Linear logo

Linear

Organization
initializ
linear

Read Linear issues, transition state, and post comments. The entry point for ticket-driven agent workflows.

Overview

Publisherinitializ
Repositoryforge
Skill namelinear
Stars
242
Forks
14
Bundled files
7
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 7 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by initializ on GitHub. Read the source before you install it.

Installation

Install the Linear AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/initializ/forge/tree/main/forge-skills/local/embedded/linear
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/initializ/forge.git /tmp/forge
mkdir -p .claude/skills
cp -r /tmp/forge/forge-skills/local/embedded/linear .claude/skills/linear
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Linear in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Linear on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Linear is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Linear Skill

You can read, search, and update Linear issues, list workflow states, and post comments. Use this skill as the entry point for ticket-driven workflows — turn ENG-123 into a structured payload, transition state, comment on progress.

When to use this skill

  • The user references a Linear issue by identifier (ENG-123, OPS-7, etc.).
  • The user asks for "my tickets" / "open issues" / "what's assigned to me".
  • An automation needs to mark work started, post a PR link as a comment, or move a ticket through workflow states.

Issue identifier format

Linear identifiers look like <TEAM_KEY>-<NUMBER> — ENG-123, OPS-7. They are not GraphQL UUIDs. The Linear API accepts both forms on issue(id:), so always pass the human identifier the user gave you. Never invent or normalise identifiers — use them verbatim.

State transition pattern (hard rule)

You MUST call linear_get_workflow_states first and use the resolved id when calling linear_update_issue_state. State IDs are per-team UUIDs; state names like "Todo" or "In Progress" are not portable across teams and cannot be passed to linear_update_issue_state directly.

Workflow:

  1. linear_get_issue to find the issue's team.id.
  2. linear_get_workflow_states with that team_id to enumerate the team's states.
  3. Pick the state by matching its name (case-insensitive) or type (unstarted, started, completed, canceled, triage, backlog).
  4. linear_update_issue_state with the issue identifier and the resolved state_id.

Commenting etiquette

Post a comment when:

  • Work has been picked up (one comment, e.g. "Working on this.").
  • A pull request has been opened (one comment with the PR URL).
  • Work is blocked and the user should know.
  • Work is complete (one comment summarising what shipped).

Do not chatter. Post no more than one comment per agent action. Do not narrate intermediate tool calls, file edits, or reasoning into Linear comments — the channel-side conversation is the place for that. Comments are durable artifacts on the ticket; treat them like git commit messages, not Slack messages.

Safety rules

  • Never include secrets, tokens, or environment variable values in comment bodies.
  • Never transition an issue to a "Done" or "Completed" state without explicit user confirmation.
  • Never delete issues, comments, or projects through this skill — the tools don't support it. If the user asks, tell them this skill is read/comment/transition only.
  • When the user asks for "my tickets", default to state filter "Todo" or "In Progress" (state types unstarted, started) unless they specify otherwise.

Tool: linear_get_issue

Fetch a Linear issue by its human identifier.

Input:

ParameterTypeRequiredDescription
identifierstringyesIssue identifier like ENG-123

Output:

json
{
  "identifier": "ENG-123",
  "title": "...",
  "description": "...",
  "state": { "id": "...", "name": "In Progress", "type": "started" },
  "assignee": { "email": "...", "name": "..." },
  "team": { "id": "...", "key": "ENG", "name": "Engineering" },
  "labels": ["bug", "p1"],
  "priority": 2,
  "url": "https://linear.app/..."
}

Tool: linear_search_issues

Filter issues across one team — or across all teams the API key can see, if no team is supplied. All parameters are optional. Call this tool with {} when the user asks something broad like "list open issues" or "what's in the backlog" — do not ask for a team_id first; the result will include the team key in each issue's identifier (e.g. ENG-12 vs OPS-7) and the user can drill down from there.

Input:

ParameterTypeRequiredDescription
team_idstringnoLinear team UUID or team key like ENG. Auto-detects which form. Defaults to $LINEAR_DEFAULT_TEAM_ID when set.
statestringnoWorkflow state type (unstarted, started, completed, canceled, triage, backlog).
assignee_emailstringnoFilter by assignee email.
labelstringnoFilter by label name.
querystringnoFree-text search over title and description.
limitintegernoMax results (default 20, capped at 100).

Examples — call the tool directly, do not ask the user for an ID:

User saysTool input
"list open issues" / "what's in the backlog"{}
"show me INI tickets"{"team_id": "INI"} (team key works)
"open bugs in ENG"{"team_id": "ENG", "state": "unstarted", "label": "bug"}
"what's @alice working on?"{"assignee_email": "alice@example.com", "state": "started"}

Output:

json
{
  "count": 3,
  "issues": [
    { "identifier": "ENG-1", "title": "...", "state": "Todo", "assignee_email": "...", "url": "..." }
  ]
}

Tool: linear_list_my_issues

List issues assigned to the API key's owner (viewer).

Input:

ParameterTypeRequiredDescription
statestringnoComma-separated state types. Default: "started,unstarted" ("In Progress" / "Todo").
limitintegernoMax results (default 20, capped at 100).

Output: same shape as linear_search_issues.

Tool: linear_get_workflow_states

Enumerate a team's workflow states. Required before linear_update_issue_state.

Input:

ParameterTypeRequiredDescription
team_idstringyesLinear team UUID (from linear_get_issue's team.id).

Output:

json
{
  "team_id": "...",
  "states": [
    { "id": "...", "name": "Todo",        "type": "unstarted", "position": 0 },
    { "id": "...", "name": "In Progress", "type": "started",   "position": 1 },
    { "id": "...", "name": "Done",        "type": "completed", "position": 2 }
  ]
}

States are sorted by position.

Tool: linear_update_issue_state

Transition an issue to a different workflow state. The state_id must come from linear_get_workflow_states — do not invent or guess it.

Input:

ParameterTypeRequiredDescription
identifierstringyesIssue identifier like ENG-123.
state_idstringyesWorkflow state UUID from linear_get_workflow_states.

Output:

json
{
  "success": true,
  "identifier": "ENG-123",
  "state": { "id": "...", "name": "In Progress", "type": "started" }
}

Tool: linear_add_comment

Post a markdown comment to an issue.

Input:

ParameterTypeRequiredDescription
identifierstringyesIssue identifier like ENG-123.
bodystringyesMarkdown comment body. Capped at 10 000 characters; longer bodies are truncated client-side.

Output:

json
{
  "success": true,
  "comment": { "id": "...", "url": "https://linear.app/...", "created_at": "2026-05-20T..." }
}

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Linear AI skill do?

Read Linear issues, transition state, and post comments. The entry point for ticket-driven agent workflows.

Why use Linear on TypingMind?

Because you install it once and use it with any model. Linear is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Linear in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/initializ/forge/tree/main/forge-skills/local/embedded/linear. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Linear?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Linear?

As many as you like. As long as a model supports skills, you can use Linear with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Linear AI skill free?

Yes. It is published on GitHub by initializ under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇