Skip to main content
ClaudeWave
Skill58 estrellas del repoactualizado 2mo ago

linear-task-management

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

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/monkilabs/opencastle /tmp/linear-task-management && cp -r /tmp/linear-task-management/src/orchestrator/plugins/linear ~/.claude/skills/linear-task-management
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .opencastle/ directory instead. -->

# Task Management with Linear

For project-specific team ID, workflow state UUIDs, and label UUIDs, see [tracker-config.md](../../.opencastle/project/tracker-config.md). For status transitions, follow the **Status Update Procedure** section below.

## MCP Tool Examples

```json
// 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" }
```

## Discovered Issues

- Search Linear for existing tickets; if found, link and add evidence.
- If not found, create: Title `[Bug] <symptom>`, Labels `bug` + domain, Priority P1–P4 with rationale, Acceptance steps.

## Issue Naming

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`
```

## Priority

| 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 |

## Status Workflow

```
Backlog -> Todo -> In Progress -> In Review -> Done -> Cancelled
```

### Transition Rules

- Agent (via MCP): `Todo → In Progress` on start; `In Progress → Done` on verified completion; `Any → Cancelled` to drop.
- GitHub integration: auto-updates status on PR events (push → In Progress, review → In Review, merge → Done). Configure in Linear *Settings → Team → Pull request automation*.
- Link via issue ID in branch/PR title (e.g., `TAS-123`).

## Issue Descriptions

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.

## Session Workflow

1. Check board for existing in-progress work.
2. Decompose feature into issues; create all on Linear — verify each returns a valid issue ID.
3. Delegate: move to **In Progress** before starting; **Done** after verified.
4. If blocked, update the issue description (Linear MCP has no comment API).
5. On resume: filter by In Progress/Todo, read descriptions, continue.
6. On completion: verify all issues Done/Cancelled, run build/lint/test.

If creation fails: check team ID and state UUIDs in [tracker-config.md](../../.opencastle/project/tracker-config.md); retry once. If board state is inconsistent on resume: re-read all issue statuses before proceeding.

## Status Update Procedure

> ⚠️ `update_issue` requires a workflow state **UUID** — passing a name like `"In Progress"` always fails with `stateId must be a UUID`.

1. **Read UUIDs from [tracker-config.md](../../.opencastle/project/tracker-config.md)** before any status transition. Names returned by `list_issues`/`get_issue` are display-only, not valid `stateId` values.
2. **If `tracker-config.md` has no state UUIDs**, skip status updates and log a warning.

```json
// ✅ UUID from tracker-config.md
{ "issueId": "TAS-42", "stateId": "a1b2c3d4-e5f6-7890-abcd-ef1234567890" }
// ❌ FAILS — name, not UUID
{ "issueId": "TAS-42", "status": "In Progress" }
```

## One-Time Setup: Discover Workflow State UUIDs

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.
astro-frameworkSkill

Creates pages/layouts, defines content collections, configures hydration directives, and wires integrations. Use when adding or modifying Astro pages, layouts, components, or content collections. Trigger terms: Astro, content collection, client:load, client:visible, astro:content

browser-testingSkill

Drive real browsers via Chrome DevTools MCP: navigate pages, capture snapshots, run responsive checks, and collect console/perf traces. Use when the user mentions: 'validate UI change in Chrome', 'capture a screenshot', 'run responsive checks', or 'collect console logs'. Trigger terms: browser testing, DevTools, console logs, screenshot, responsive testing

cloudflare-platformSkill

Creates and deploys Cloudflare Workers, configures wrangler.toml bindings, sets up KV/D1/R2 storage and Durable Objects, manages Pages deployments, and implements edge function patterns. Use when building or deploying Cloudflare Workers, setting up Pages, working with KV/D1/R2 storage, configuring wrangler.toml, or deploying edge applications.

contentful-cmsSkill

Creates Contentful content types, queries entries via GraphQL/REST, runs CLI migrations, and manages assets and locales. Use when building or modifying Contentful content models, writing queries, or migrating content.

convex-databaseSkill

Convex reactive database patterns, schema design, real-time queries, mutations, actions, authentication, migrations, performance optimization, and component creation. Use when designing Convex schemas, writing queries/mutations, managing the Convex backend, setting up auth, migrating data, optimizing performance, or building Convex components.

coolify-deploymentSkill

Deploys applications, databases, and services on self-hosted Coolify instances, manages environments and env vars, runs infrastructure diagnostics, and performs batch operations. Use when deploying apps to Coolify, managing Coolify servers, debugging deployment issues, setting up databases, or managing Coolify infrastructure.

cypress-testingSkill

Writes Cypress E2E/component tests, configures `cy.intercept()` and `cy.session()`, authors custom commands, and wires CI artifacts. Use when creating E2E specs, component tests, or CI test pipelines. Trigger terms: cypress, e2e, component test, cy.intercept, cy.session

drizzle-ormSkill

Drizzle ORM schema definition, type-safe queries, relational queries, CRUD operations, transactions, migrations with drizzle-kit, and database setup for PostgreSQL, MySQL, and SQLite. Use when defining database schemas, writing queries or joins, managing migrations, setting up a new Drizzle project, or working with drizzle-kit.