breakdown-to-next-report — Claude Code skill: diagnosis to report
The breakdown-to-next-report Claude Code skill investigates equipment failures and carries the downtime record into the next production report. It starts from a breakdown or a request to run the diagnostic chain.
Apache-2.0 ★ 47,914 updated 2026-10-24
npx skills add anthropics/claude-plugins-official --skill breakdown-to-next-report -a claude-codeWhat breakdown-to-next-report does
The skill assembles failure evidence and prepares an entry for the next production report. It compares sensor readings with maintenance history and notes, technician photos, and the manufacturer's manual, then ranks possible causes and proposes a test to distinguish them. Each candidate is tied to supporting evidence and prior work orders; an unsupported candidate is labelled a guess.
Safety implications come before diagnosis. The chain then waits while a technician works on the physical machine. Its diagnosis remains advisory, and it never updates a CMMS ticket. The downtime record goes into the next report's log and exceptions; a matching MES event is identified by asset and start time so the stoppage is counted once.
A connected CMMS connector provides maintenance history and plans; Limble is the worked example. The skill can also use a historian export and uploaded photos. It can run without sensor data or a connector, but the technician's cause remains unconfirmed until that step is completed.
What it helps with
- compare sensor readings with maintenance history after a failure
- rank likely causes and identify a test that separates them
- carry a diagnosis and downtime into the next production report
- match a diagnosis to an MES event without counting the stoppage twice
Example prompts for the agent
- Run the diagnostic chain for this equipment failure.
- Diagnose the breakdown and add it to the next report.
- Investigate the stoppage and include the downtime in the report.
How to install breakdown-to-next-report
1Skills CLI (Vercel)
npx skills add anthropics/claude-plugins-official --skill breakdown-to-next-report -a claude-code2Manually: put the files in place
~/.claude/skills/breakdown-to-next-report/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/breakdown-to-next-report/
1Skills CLI (Vercel)
npx skills add anthropics/claude-plugins-official --skill breakdown-to-next-report -a codex2Manually: put the files in place
.agents/skills/breakdown-to-next-report/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add anthropics/claude-plugins-official --skill breakdown-to-next-report -a cursor2Manually: put the files in place
.cursor/skills/breakdown-to-next-report/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install anthropics/claude-plugins-official plugins/claude-for-manufacturing/skills/breakdown-to-next-report2Manually: put the files in place
.github/skills/breakdown-to-next-report/SKILL.md1Skills CLI (Vercel)
npx skills add anthropics/claude-plugins-official --skill breakdown-to-next-report -a gemini-cli2Platform CLI
gemini skills install https://github.com/anthropics/claude-plugins-official --path plugins/claude-for-manufacturing/skills/breakdown-to-next-reportManually: put the files in place
.devin/skills/breakdown-to-next-report/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about breakdown-to-next-report
How do I install breakdown-to-next-report in Claude Code?
Run npx skills add anthropics/claude-plugins-official --skill breakdown-to-next-report -a claude-code. The skill file is located at ~/.claude/skills/breakdown-to-next-report/SKILL.md.
What does breakdown-to-next-report do?
It analyzes failure evidence, ranks possible causes, and sends the diagnosis and downtime into the next production report. The diagnosis is advisory; the skill does not update CMMS tickets.
What does breakdown-to-next-report need to run?
It can run without a CMMS connector or sensor data. When connected, a CMMS connector supplies maintenance history and plans; the skill can also use a historian export and technician photos.
Source text
SKILL.md · Apache-2.0
--- name: breakdown-to-next-report description: "Runs the chain from a machine going down to the diagnosis landing in tomorrow's production report: reads the sensor window, the maintenance history and its free-text close-out notes, technician photographs and the manufacturer's manual together, ranks likely causes with the cheapest test that tells them apart, then folds the diagnosis and its downtime into the next morning's downtime log and exceptions. Use when someone says \"run the breakdown chain,\" \"a machine went down,\" \"diagnose this and get it into the report,\" or \"breakdown to next report.\"" compatibility: "Requires none. Chains breakdown-diagnosis and daily-production-report. Reads a CMMS connector (Limble is the worked example) for assets, history and PM plans when connected, plus a historian export and uploaded photos. Runs with no sensor data and no connector at all. Safety implications surface before any diagnosis. The diagnosis is advisory throughout and is never written back to a ticket." --- # Breakdown to Next Report Chain 4. `breakdown-diagnosis` → `daily-production-report`. Every minute a machine is down, the plant is not producing. The largest component of MTTR is usually not the repair; it is working out what is actually wrong. This chain does that part, then makes sure the answer does not evaporate before the morning meeting. **Quick start** ``` → Capture the event: asset, time down, symptom, fault codes → SAFETY FIRST. Any safety implication surfaces before any diagnosis. Always → Read sensor window, maintenance history, close-out notes, photos, the manual → Rank causes. Each CITES specific prior work orders. No citation means a guess → The technician works the list. The chain pauses here by nature → The diagnosis and its downtime land in the next report's log and exceptions ``` --- ## Inputs | Input | Source | Form | |---|---|---| | The breakdown event | A user report, or a maintenance work order | Conversation, CMMS connector or maintenance export | | Sensor window around the failure | Historian export, scheduled or on demand | CSV | | Technician photos | Uploaded, or M365 | Images | | Everything else | Whatever the two member skills read | See each skill | --- ## The five steps **1. A machine goes down.** **2. Read the evidence together** — the recent sensor window, the maintenance history including its free-text close-out notes, the technician's photographs, and the manufacturer's manual. The close-out notes are the highest-signal input and the least used: what the technician actually wrote about what they found, in prose, which nobody ever aggregates. **3. Rank the likely causes**, each with the evidence supporting it, **the cheapest and fastest test that tells it apart from the others**, and the expected fix. Every candidate cites the specific prior work orders behind it, so the technician can read what was actually done last time. A candidate with no citation is a guess and is labelled as one. **4. The technician works the list.** The chain pauses here by nature: this is a person at a physical machine. **5. The diagnosis and the resulting downtime feed into the next production report's downtime log and exceptions**, through `daily-production-report`. **State the match rule, and say the stoppage was counted once.** The diagnosis record and the MES downtime row describe the same stoppage. The chain matches them on **asset plus start time** — same `asset_id`, and `started_at` within the same shift — and the report carries one row for the stoppage, with the diagnosis fields attached to it. Two required lines in the output: *"Matched the diagnosis record to MES row <asset, started_at> on asset plus start time"* and *"counted once."* Where no MES row matches, say that, and the diagnosis record stands alone as the row. Flagging the possible double count without stating the rule leaves the reader to reconcile it. --- ## Approval gates **Step 4 is the pause, and it is not a gate the plugin enforces** — it is a human working a machine. The chain simply has nothing to do until they are done. **Say whether step 4 happened.** The record carries `technician_step`: `confirmed` when the technician came back with a confirmed or corrected cause, `pending` while the chain waits, `skipped` when the record was folded in with no technician step (a test, a demo, or "put it in the report now"). The output states it in one line, and the report carries it beside the cause: *"cause proposed, technician step skipped"* reads differently from *"cause proposed, technician still working"*. **The diagnosis is advisory throughout.** A CMMS connector's write scope for closing or updating work orders is unconfirmed (Limble's is not public), so the output is a draft the technician applies, never an automatic ticket update. Nothing here writes to a system. **Safety outranks the sequence.** Where a failure has a safety implication, it surfaces **first**, before any diagnosis. Never let a diagnosis suggestion precede a safety flag. --- ## The handoff is the chain's whole risk `breakdown-diagnosis` emits a downtime record in **exactly** the shape `daily-production-report` consumes, with **no transformation step in between**. The reason is specific: the report already reads downtime events from the MES or historian export. A record arriving from a diagnosis is a **row in that same log**, not a separate feed. If the two shapes differ, the report has to reconcile them, and a reconciliation step between two sources of downtime is exactly how a stoppage gets counted twice or dropped. Read `../../shared/contracts/downtime-record.md`. Two fields carry weight across the handoff. `safety_flagged` is required, and a missing value is treated as unknown rather than false. `duration_minutes` is null while the machine is still down and **never zero**, because a zero would rank an ongoing outage last in a log sorted by minutes. --- ## Output **Every document this skill produces is printed in the reply, in full.** Saving a copy to a file as well is fine, as Word or Excel per `../../shared/replies.md`, never `.txt`; a file *instead of* the reply is not. The person reads the reply, and every delimited block and outbound check lives in it — a document only on disk has been neither seen nor checked. **A record handed to another skill is saved and summarised, never pasted as raw YAML**; memory blocks are written where the plant's memory lives; and the name on an approval is asked, never taken from the account. All three per `../../shared/replies.md`. The ranked candidate causes with their evidence and discriminating tests, the cited history behind each, a plain statement of what the sensor data showed, the PM plan adjustment drafted for the planner, and the structured downtime record that flows into the next report. **The figures block** — required. How many maintenance records the asset has, how many carried usable notes, how many downtime events and minutes: each is printed from a query run in this session, listed with that query, and quoted by the prose rather than retyped. A chain summary is where a count most often drifts from the step that produced it. Per `../../shared/computed-figures.md`. **The Operations command-center page, maintenance section** — an artifact you place. Read `../../shared/command-center.md`. --- ## Edge cases and failure modes - **No sensor data for this asset** — very common, most machines are not instrumented. Proceed on history, notes, photos and the manual, and say clearly that sensor evidence was unavailable. - **A new machine with no history** — fall back to the manual and to sibling assets of the same model. - **Close-out notes are terse or useless** — report the coverage honestly rather than over-reading "fixed." - **Photos are ambiguous** — describe what is visible. Do not assert a diagnosis from an unclear image. - **The machine is still down when the report runs** — the record carries a null duration, leads the exceptions, and is excluded from the minutes ranking with that exclusion stated. --- ## Degradation | Not available | What happens | |---|---| | The historian export | Run on history, notes, photos and the manual. Say sensor evidence was unavailable | | The current PM plan | The PM-plan-adjustment step degrades to a recommendation that first asks what today's interval is. **The step stays either way** | | **A CMMS connector** (Limble or any other) | See below | **Check the freshness of anything export-sourced, and say it.** A scheduled export that silently stopped is the normal failure here, and a diagnosis built on a stale sensor window or stale history reads exactly like one built on current data. Name the age of each source in the output. **If Limble isn't included, or no CMMS connector is live** — the default — this is the chain that changes most. It still runs end to end: step 2 reads maintenance history from a scheduled export rather than live tickets, and everything downstream is unchanged. What is lost is the chain's real-time character. A breakdown is happening *now* and a nightly export is not, so the tickets closest to the event are exactly the ones missing. **Any of three mitigations satisfies step 2**, and all three are cheap: an on-demand export the technician triggers, pasted or uploaded work orders for that asset, or the technician simply describing recent work in conversation. Build the chain so any one of them is enough. --- ## Chain position **This is Chain 4 itself.** Members: `breakdown-diagnosis`, `daily-production-report`. **Metric.** MTTR, owned by `breakdown-diagnosis`. Downtime cost visibility, owned by `daily-production-report`, which prices downtime against the configured cost-per-hour on every run. --- ## Reference files | File | Load when | |---|---| | `../breakdown-diagnosis/SKILL.md` | Steps 2 and 3, and the bad-actor batch mode | | `../daily-production-report/SKILL.md` | Step 5 | | `../../shared/contracts/downtime-record.md` | The handoff — the shape that must not be transformed | | `../../shared/command-center.md` | The Operations page, and why it is never a write | | `../../shared/computed-figures.md` | Before stating any count — the figures block |
© anthropics · Apache-2.0 · anthropics/claude-plugins-official