\nact (click/type/select/press)\nsnapshot and verify\nFailure handling\nMissing element/ref:\nrefresh snapshot\nretry once with updated refs\nNavigation/login interruption:\npause and ask user to complete auth/MFA\nAmbiguous target:\nask for disambiguation (team/project/issue)\nMissing required issue fields:\nkeep prompting until provided or user cancels\nNo explicit yes on submit confirmation:\ndo not submit\nCompletion report format\n\nReturn:\n\nactions performed\nitems changed (issue IDs/titles if visible)\nverification checks passed/failed\nany manual follow-up needed" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/hassam-powerhouse/lba", "publisherUrl": "https://clawhub.ai/hassam-powerhouse/lba", "owner": "hassam-powerhouse", "version": "1.0.2", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/lba", "downloadUrl": "https://openagent3.xyz/downloads/lba", "agentUrl": "https://openagent3.xyz/skills/lba/agent", "manifestUrl": "https://openagent3.xyz/skills/lba/agent.json", "briefUrl": "https://openagent3.xyz/skills/lba/agent.md" } }