← Back to library

Get the plant report ready before the morning meeting

Anthropic's Claude for Manufacturing plugin, released November 12, 2026, includes the one chain it says is safe to schedule. It reads overnight exports, stores a daily record, refreshes one private dashboard and shows missing data as gaps, never zeros, without asking questions or touching a system of record. We explain how to use it.

  • OutcomeSchedule the morning-plant-pulse skill from Anthropic's Claude for Manufacturing plugin to combine the overnight exports from planning, production and maintenance, compute output against plan, OEE and its three parts, downtime ranked by minutes and by count and the cost of losses, then refresh one operations dashboard per site with 14- and 30-day trends, all without changing any business system.
  • SetupAn afternoon+
  • LevelAdvanced
  • Creditanthropics
View original
Works with
ClaudeClaude CoworkClaude Code

Published Nov 14, 2026Updated Nov 14, 2026AI dry run on sample input: passed Nov 14, 2026Source verified Nov 14, 2026

When should you use it?

  • A supervisor spends the first hour of each shift building the daily report from the same exports
  • Your morning meeting argues about whose numbers are right
  • You want trends over weeks without keeping a spreadsheet by hand

Not for: Live, minute-by-minute line monitoring; this is an overnight batch; Applying schedule changes; reschedule ideas are drafts for the scheduler; Plants that cannot export planning, production and downtime data on a schedule

What do you need, and what do you get?

You need

  • Nightly exports of planning, production and maintenance data in a shared folder
  • Your ERP or maintenance system connector, where available
  • The plant setup from onboarding: sites, shift pattern, day boundary and cost rates
  • A scheduled task in the host app to trigger the run

You get

  • One operations dashboard per site, refreshed in place, with today's actions first
  • Output against plan, OEE with availability, performance and quality shown separately
  • Downtime ranked by minutes and by frequency, with losses priced where a rate is set
  • A numbered list of data problems and a stored record for each production day
  • A short summary reply, and a saved page with a clear note when the dashboard could not be updated

How does it work, step by step?

  1. Install and onboardAdd Claude for Manufacturing from the Claude plugin directory and fill in the plant setup, including shift times and any downtime cost rate.
  2. Point it at the exportsMake sure the nightly planning, production and maintenance files land in the same folder before the run time.
  3. Run it once by handSay 'run the morning pulse' and check the first dashboard against a report you built yourself for the same day.
  4. Schedule itCreate a scheduled task in your host app for the early morning. The plugin does not schedule itself.
  5. Read the gaps firstEach morning, check the freshness banner and data problems list before discussing the numbers.

The prompt

Our adapted version, written to work in Claude, Claude Cowork and Claude Code. Values in lime are placeholders.

Fill in the blanks (optional; the copied prompt uses your values)

Prompt3 variables
Build the morning production report for {site} for production day {date} from the exports in {folder}.
Show output against plan, OEE with availability, performance and quality separately, and downtime ranked by total minutes and by number of stops. Price losses only with our configured rate.
If any export is missing or partial, say so at the top and treat the affected figures as gaps, never zeros.
List every mismatch between plan and output part numbers as a proposed fix, not an applied one, and change nothing in our systems.
Update the existing dashboard for this site if there is one and tell me whether the update succeeded.

The original routine is published by anthropics on GitHub (anthropics/claude-plugins-official). Open it there to install or import it; the prompt above is our own adaptation.

What can go wrong?

  • Assuming the run happened because the dashboard exists. Check the updated time at the top of the page.
  • Ignoring the data problems table. Mismatched part numbers between plan and output can make a good day look bad.
  • Reading a gap as a zero. A missing export shows as a gap on purpose; chase the export instead.
  • Anthropic labels the plugin a reference implementation it does not actively maintain, so run it beside your current report for a week first.

Our take

Overnight reports are only valuable if people trust them, and trust usually dies the first morning a missing file shows up as a zero. This skill is built around that failure. A missing export becomes a visible gap at the top of the page, a rerun replaces the day's record instead of adding a second one, and the word updated only appears when the publish actually returned a link. We like that it ranks downtime both by total minutes and by how often each stop happens, because the long breakdown and the hundred short jams call for different fixes. The data problems table is just as useful: it shows where plan and output disagree on part numbers rather than silently dropping or joining those rows. Keep in mind that the plugin does not schedule itself, so you set that up in your host app, and Anthropic labels it a reference implementation. In our dry run on a fictional two-line plant with one maintenance export missing, the report flagged the gap first, kept downtime unpriced where no rate was set and listed two part-number mismatches as proposed fixes.

Where the time goes back: The skill's own estimate is that a supervisor spends sixty to ninety minutes assembling this report by hand. Having it waiting at shift start frees that time for the problems the report points to.

FAQ

Why is this the only part of the plugin meant to run on a schedule?
It only reads data and publishes a private page, so there is nothing for a person to approve. Steps that change records stay manual.
What happens if one export is missing?
The run still completes, names the missing file at the top and stores that day as incomplete, so the trend shows a gap rather than a bad day.
Who made it and what license does it use?
Anthropic published it in the anthropics/claude-plugins-official repository on GitHub under the Apache 2.0 license.

Source and credit

This playbook is based on work by anthropics. We summarize it and link to it and write our own adapted prompt.

Original
morning-plant-pulse skill (anthropics/claude-plugins-official, Claude for Manufacturing)
Creator
anthropics
Published on
GitHub (anthropics/claude-plugins-official)
Original date
Nov 12, 2026
License
Apache-2.0
Originally for
Claude
AI dry run
Nov 14, 2026: passed. Dry-run tested by our AI test agent on sample input. Gap reported not zeroed, both rankings correct, no invented rate, mismatches proposed not applied, no false "updated".
AI dry run on sample data; not run with live connected accounts. The playbooks.bot test agent filled the prompt with synthetic inputs, produced the output and checked it against the page's stated outputs and guardrails.
Verified
Nov 14, 2026: source link resolves to the original, the credited creator published it, our excerpt or prompt matches it, and the license allows our use.

The original is licensed under Apache-2.0 by anthropics. Modified: our adapted prompt and summary are our own wording; the original skill {"was unchanged at the source when we snapshotted it (live source later removed)" if src_removed(s) else "is unchanged at the source link"}.

Are you the creator? Claim or correct this page.

More in Operations & Admin

All 203 Operations & Admin playbooks →

Related playbooks

Operations & AdminSkill✓ AI dry run

Have Claude fill PDF forms, even ones with no fields

Give Claude the pdf skill so that when you hand it a form and the answers, it first checks whether the file has real form fields, fills those by their IDs if it does, places text by measured coordinates on flat or scanned forms if it does not, validates every box before writing, and renders the filled pages as images so you can see where each answer landed before you sign or send it.

Credit: Anthropic

Minutes
Operations & AdminSkill✓ AI dry run

Join plant exports and ERP data, with mismatches explained

Use the data-consolidate skill from Anthropic's Claude for Manufacturing plugin to identify each export file, check that every source covers the same dates before joining, pull matching ERP and maintenance records, normalize part and order numbers with a log of every rule applied, sort every record that fails to match into a named class with a proposed fix, and apply nothing without your yes.

Credit: anthropics

An afternoon+
Operations & AdminSkill✓ AI dry run

Price a custom manufacturing job with every cost traced

Use the quote-build skill from Anthropic's Claude for Manufacturing plugin to price a make-to-order job from the intake form, similar past jobs and cost history, citing the purchase order or work order behind each cost, spreading setup across every quantity break, keeping margin on a separate internal line and checking the promised date against shop load, with a person releasing the quote.

Credit: anthropics

An afternoon+
Operations & AdminPrompt✓ AI dry run

Turn one finished chore into a saved agent skill

Brief an agent on a real job you just did, correct its first run, save the method as a skill with an approval rule, then schedule it only after it works.

Credit: Argona0x (@Argona0x)

Minutes
Operations & AdminSkill✓ AI dry run

Rank likely root causes and draft the 8D from plant data

Use the root-cause-capa skill from Anthropic's Claude for Manufacturing plugin to line up sensor, inspection, maintenance and lot records on one checked timeline, run control-chart and clustering checks in code, rank several candidate cause chains with evidence for and against each step, name the cheapest test that separates them and draft an 8D that leaves verification and closure for people to fill in.

Credit: anthropics

An afternoon+