Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub · Communication & Collaboration
LBA
Automate Linear.app workflows in the OpenClaw-managed browser profile using browser tool actions (open, navigate, snapshot, act). Use when users want UI-base...
skill openclawclawhub Free
Automate Linear.app workflows in the OpenClaw-managed browser profile using browser tool actions (open, navigate, snapshot, act). Use when users want UI-base...
⬇ 0 downloads ★ 0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- _meta.json, SKILL.md, .clawhub/origin.json, references/workflows.md, references/selectors-and-fallbacks.md
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- 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.
New install
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
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.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.0.2
Provenance
- Publisher
- hassam-powerhouse
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Linear Browser Automation
Automate Linear workflows through UI interactions in the OpenClaw-managed browser.
Execution mode
Always use browser profile: openclaw Always run actions against host browser control Reuse an already-open, logged-in Linear tab in the managed browser whenever available. Do not open a new Linear tab if an existing authenticated Linear tab can be reused. Keep actions in one tab unless explicitly opening a new tab is required by user request.
Standard workflow
Ensure managed browser is running (profile="openclaw"). Check existing open tabs in managed browser and prefer a tab already on Linear. If an existing Linear tab is found: focus and reuse that tab snapshot and detect auth state If no Linear tab exists, open/navigate to https://linear.app/. If on public landing page / unauthenticated state: automatically navigate to /login show a browser alert asking the user to log in to continue wait for authenticated dashboard/workspace state After login is complete and dashboard is visible, continue automatically from the same task context and same tab. Resolve references from the snapshot. Execute deterministic actions (click/type/select/press). Re-snapshot and verify expected state before finishing.
Required-input policy (hard rule)
For all Linear actions, always collect and confirm required details in chat before executing.
1) Create issue
Required fields: Team (or project context that implies team) Title Optional fields (prompt if missing): description, priority, assignee, labels, due date. Before submission, always present a summary block and ask: Proceed? (yes/no) Only proceed on explicit yes. Any other response (no/cancel/edit/silence) means do not submit.
2) Edit issue and comment on issue
Required fields: Team name Issue number/identifier (e.g., POW-123) Hard rule: Do not run these automations when either team name or issue number is missing. If the user gives only title text or a partial reference, ask for the team name and issue number. Resolve and open the exact issue from the provided team + issue number before making changes.
3) Move issue state
Non-negotiable required fields: Team name Issue number/identifier (e.g., POW-123) New state/status (e.g., Todo, In Progress, Done) Comment text to add on the issue Valid issue statuses (only these are accepted): Backlog Todo In Progress Done Canceled Duplicate Hard rule: Do not run move-state automation when any one of these is missing. If state is not explicitly provided, ask for it and wait. If comment text is not explicitly provided, ask for it and wait. Reject any state value not in the valid-status list and ask user to pick one valid option. Do not infer or auto-pick a state unless user explicitly instructs you to choose one. Resolve the exact issue from team + issue number first, then apply the requested new state and add the comment.
Priority validation rule
For any automation that sets or updates issue priority, only accept these values: Urgent High Medium Low Hard rule: Reject any other priority value and ask for one valid option.
Required-input conversation contract
When user requests a new issue: Check whether required fields are already provided. Ask only for missing required fields first. Ask optional fields (or accept defaults). Present final summary: Team/Project Title Description Priority Assignee Labels Due date Ask Proceed? (yes/no). Submit only after yes. When user requests edit/comment: Check for team name and issue number first. Ask for whichever is missing. Confirm target in one line (e.g., Target issue: POW-123 (Powerhouse)). Execute only after target resolution is unambiguous. When user requests move-state: Check for team name, issue number, explicit new state, and comment text. Ask for whichever is missing. Confirm target, destination, and comment in one line (e.g., Target issue: POW-123 (Powerhouse) → In Progress | Comment: <text>). Execute only after target resolution, new state, and comment are unambiguous.
Safety + reliability rules
Prefer stable selectors/refs from fresh snapshot before acting. Re-snapshot after major UI transitions. If unauthenticated state appears, auto-navigate to login and trigger an in-browser alert instructing the user to log in. After user login completes and dashboard is detected, resume the task automatically. For destructive actions (delete/archive), require explicit confirmation. If team/project context is ambiguous, ask before acting.
Supported automations
Open Linear and verify dashboard loaded Search/filter issues (team, assignee, state, label) Create new issue (with required-input policy) Edit issue fields (title, description, priority, due date, labels) Move issue state (Backlog/In Progress/Done) Add comments Bulk triage (limited batch with confirmation) Visual verification (post-action snapshot checks)
Example test prompts (one per supported automation)
Use these prompts verbatim (or with your own team/issue values) to test each supported automation.
1) Open Linear and verify dashboard loaded
"Using the linear-browser-automation skill in the OpenClaw-managed browser, open Linear and verify the workspace dashboard is loaded for team <team_name>. Return the current page URL, visible workspace/team name, and whether auth is active."
2) Search/filter issues
"Using the linear-browser-automation skill in the OpenClaw-managed browser, list issues for team <team_name> filtered by assignee <assignee_name>, state <state_name>, and label <label_name>. Return issue identifier, title, state, assignee, labels, due date, and URL. If no issues match, say No matching issues found."
3) Create new issue
"Using the linear-browser-automation skill in the OpenClaw-managed browser, create a new issue in team <team_name> with title <issue_title>. Set priority <priority_name>, assignee <assignee_name>, label <label_name>, and due date <due_date_yyyy-mm-dd>. Show a summary and ask Proceed? (yes/no) before submitting."
4) Edit issue fields
"Using the linear-browser-automation skill in the OpenClaw-managed browser, edit issue <issue_number> in team <team_name>. Update title to <updated_issue_title>, set priority to <priority_name>, set due date to <due_date_yyyy-mm-dd>, and ensure label <label_name> is applied. Return issue identifier, updated title, state, priority, assignee, labels, due date, and URL."
5) Move issue state
"Using the linear-browser-automation skill in the OpenClaw-managed browser, move issue <issue_number> in team <team_name> to state <new_state> and add this comment: <comment_text>. Return issue identifier, title, previous state, new state, assignee, labels, due date, comment posted, and URL."
6) Add comments
"Using the linear-browser-automation skill in the OpenClaw-managed browser, add this comment to issue <issue_number> in team <team_name>: <comment_text>. Return issue identifier, title, assignee, current state, comment text posted, and URL."
7) Bulk triage
"Using the linear-browser-automation skill in the OpenClaw-managed browser, triage up to <max_items> issues in team <team_name> where state is <source_state> and assignee is empty. For each selected issue, set priority to <priority_name> and add label <label_name>. Show the candidate list first, ask for confirmation, then apply updates and return the changed issues with before/after fields."
8) Visual verification
"Using the linear-browser-automation skill in the OpenClaw-managed browser, open issue <issue_number> in team <team_name> 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."
Open Linear in managed profile
start browser (profile="openclaw") open https://linear.app/
Reuse existing tab
navigate current targetId to target URL
Interaction cycle
snapshot (refs=aria preferred) act (click/type/select/press) snapshot and verify
Failure handling
Missing element/ref: refresh snapshot retry once with updated refs Navigation/login interruption: pause and ask user to complete auth/MFA Ambiguous target: ask for disambiguation (team/project/issue) Missing required issue fields: keep prompting until provided or user cancels No explicit yes on submit confirmation: do not submit
Completion report format
Return: actions performed items changed (issue IDs/titles if visible) verification checks passed/failed any manual follow-up needed
Category context
Messaging, meetings, inboxes, CRM, and teammate communication surfaces.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
3 Docs2 Config
- SKILL.md
- references/selectors-and-fallbacks.md
- references/workflows.md
- _meta.json
- .clawhub/origin.json