agentleFS
Sign inStart free
nonlinear-xyznonlinear-xyz/factory-kit/skills/factory-standup/SKILL.md

factory-standup

Skill9 starsChanged 4 months agoMITView on GitHub

Dev standup — open Linear tickets grouped by in-flight, top priority, and backlog

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read project configuration: Prefer .factory-kit/linear.json.

    line 10

≈ “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 giving the user a dev-standup view of their open Linear work in this project. The goal is to answer "what's in flight, what's the top priority, what's waiting?" without making them open Linear in a browser.

What to do

  1. Read project configuration. Prefer .factory-kit/linear.json. If it is absent, read legacy .claude/linear.json as a migration fallback and tell the user to run the setup-linear workflow to migrate. If neither exists, stop and direct the user to setup-linear.
  2. Resolve scope. Pull teamId from the config. If projectId is present, scope to that project; otherwise stay team-wide.
  3. List open issues through the connected Linear integration:
    • team: <teamId>
    • project: <projectId> (if present in config)
    • state filtered to open states only (exclude Done, Completed, Cancelled, Duplicate)
    • Sort by priority (Urgent → High → Normal → Low), then by updated date desc

  4. Return a tight status (≤ 300 words):

    Project: name + active milestone if present, or just team name if no project scope

    In progress — issues in In Progress (or whatever the team's equivalent active state is). One line per issue: <TEAM-N> — title (assignee if not me).

    In review — issues in In Review. Same format. Surface stale ones (> 3 days).

    Top priority (next up) — Urgent and High-priority open issues not yet started. Order by priority then update date. Show 5–8.

    Backlog — count + a sample of 3–5 from Todo/Backlog states, prioritized.

    Blocked (only if any) — issues with open blockedBy. Show what's blocking each.

    One-line recommendation: the single best issue to pick up next, given priority and blockers. Cite the portable entry workflow with <TEAM-N>; in Claude, preserve the compatibility form /entry <TEAM-N>.

Style

Follow factory-voice.md. Tight, glanceable lines — the user is scanning for a decision, not reading a report. Don't reprint full descriptions; titles only. Always cite issue IDs in canonical form (e.g., NON-45). The recommendation at the end is a call, not a suggestion — name the reason in one clause ("highest priority, no blockers" / "in review > 3 days, unblock the reviewer first").

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.

Check your setup, free