Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Add Linear Channel Integration

Wires a NanoClaw agent into Linear issue comment threads so it answers every comment automatically.

AutomationAdvanced★ 30,471⑂ 12,865AI score 7/10Last updated: Aug 9, 2026

What it does

This skill installs the Linear channel adapter into a NanoClaw project via the Chat SDK bridge, turning each issue's comment thread into its own agent conversation.

  • Copies src/channels/linear.ts and its registration test from the channels branch
  • Appends one self-registration import to src/channels/index.ts
  • Installs @chat-adapter/linear@4.29.0 pinned exactly (ranges and latest are rejected by policy)
  • Builds and runs a single integration test to prove registration
  • Collects OAuth app credentials (or a Personal API key), webhook signing secret, and team key into .env
  • Wires the team to an agent with ncl messaging-groups create and ncl wirings create

Every step is expressed as an idempotent nc: directive fence, so the skill is safe to re-run and can be applied either by an agent reading the prose or by a deterministic parser. Because Linear OAuth apps can't be @-mentioned, engage mode is pattern . (respond to all comments) with per-thread session isolation.

Who it's for

  • Teams self-hosting NanoClaw who use Linear as their issue tracker
  • Devs and PMs who want AI replies right inside issue comment threads
  • Platform engineers who prefer documented, replayable channel-adapter setup

Examples

  1. Bug triage: paste a stack trace as a comment on an ENG issue; the agent replies in the same thread with a likely cause and relevant files.
  2. Spec discussion: each issue gets an isolated session, so drafting docs on one issue never bleeds context from another.
  3. Public workspace safety: pick the strict unknown-sender policy so only registered members can talk to the agent.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the .claude/skills/add-linear folder from the GitHub repo nanocoai/nanoclaw into my ~/.claude/skills/add-linear/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/nanocoai/nanoclaw.git && cp -r nanoclaw/.claude/skills/add-linear ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and go to the folder where your NanoClaw project lives.
  2. Download the skill: git clone https://github.com/nanocoai/nanoclaw.git
  3. Copy it into Claude Code's skills folder: cp -r nanoclaw/.claude/skills/add-linear ~/.claude/skills/
  4. In Linear, open Settings > API > OAuth Applications, create an app, enable Client credentials after creation, and copy the Client ID and Secret (or use a Personal API Key for a simpler setup).
  5. In Settings > API > Webhooks, create a webhook pointing to https://your-domain/webhook/linear, pick the team, check the Comment event, and copy the signing secret.
  6. Run Claude Code from your NanoClaw project root and ask it to "add the Linear channel"; the skill walks the Apply steps in order.
  7. Answer the prompts: Client ID/Secret, webhook secret, team key (e.g. ENG), and bot display name.
  8. Confirm both pnpm run build and pnpm exec vitest run src/channels/linear-registration.test.ts pass cleanly.
  9. Restart the service with the provided launchctl (macOS) or systemctl --user restart (Linux) command. Note that brand-new Linear webhooks can lag 1–5 minutes.
View source on GitHub ↗License: MIT