src/orchestrator/plugins/linear/SKILL.md
Creates and names Linear issues, assigns labels and priorities, manages status transitions, and links issues to PRs. Use when decomposing features into tasks or resuming interrupted sessions. Trigger terms: tickets, backlog, task breakdown, project board, sprint planning
npx skillsauth add monkilabs/opencastle linear-task-managementInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
For project-specific team ID, workflow state UUIDs, and label UUIDs, see tracker-config.md. For status transitions, follow the Status Update Procedure section below.
// Create issue
{ "teamId": "TEAM_UUID", "title": "[UI] Build PriceRangeFilter", "description": "Objective: ...\nFiles: ...\nAC: ...", "labelIds": ["LABEL_UUID"], "priority": 2 }
// → { "id": "TAS-42", "url": "https://linear.app/team/TAS-42" }
// Update issue status (see Status Update Procedure)
{ "issueId": "TAS-42", "stateId": "<UUID from tracker-config.md>" }
// Search issues
{ "query": "is:open assignee:me", "teamId": "TEAM_UUID" }
[Bug] <symptom>, Labels bug + domain, Priority P1–P4 with rationale, Acceptance steps.Name issues using a verb-first, actionable format that maps to operator intent:
Add priceRange field to place type -> Action: `Add schema: priceRange to place`
Run DB migration to add price_range column -> Action: `Migrate DB: add price_range`
Update GROQ query to include priceRange filter -> Action: `Update query: include priceRange`
Build PriceRangeFilter component -> Action: `Implement UI: PriceRangeFilter`
| Level | When to use | |-------|-------------| | P1 (Urgent) | Blocks other tasks, critical path | | P2 (High) | Core feature work, on critical path | | P3 (Medium) | Supporting tasks, can be parallelized | | P4 (Low) | Docs, cleanup, polish |
Backlog -> Todo -> In Progress -> In Review -> Done -> Cancelled
Todo → In Progress on start; In Progress → Done on verified completion; Any → Cancelled to drop.TAS-123).Every issue must include: Objective (one sentence), Files (partition) (paths this agent may modify), Acceptance Criteria (verifiable checklist), Dependencies (#TAS-XX).
Group related issues under a Linear project; issues track individual subtasks.
If creation fails: check team ID and state UUIDs in tracker-config.md; retry once. If board state is inconsistent on resume: re-read all issue statuses before proceeding.
⚠️
update_issuerequires a workflow state UUID — passing a name like"In Progress"always fails withstateId must be a UUID.
list_issues/get_issue are display-only, not valid stateId values.tracker-config.md has no state UUIDs, skip status updates and log a warning.// ✅ UUID from tracker-config.md
{ "issueId": "TAS-42", "stateId": "a1b2c3d4-e5f6-7890-abcd-ef1234567890" }
// ❌ FAILS — name, not UUID
{ "issueId": "TAS-42", "status": "In Progress" }
If tracker-config.md lacks state UUIDs, ask the user to populate them from Linear Settings → Teams → Workflow (UUID in browser URL per state) or via the GraphQL workflowStates { nodes { id name } } query.
development
Defines 10 sequential validation gates: secret scanning, lint/test/build checks, blast radius analysis, dependency auditing, browser testing, cache management, regression checks, smoke tests. Use when running pre-deploy validation or CI checks, CI/CD pipelines, deployment pipeline validation, pre-merge checks, continuous integration, or pull request validation.
development
Generates test plans, writes unit/integration/E2E test files, identifies coverage gaps, flags common testing anti-patterns. Use when writing tests, creating test suites, planning test strategies, mocking dependencies, measuring code coverage, or test planning.
development
Provides model routing rules, validates delegation prerequisites, supplies cost tracking templates, defines dead-letter queue formats for Team Lead orchestration. Load when assigning tasks to agents, choosing model tiers, starting delegation session, running multi-agent workflow, delegating work, choosing which model to use, or assigning tasks.
testing
Saves, restores session state including task progress, file changes, delegation history. Use when saving progress, resuming interrupted work, picking up where you left off, or checkpointing current work.