agentleFS
nonlinear-xyznonlinear-xyz/factory-kit/skills/factory-setup-linear/SKILL.md

factory-setup-linear

Skill9 starsChanged 4 months agoMITView on GitHub

Configure portable Linear workflow settings in `.factory-kit/linear.json`, migrating legacy `.claude/linear.json` settings when present.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Discover Linear context: Use the connected Linear integration's available capabilities:

    line 12
  2. Very specific:

    Ask which team to use through the host's user-interaction capability, or directly in chat when no structured prompt exists.

    line 14
  3. Very specific:

    If a project is chosen, capture id and name.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

You're configuring this project to use the Factory Kit Linear workflows. The other workflows read .factory-kit/linear.json from the project root; this workflow creates or migrates it.

What to do

  1. Check for configuration. Read .factory-kit/linear.json. If it exists, show the current contents and ask whether the user wants to overwrite, edit, or abort. If it is absent but legacy .claude/linear.json exists, use that as a migration fallback, show it, and offer to write the equivalent canonical file.
  2. Discover Linear context. Use the connected Linear integration's available capabilities:
    • List teams the user can access. Show key — name (id) lines.
    • Ask which team to use through the host's user-interaction capability, or directly in chat when no structured prompt exists. Capture both key (e.g., NON) and id (UUID).
    • List projects filtered to the chosen team. Ask whether standup should be scoped to one active project; "no" means team-wide.
    • If a project is chosen, capture id and name.
  3. Confirm state names. Defaults are "In Review" and "Done". List issue statuses for the chosen team through the Linear integration and verify both names exist. If not, ask the user for the actual names.
  4. Write .factory-kit/linear.json with this shape:

    {
      "teamKey": "NON",
      "teamId": "<uuid>",
      "projectId": "<uuid-or-omit>",
      "projectName": "<name-or-omit>",
      "states": {
        "inReview": "In Review",
        "done": "Done"
      },
      "branchPattern": "<owner>/<teamKey-lower>-<number>-<topic>"
    }
    • projectId / projectName are optional — omit the keys entirely if the user didn't pick a project.
    • branchPattern is documentation-only — /submit and /close parse the branch with a regex (-(\d+)-) and don't depend on this string. Include it so future readers know the convention.
  5. Show the file path and confirm — print "Wrote .factory-kit/linear.json. Factory Kit's standup, entry, submit, and close workflows are ready." Don't commit it; the user decides whether to check it in.

Style

Direct, minimal back-and-forth. If the user has only one team, skip the question — just use it. If they don't pick a project, that's fine — many repos don't have one.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.