Agent skill · operations · lobehub
linear
Use for Linear issues, LOBE-xxx links, status updates, completion comments and sub-issue trees.
Why this skill is useful
Adds specific commands and workflows for managing Linear issues that the AI wouldn't reliably generate on its own.
What it needs
Requires linear account access. About 4k tokens when loaded. Last updated 2026-08-07. 81,352 stars on the source repository.
What this skill does
Linear Issue Management Before using Linear workflows, discover the available Linear tools, including deferred tools, and inspect their current schemas. Select tools by capability (issue lookup, images, sub-issues, create/update, comments), not a fixed MCP prefix or historical tool name. Report a missing capability only after discovery. Workflow 1. Retrieve issue details before starting using the issue lookup capability. 2. Read images — issue descriptions often contain screenshots with critical context (mockups, error states, before/after). Use the available image extraction or viewing capability; reading raw markdown alone misses what the reporter was looking at. 3. Check for sub-issues using the available parent filter or issue relation fields. 4. Mark as In Progress at the moment you start planning or implementing — this signals to teammates the issue is owned, so they don't double-pick it up. 5. Follow Per-Issue Completion before moving to the next issue. Creating Issues When creating issues, add the claude code label. Reason: the label is how the team filters/audits AI-generated issues; without it those issues vanish into the general backlog and the team loses visibility into AI contribution patterns. Unless the user explicitly specifies another assignee or asks for the issue to remain unassigned, pass assignee: "me" so the issue is assigned to the authenticated Linear user. Always honor explicit assignment instructions over this default. Language Match the issue language to the conversation that produced it — if you're discussing in 中文，write the issue in 中文；if discussing in English, write it in English. Reason: the issue is a continuation of the conversation, and forcing a language switch creates translation friction for the collaborator who started the thread. Specifics: 中文 conversation → 中文 body; technical terms (file paths, identifiers, library names, commands, error messages) stay in English. English conversation → English body. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills lobehub/linear