MCPInstall

linear

Manage Linear tickets, projects, milestones, and documents. Use for coordinating work across skills (orca-security, multi-repo) or tracking remediation progress.

Installs
41
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/nodnarbnitram/claude-code-extensions --skill linear
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads linear automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Linear Project & Ticket Management

This skill manages Linear through the GraphQL endpoint only. Do not use linearis or any other CLI wrapper. The project scripts in .claude/skills/linear/scripts/ share a single GraphQL client and hit https://api.linear.app/graphql directly.

Prerequisites

Required: API Token

export LINEAR_API_TOKEN='lin_api_xxxxx'

Get the token from Linear → Settings → Security & Access → Personal API keys.

Verify Setup

uv run .claude/skills/linear/scripts/read-ticket.py ICE-2041

If this returns ticket JSON, auth and GraphQL access are working.

IMPORTANT: Use Scripts First

Prefer the scripts in .claude/skills/linear/scripts/ over ad hoc curl calls. They resolve names to IDs, normalize errors, and keep output JSON-shaped for agent workflows. If you need raw queries for debugging or unsupported operations, use references/graphql-reference.md.

When to Use This Skill

  • Create or update tickets for feature work, bugs, or remediation
  • Create projects and milestones to organize work
  • Add comments with progress or review notes
  • Create, list, or read project documents
  • Move issues into projects or milestones

Scripts Overview

ScriptPurpose
list-issues.pyList issues with optional team, status, and project filters
search-issues.pyFull-text search issues
create-ticket.pyCreate a ticket
read-ticket.pyRead ticket details by identifier or UUID
update-ticket.pyUpdate ticket fields
add-comment.pyAdd a comment to a ticket
create-project.pyCreate a project
add-issues-to-project.pyAdd tickets to a project
create-milestone.pyCreate a project milestone
add-issues-to-milestone.pyAdd tickets to a milestone
create-document.pyCreate a project document
list-documents.pyList documents, optionally by project
read-document.pyRead a document by UUID

Ticket Operations

List Issues

uv run .claude/skills/linear/scripts/list-issues.py --team ICE-T
uv run .claude/skills/linear/scripts/list-issues.py --team ICE-T --limit 100
uv run .claude/skills/linear/scripts/list-issues.py --team ICE-T --status "Todo,In Progress"
uv run .claude/skills/linear/scripts/list-issues.py --team ICE-T --project "Orca Security Remediation"

Options:

  • --team filter by team key or name
  • --limit, -l max issues to fetch, default 50
  • --status, -s comma-separated workflow states
  • --project project name or UUID

Search Issues

uv run .claude/skills/linear/scripts/search-issues.py "Orca Security"
uv run .claude/skills/linear/scripts/search-issues.py "CVE" --team ICE-T
uv run .claude/skills/linear/scripts/search-issues.py "Privileged Role" --status "Todo,Triage"
uv run .claude/skills/linear/scripts/search-issues.py "Docker" --team ICE-T --limit 20

Options:

  • query required search text
  • --team filter by team key or name
  • --status, -s comma-separated workflow states
  • --project project name or UUID
  • --assignee, -a assignee user ID
  • --limit, -l max results, default 25

Create Ticket

uv run .claude/skills/linear/scripts/create-ticket.py "Fix CVE-2024-1234" \
  --team ICE-T \
  --description "Critical vulnerability in production" \
  --priority 1 \
  --labels "security" \
  --json

Options:

  • title required ticket title
  • --team required team key or name
  • --description, -d description
  • --priority, -p 1=urgent, 2=high, 3=normal, 4=low
  • --labels comma-separated label names or UUIDs
  • --json print structured JSON instead of just the identifier

Read Ticket

uv run .claude/skills/linear/scripts/read-ticket.py ICE-2021
uv run .claude/skills/linear/scripts/read-ticket.py 9e05263f-ed01-4b85-9c74-569fd1a0ce13

Update Ticket

uv run .claude/skills/linear/scripts/update-ticket.py ICE-2021 --status "In Progress"
uv run .claude/skills/linear/scripts/update-ticket.py ICE-2021 --status "Done" --priority 2
uv run .claude/skills/linear/scripts/update-ticket.py ICE-2021 --labels "security,urgent"

Options, at least one required:

  • --status new status name or UUID
  • --priority 1=urgent, 2=high, 3=normal, 4=low
  • --assignee assignee user ID
  • --labels comma-separated label names or UUIDs; labels are added to the existing set
  • --project project name or UUID
  • --project-milestone milestone name or UUID
  • --title new title
  • --description new description

Add Comment

uv run .claude/skills/linear/scripts/add-comment.py ICE-2021 "Fixed in PR #123"

Project Operations

Create Project

uv run .claude/skills/linear/scripts/create-project.py "Security Remediation Q1" \
  --team ICE-T \
  --description "Eliminate all High severity alerts" \
  --priority 1 \
  --json

Options:

  • name required project name
  • --team required team key or name
  • --description short summary, max 255 chars
  • --content full markdown content for the project page
  • --priority 0=none, 1=urgent, 2=high, 3=normal, 4=low
  • --target-date YYYY-MM-DD
  • --json print full project JSON

Add Issues to Project

uv run .claude/skills/linear/scripts/add-issues-to-project.py PROJECT_UUID ICE-2027
uv run .claude/skills/linear/scripts/add-issues-to-project.py PROJECT_UUID ICE-2027 ICE-2028 ICE-2029
uv run .claude/skills/linear/scripts/add-issues-to-project.py PROJECT_UUID --issues ICE-2027,ICE-2028

Milestone Operations

Create Milestone

uv run .claude/skills/linear/scripts/create-milestone.py "P1: Critical Fixes" \
  --project PROJECT_UUID \
  --description "RCE and exposed secrets" \
  --target-date 2026-02-09 \
  --json

Options:

  • name required milestone name
  • --project required project UUID
  • --description milestone description
  • --target-date due date in YYYY-MM-DD
  • --json print full milestone JSON

Add Issues to Milestone

uv run .claude/skills/linear/scripts/add-issues-to-milestone.py MILESTONE_UUID ICE-2027 ICE-2028

Document Operations

Create Document

uv run .claude/skills/linear/scripts/create-document.py \
  --title "Security Findings Report" \
  --project PROJECT_UUID \
  --content-file ./report.md \
  --json

Options:

  • --title required document title
  • --project required project name or UUID
  • --content markdown content
  • --content-file read content from file
  • --json print structured JSON

List Documents

uv run .claude/skills/linear/scripts/list-documents.py --project PROJECT_UUID
uv run .claude/skills/linear/scripts/list-documents.py --project "Security Remediation" --limit 100

Read Document

uv run .claude/skills/linear/scripts/read-document.py DOCUMENT_UUID

Common Workflow

# 1. Create project
PROJECT_ID=$(uv run .claude/skills/linear/scripts/create-project.py \
  "Security Remediation" \
  --team ICE-T \
  --description "Eliminate all security vulnerabilities")

# 2. Create milestone
MILESTONE_ID=$(uv run .claude/skills/linear/scripts/create-milestone.py \
  "P1: Critical" \
  --project "$PROJECT_ID" \
  --target-date 2026-02-09)

# 3. Create ticket
TICKET_ID=$(uv run .claude/skills/linear/scripts/create-ticket.py \
  "Patch CVE-2024-1234" \
  --team ICE-T \
  --priority 1)

# 4. Link ticket into the plan
uv run .claude/skills/linear/scripts/add-issues-to-project.py "$PROJECT_ID" "$TICKET_ID"
uv run .claude/skills/linear/scripts/add-issues-to-milestone.py "$MILESTONE_ID" "$TICKET_ID"

# 5. Attach supporting documentation
uv run .claude/skills/linear/scripts/create-document.py \
  --title "Findings Report" \
  --project "$PROJECT_ID" \
  --content-file ./report.md

Direct GraphQL Usage

If a needed operation does not have a wrapper yet, call the GraphQL endpoint directly rather than introducing a CLI dependency.

curl -X POST https://api.linear.app/graphql \
  -H "Content-Type: application/json" \
  -H "Authorization: $LINEAR_API_TOKEN" \
  -d '{"query":"{ viewer { id name } }"}'

Do not use a Bearer prefix. Linear expects the raw token.

For reusable queries and resolver examples, see references/graphql-reference.md.


Known Limitations

  • Due dates are not handled by the current project wrappers; use the UI if you need fields not exposed here
  • Labels must already exist in the workspace
  • Project description is capped at 255 characters; use content for long-form project docs

Error Handling

All scripts exit with code 1 on errors.

Common failures:

  • Error: LINEAR_API_TOKEN not set and ~/.linear_api_token not found
  • Error: Ticket ICE-9999 not found
  • Error: Team 'INVALID' not found
  • Error: Milestone 'Release 1' matched multiple projects (...)

Version

  • Skill version: 3.0
  • Transport: Linear GraphQL endpoint only

FAQ

What does the linear skill do?

Manage Linear tickets, projects, milestones, and documents. Use for coordinating work across skills (orca-security, multi-repo) or tracking remediation progress.

How do I install linear?

Run npx skills add https://github.com/nodnarbnitram/claude-code-extensions --skill linear in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/linear/ (personal) or .claude/skills/linear/ (project).

Which AI agents can use linear?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is linear safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains linear?

It is published by nodnarbnitram in nodnarbnitram/claude-code-extensions. It has 41 recorded installs.

More from nodnarbnitram/claude-code-extensions

View all →

tauri-v2

nodnarbnitram/claude-code-extensions

Tauri v2+ cross-platform app development with Rust backend. Use when configuring tauri.conf.json, implementing Rust commands ([tauri::command]), setting up IPC patterns (invoke, emit, channels), configuring permissions/capabilities, troubleshooting build issues, or deploying desktop/mobile apps. Triggers on Tauri, src-tauri, invoke, emit, capabilities.json.

Backend & APIs8.1K installs

code-reviewer

nodnarbnitram/claude-code-extensions

Open the skill to read its SKILL.md instructions.

293 installs

ha-voice

nodnarbnitram/claude-code-extensions

Open the skill to read its SKILL.md instructions.

Media & Creative218 installs

esphome-config-helper

nodnarbnitram/claude-code-extensions

Open the skill to read its SKILL.md instructions.

136 installs

frigate-configurator

nodnarbnitram/claude-code-extensions

Open the skill to read its SKILL.md instructions.

117 installs

ha-energy

nodnarbnitram/claude-code-extensions

Open the skill to read its SKILL.md instructions.

104 installs

Popular productivity & automation skills

View category →

agent-browser

vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

OfficialProductivity & Automation1.3M installs

lark-doc

open.feishu.cn

飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。

lark-base

open.feishu.cn

飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。

lark-drive

open.feishu.cn

飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。

lark-shared

open.feishu.cn

Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.

lark-im

open.feishu.cn

飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。