Agent skill

Ade Linear

by arul28 in arul28/ADE

A skill your agent uses whenever your task is a Linear issue (or an ADE chat/lane launched with a Linear issue attached) and you need to read or update that issue — change its workflow state…

AGPL-3.0Auto-check passed

Install Ade Linear

skills CLI
$ npx skills add arul28/ADE --skill ade-linear -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install arul28/ADE ade-linear --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/arul28/ADE.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/desktop/resources/agent-skills/ade-linear .claude/skills/ade-linear && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ade-linear
GitHub stars
114
Token cost
~2k tokens
SKILL.md length
811 words
Files
1
Skills in repo
28
Repo updated
First seen
Licence
AGPL-3.0

At a glance

A skill your agent uses whenever your task is a Linear issue (or an ADE chat/lane launched with a Linear issue attached) and you need to read or update that issue — change its workflow state…

  • Your task is a Linear issue (or an ADE chat/lane launched with a Linear issue attached) and you need to read
  • SKILL.md covers What you have, Knowing which issue is yours, Reading and Updating (you have write access), plus 5 more sections
  • Calls node; reaches linear.app
  • Update that issue — change its workflow state

What it does

Ade Linear is an agent skill from arul28/ADE. Use this skill whenever your task is a Linear issue (or an ADE chat/lane launched with a Linear issue attached) and you need to read or update that issue — change its workflow state, comment progress, assign it, add a label, or read its comments. ADE routes all of this through its own Linear connection via the ade linear CLI, so you have effective Linear write access with no API key.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with Linear. The licence is AGPL-3.0.

When your agent uses it

  • Your task is a Linear issue (or an ADE chat/lane launched with a Linear issue attached) and you need to read
  • Update that issue — change its workflow state
  • Comment progress
  • Read its comments

Example prompts

  • “/ade-linear”

What it can do on your machine

Read from SKILL.md and the folder at commit fbbd974. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • linear.app

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ade Linear loads about 2k tokens when it runs. Until then it costs about 100 tokens; SKILL.md has 811 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~100
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from arul28/ADE at commit fbbd974, republished under its AGPL-3.0 licence (© arul28). 811 words, ~2,043 tokens.

Download SKILL.mdSave it as .claude/skills/ade-linear/SKILL.md (or your agent's skills folder).
name
ade-linear
description
Use this skill whenever your task is a Linear issue (or an ADE chat/lane launched with a Linear issue attached) and you need to read or update that issue — change its workflow state, comment progress, assign it, add a label, or read its comments. ADE routes all of this through its own Linear connection via the `ade linear` CLI, so you have effective Linear write access with no API key.

ADE Linear

What you have

If ADE launched you on a Linear issue, that issue lives in ADE's Linear connection and you can both read and write it through the ade linear CLI. You do not hold a Linear token and you do not need one: every ade linear command routes over the ADE daemon to the desktop runtime, which owns the Linear credentials. The daemon does the authenticated Linear API call on your behalf.

You do not need to know how you were launched, what mode you are in, or how the issue got attached. You have a task, an attached issue, and these commands.

Prefer ade linear over any Linear MCP server or direct Linear API call — the ade linear bridge is the connection that is actually configured for this workspace, and it keeps the issue's ADE links and sync state consistent.

Knowing which issue is yours

When ADE attaches an issue to your session it injects two environment variables:

  • ADE_LINEAR_ISSUE_IDS — comma-separated identifiers of every attached issue, e.g. ENG-431,ENG-440. The first one is your primary issue.
  • ADE_LINEAR_CONTEXT_FILE — absolute path to a JSON file describing the attached issues. Read it for title, state, URL, and team before you act.
  • ADE_CHAT_SESSION_ID — your session id (used by the --this-session flag).

The context file looks like:

json
{
  "sessionId": "...",
  "updatedAt": "2026-05-29T...",
  "issues": [
    {
      "id": "uuid",
      "identifier": "ENG-431",
      "title": "Fix Linear deeplink race",
      "url": "https://linear.app/...",
      "stateName": "Todo",
      "role": "primary",
      "teamKey": "ENG"
    }
  ]
}

If those vars are unset, no issue is attached — fall back to passing an explicit identifier (e.g. ENG-431) to the read/write commands below, or check ade linear issues for what your session has.

Reading

The attached-issue commands default to your session's first attached issue when you omit the id (precedence: --issue-id <id> flag → leading positional → $ADE_LINEAR_ISSUE_IDS). So inside a tracked session you can drop the id.

bash
ade linear issues --text                         # list issues attached to this session
ade linear issue --text                          # read your attached issue (full detail)
ade linear issue ENG-431 --text                  # read a specific issue
ade linear issue-comments --issue-id ENG-431 --text   # read an issue's comment thread
ade linear graphql --query 'query { viewer { id name } }'  # advanced Linear API via ADE credentials
ade linear graphql --query-file query.graphql --variables-file vars.json

Use --text for human-readable output; omit it for JSON when you want to parse.

Updating (you have write access)

These move the issue forward through ADE's Linear connection — no API key. Each takes an optional leading issue id; omit it to target your attached issue.

bash
ade linear set-state ENG-431 <state-id>          # move workflow state (e.g. In Progress, Done)
ade linear comment "Pushed a fix, CI is running" # comment on your attached issue
ade linear comment ENG-431 "Done — see PR #123"  # comment on a specific issue
ade linear assign me                             # assign to the connected user
ade linear assign ENG-431 <user-id>              # assign to a specific user
ade linear assign none                           # clear the assignee (also: null / unassigned)
ade linear label ENG-431 "needs-review"          # add a label by name

Notes:

  • set-state takes a workflow state id, not a free-text name. To discover the valid states/ids (and users) for the issue picker, run ade linear picker-data --text (you may need to prefix --role cto: ade --role cto linear picker-data --text). The state id can also be passed via --state-id <id>.
  • comment, set-state, assign, and label all accept the value via a flag too (--message/-m, --state-id, --assignee, --label) if a positional is ambiguous.
  • Use ade linear graphql for Linear operations not covered by the typed commands. It still routes through ADE's saved Linear OAuth/API key; do not ask for or print token material.
Show full SKILL.md (384 more words)Show less

Filing follow-up issues and linking issues

File a follow-up when you find a real, separate problem that is outside the scope of your issue. Do not file one for work you can finish inside your issue, for style nits, or for guesses you did not check.

bash
ade linear create --title "Share page leaks OG metadata" --description "…evidence, file:line…"
ade linear create --title "…" --blocked-by        # the new issue waits on your issue
ade linear create --title "…" --blocks            # your issue waits on the new one
ade linear create --title "…" --sub-issue         # a child of your issue
ade linear create --title "…" --standalone --team VER   # not linked to your issue
ade linear relate VER-12 --blocks VER-13          # link two existing issues
ade linear relate --related VER-40                 # link your issue to VER-40
ade linear inbox                                   # the connected user's unread Linear inbox

Rules:

  • create links the new issue to your attached issue as related by default, in the same team and project. It refuses when an open issue in that team has a near-identical title and prints that issue; link to it with relate instead. Pass --allow-duplicate only when you checked it is different.
  • File at most a few follow-ups per task. Put the evidence (what you saw, the file and line, how to reproduce) in --description.
  • After filing, add one comment on your own issue that names the new issue.

ADE posts its own Linear attachments/cards for lane, chat, and PR flows. The ade-deeplinks skill holds the matrix of which flow ADE covers automatically and which one leaves the link to you, plus the ade link ... commands and the HTTPS-vs-ade:// guidance.

The short version for this skill's commands: the direct issue actions (comment, set-state, assign, label, graphql) are the ones ADE does not link for you, so include the relevant ADE link yourself in any user-facing Linear comment — especially when the action creates new Linear state or hands work to a human.

bash
ade linear graphql --query-file create-issue.graphql --variables-file vars.json
ade linear comment NEW-123 "Created via ADE. Open in ADE: $(ade link linear-issue NEW-123 --no-clipboard)"

Attaching / detaching this session

bash
ade linear attach --this-session --issue-id ENG-431   # attach an issue to your session
ade linear detach --this-session --issue-id ENG-431   # detach one issue
ade linear detach --this-session                      # detach every issue from your session

Two commands outside the ade linear surface also attach an issue: ade chat attach-linear-issue <session> --issue-id <id> and ade lanes link-linear-issue <lane> --linear-issue-json '{...}'.

What lands where

An ade linear comment is the issue's status channel — it is what reviewers and the issue's watchers see, and it is visible to people who never open ADE. The workflow state you set with set-state is what shows in the team's board. Neither is inferred from your ADE activity; if you do not write them, the issue does not move.

set-state takes a workflow state id, and the valid states are per-team, so resolve the id with ade linear picker-data --text rather than assuming a Done/In Review convention.

Discovery

Run ade help linear for the full flag set, or ade linear --help. If ade is not on PATH, see the ade-cli-control-plane skill for the fallback resolution order ($ADE_CLI_PATH, $ADE_CLI_BIN_DIR/ade, or node apps/ade-cli/dist/cli.cjs).

© arul28, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in apps/desktop/resources/agent-skills/ade-linear of arul28/ADE.

Open the folder on GitHubat commit fbbd974

Compare with similar skills

Ade Linear next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ade Linear compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ade Linear this skillarul28/ADE114—~2kAutomated safety check: PassAGPL-3.0
Orca Linear Ticket Workflowstablyai/orca87k1 repos~522Automated safety check: PassMIT
Review Triage Phaseprisma/orm48k—~995Automated safety check: PassApache-2.0
Commitdinerojs/dinero.js6.8k—~667Automated safety check: PassMIT
Draft Pull Request Creatorwordpress-mobile/WordPress-Android3.2k—~881Automated safety check: NotesGPL-2.0
Linear Tickets via Orcastablyai/orca87k—~558Automated safety check: PassMIT

Similar skills

  • Linear ticket work through Orca's CLI. Use when working from a linked Linear issue, finishing work with a PR/MR link and a completion comment, moving a ticket…

    87k GitHub starsUsed in 1 repo~522 tokens
    Productivity & AutomationAuto-check passed
  • Official

    Runs the triage step of the review-framework loop: reads fetched PR review state, builds `review-actions.json`, validates it and renders `review-actions.md`.

    48k GitHub stars~995 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Commit

    dinerojs/dinero.js

    Create a git commit with optional automatic Linear issue linking.

    6.8k GitHub stars~667 tokensUpdated 3 days ago
    DevelopmentAuto-check passed
  • Draft Pull Request Creator

    wordpress-mobile/WordPress-Android

    Commits and pushes current changes, writes a pull request title and body from the branch history and template, and opens a draft PR on GitHub after you approve it.

    3.2k GitHub stars~881 tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Linear ticket work through Orca's CLI. Use when working from a linked Linear issue, finishing work with a PR/MR link and a completion comment, moving a ticket…

    87k GitHub stars~558 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Add Icon Mapping

    lobehub/lobe-icons

    Add or modify icon keyword mappings for providers, models, or agents in lobe-icons.

    2.6k GitHub stars~1.5k tokensUpdated yesterday
    MobileAuto-check: warnings

More from arul28/ADE

All 28 skills in this repo
  • Ade App Control

    arul28/ADE

    A skill your agent uses when you need to run or drive a local Electron/desktop app and capture what it does — launch it or attach to a running renderer, read its logs or answer its terminal prompts…

    114 GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • Iteratively optimize an ADE tab's CPU/memory/IPC/render performance.

    114 GitHub stars~4.2k tokensUpdated today
    Auto-check passed
  • Ade Browser

    arul28/ADE

    A skill your agent uses for any browser behavior at all — opening a URL, checking a localhost page, clicking or filling a form, logging in, screenshotting, inspecting the DOM, or verifying a page…

    114 GitHub stars~3.3k tokensUpdated today
    Auto-check passed
  • Ade Deeplinks

    arul28/ADE

    A skill your agent uses when an agent needs to mint, share, or open ADE deeplinks (lane, work session, file, commit, artifact, branch, PR, Linear issue) so users — or the agent itself — can jump…

    114 GitHub stars~3.2k tokensUpdated today
    Auto-check passed
  • Ade Harnesses

    arul28/ADE

    A skill your agent uses when you need to run a chat, a CLI session, or a subagent on a specific setup — any model you pay for inside any harness (e.g.

    114 GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Ade Lanes Git

    arul28/ADE

    A skill your agent uses when creating, inspecting, syncing, committing, pushing, archiving, or rebasing ADE lanes and lane worktrees through ade lanes and ade git.

    114 GitHub stars~594 tokensUpdated today
    Auto-check passed

Works with

Questions about Ade Linear

What does Ade Linear do?

A skill your agent uses whenever your task is a Linear issue (or an ADE chat/lane launched with a Linear issue attached) and you need to read or update that issue — change its workflow state…. Ade Linear is an agent skill from arul28/ADE. Use this skill whenever your task is a Linear issue (or an ADE chat/lane launched with a Linear issue attached) and you need to read or update that issue — change its workflow state, comment progress, assign it, add a label, or read its comments.

When should I use Ade Linear?

Ade Linear fits situations like: your task is a Linear issue (or an ADE chat/lane launched with a Linear issue attached) and you need to read; update that issue — change its workflow state; comment progress; read its comments.

How do I install Ade Linear in Claude Code?

Run `npx skills add arul28/ADE --skill ade-linear -a claude-code`. Or copy the skill folder (apps/desktop/resources/agent-skills/ade-linear in arul28/ADE) into .claude/skills/ade-linear in your project. Claude Code loads it when a task matches its description.

How do I install Ade Linear in Codex?

Run `npx skills add arul28/ADE --skill ade-linear -a codex`. Or copy the skill folder (apps/desktop/resources/agent-skills/ade-linear in arul28/ADE) into .agents/skills/ade-linear in your project. Codex loads it when a task matches its description.

Can I use Ade Linear in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add arul28/ADE --skill ade-linear -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ade-linear, .gemini/skills/ade-linear, .github/skills/ade-linear and .opencode/skills/ade-linear in your project.

What does Ade Linear need to run?

Going by SKILL.md and its folder, Ade Linear needs the command-line tools its instructions call (node).

Does Ade Linear access the network?

SKILL.md names 1 domain. In commands or code: linear.app; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Ade Linear safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ade Linear use?

Ade Linear is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ade Linear use?

About 2k tokens (SKILL.md is roughly 8.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ade Linear?

Skills that share tags, products or a category with Ade Linear: Orca Linear Ticket Workflow (stablyai/orca, 87k stars), Review Triage Phase (prisma/orm, 48k stars), Commit (dinerojs/dinero.js, 6.8k stars) and Draft Pull Request Creator (wordpress-mobile/WordPress-Android, 3.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ade Linear?

arul28 (a GitHub user) maintains it in arul28/ADE, which has 114 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on October 8, 2026.

Source: arul28/ADE on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.