inspection-to-capa — скилл для Claude Code: задачи и установка
Скилл inspection-to-capa для Claude Code проводит разбор несоответствия от инспекции до проекта отчёта 8D. Он включается по запросу пройти весь процесс CAPA.
Apache-2.0 ★ 47 914 обновлён 2026-10-24
npx skills add anthropics/claude-plugins-official --skill inspection-to-capa -a claude-codeЧто делает inspection-to-capa
Скилл связывает ncr-writeup и root-cause-capa: оформляет несоответствие со ссылкой на требование, ищет похожие случаи и проверяет, сработало ли прошлое исправление. Затем сопоставляет данные инспекции и производства на общей временной шкале, предлагает ранжированные версии причин с аргументами за и против и готовит проект 8D и пакет для заказчика с diff редактирования.
В отчёте разделы D1–D5 и D7 заполняются по имеющимся свидетельствам; D6 и D8 остаются шаблонами. До продолжения владелец качества подтверждает несоответствие и план локализации, а перед отправкой материалов заказчику проверяют diff. Если требование нельзя найти, процесс останавливается на оформлении несоответствия. Данные можно вставить в переписку или передать файлами; подключённые Microsoft 365 и ERP тоже читаются.
Какие задачи решает
- оформить несоответствие со ссылкой на нарушенное требование
- найти повторные случаи и выяснить, сработало ли прежнее исправление
- сопоставить инспекционные и производственные данные по времени
- составить ранжированные версии причин с подтверждающими и опровергающими фактами
- подготовить проект 8D и редактируемый пакет для заказчика
Примеры запросов агенту
- Проведи весь процесс CAPA по этим данным инспекции.
- Оформи это несоответствие и доведи его до проекта 8D.
- Проверь, встречалась ли такая проблема раньше и помогло ли прошлое исправление.
Как установить inspection-to-capa
1Через Skills CLI (Vercel)
npx skills add anthropics/claude-plugins-official --skill inspection-to-capa -a claude-code2Вручную: положить файлы
~/.claude/skills/inspection-to-capa/SKILL.mdПапка скилла целиком; для одного проекта — .claude/skills/inspection-to-capa/
1Через Skills CLI (Vercel)
npx skills add anthropics/claude-plugins-official --skill inspection-to-capa -a codex2Вручную: положить файлы
.agents/skills/inspection-to-capa/SKILL.mdДля всех проектов — ~/.agents/skills/
1Через Skills CLI (Vercel)
npx skills add anthropics/claude-plugins-official --skill inspection-to-capa -a cursor2Вручную: положить файлы
.cursor/skills/inspection-to-capa/SKILL.mdCursor читает и .agents/skills/, и .claude/skills/
1GitHub CLI
gh skill install anthropics/claude-plugins-official plugins/claude-for-manufacturing/skills/inspection-to-capa2Вручную: положить файлы
.github/skills/inspection-to-capa/SKILL.md1Через Skills CLI (Vercel)
npx skills add anthropics/claude-plugins-official --skill inspection-to-capa -a gemini-cli2Командой платформы
gemini skills install https://github.com/anthropics/claude-plugins-official --path plugins/claude-for-manufacturing/skills/inspection-to-capaВручную: положить файлы
.devin/skills/inspection-to-capa/SKILL.mdСтарый путь .windsurf/skills/ тоже читается
Claude.ai
Упакуйте папку в zip и загрузите в Settings → Capabilities → Skills
По шагам, с командами для каждой платформы: Как установить скилл в Claude Code: пять способов
Вопросы об inspection-to-capa
Как установить inspection-to-capa в Claude Code?
Выполни npx skills add anthropics/claude-plugins-official --skill inspection-to-capa -a claude-code. Файл скилла устанавливается по пути ~/.claude/skills/inspection-to-capa/SKILL.md.
Что делает inspection-to-capa?
Скилл связывает оформление несоответствия с анализом причин: ищет повторные случаи, сопоставляет данные и готовит проект 8D и пакет для заказчика с diff редактирования.
Что происходит, если скилл не находит требование?
Процесс останавливается на этапе оформления несоответствия. Скилл не придумывает требование.
Исходный текст
SKILL.md · Apache-2.0
--- name: inspection-to-capa description: "Runs the quality chain end to end: writes the nonconformance against the requirement it violates, searches history at the moment of writing to say whether this has happened before and whether the last fix held, reads sensor and inspection data on one verified timeline, proposes ranked candidate causes with evidence for and against, drafts the 8D, and produces the customer pack behind a redaction diff. Use when someone says \"run the CAPA chain,\" \"take this nonconformance through to an 8D,\" \"inspection to CAPA,\" or asks for the full corrective-action workflow." compatibility: "Requires none. Chains ncr-writeup and root-cause-capa. Reads Microsoft 365 and the ERP (Oracle NetSuite or Infor M3) where connected; runs on pasted findings and file exports with no connector. Never asserts a requirement it cannot locate, never correlates across clocks it could not align, and nothing customer-facing leaves without review of the redaction diff." --- # Inspection to CAPA Chain 2. `ncr-writeup` → `root-cause-capa`. The path from "we found a bad part" to "we fixed the reason, and we can prove it." It ends on the 8D and its redacted customer pack. **Quick start** ``` → Write the NCR against a CITED requirement. Cannot find one? Block. Never invent → Search history AT CREATION, not on request. Did the earlier fix hold? → Gate 1: the quality owner confirms the NCR and its containment → Verify the clocks BEFORE correlating. Misaligned? Refuse, and say what survives → Ranked candidate chains with evidence FOR and AGAINST. Never one verdict → 8D: D1-D5 and D7 populated. D6 and D8 stay empty placeholders → Gate 2: nothing customer-facing leaves without the redaction diff reviewed ``` --- ## Inputs | Input | Source | Form | |---|---|---| | The finding | Inspector notes, an inspection export, an operator report, a customer complaint | Conversation, M365, pasted | | Everything else | Whatever the two member skills read | See each skill | --- ## The seven steps **1. An inspection result or a suspect lot starts it.** **2. Write the nonconformance** against the requirement, with quantity and location. All five containment locations are addressed, including with a zero quantity, because an omitted location reads as "none there" rather than "not checked." **Gate 1** — the quality owner confirms the NCR and the containment plan. **This is a pause, and the chain says so:** *"Paused at Gate 1, after step 2. The NCR is a draft. A quality owner confirms four things before step 4 — the finding, the cited requirement, the suspect scope, and the containment plan."* A missing citation is one reason the NCR is not ready; it is not the gate. Fixing the citation does not unblock the chain — the owner's confirmation does. The history search in step 3 still runs at write time, because it belongs to the NCR. Per `../../shared/approval-gates.md`. **3. Search history for the same problem.** This runs automatically at write time, not on request, because the moment of detection is the only moment anyone is looking. **Whether the earlier fix held is the highest-value single line in this chain.** A recurrence after a *closed* CAPA is a materially different finding from a first occurrence, and it changes what happens next. Surface it as such. **4. Read the prior tickets, inspection data and production history together**, aligned onto one zone-aware timeline. Verify the clocks first; where alignment cannot be verified, refuse to correlate and say which conclusions survive anyway. **5. Propose ranked candidate causal chains**, each stated as a chain with supporting *and contradicting* evidence attached to each link, and the cheapest test that would confirm or kill it. Never one confident verdict: a confident wrong root cause closes the investigation and the fix fails. **6. Draft the 8D.** D1 to D5 and D7 populated from the evidence. D6 and D8 stay as structured placeholders, because they need a real-world outcome and a human signature. **7. Produce the customer-facing pack with a redaction pass.** **Gate 2.** --- ## Approval gates | Gate | Where | What it protects | |---|---|---| | 1 | After step 2 | The quality owner confirms the finding, the cited requirement, the suspect scope and the containment plan | | 2 | After step 7 | Nothing customer-facing leaves without review of the **redaction diff** | The redaction pass is a reviewable diff, never a silent filter. The internal 8D carries cost data, other customers' names, supplier identity and internal process detail; the customer version must not. **A recurrence stays in** — removing it is misrepresentation, not redaction. --- ## 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 NCR in the plant's controlled template, the containment plan ordered by urgency, the recurrence finding with whether the previous fix held, the ranked candidate causes with their discriminating tests, the drafted 8D, the evidence appendix, and the redacted customer pack. **The figures block** — required, inside the evidence appendix. Every measurement, control limit, ratio and count the chain states is printed from the computation and listed with it, and the prose quotes the block. Two member skills doing the same arithmetic must not arrive at two different multiples of the same limit. Per `../../shared/computed-figures.md`. Where the leading candidate points at purchased material, the **supplier-caused flag** is raised, which is the trigger into Chain 5. See `supplier-escape-to-alternate-source`. **The Quality command-center page: the Quality Register** — open corrective actions, carrying the NCR and the 8D by reference, updated in place per `../../shared/live-dashboard.md`. **The chain writes no register row of its own.** `ncr-writeup` writes the row at step 2 and `root-cause-capa` adds the 8D fields at step 6, both keyed `<site>_<ncr_ref>`, so one chain run leaves one row. The chain reports the register once, at the end: the dashboard line with its URL and the sensitivity line, or the fallback with *"The Quality Register was not updated: [reason]."* It is reported as updated only when a publish returned a URL in this run, and never as shared. Read `../../shared/command-center.md`. --- ## Edge cases and failure modes - **The requirement cannot be located** — the chain **blocks at step 2**. Never invent one. That is a complete and honest outcome. - **Traceability is incomplete** — the suspect scope **widens** and says why. Never narrow it to make the number look better. - **The clocks cannot be aligned** — step 4 refuses to correlate. Non time-dependent analysis still runs, and the output says which is which. - **Two candidates are supported equally** — present both. A stated tie is a real finding, and it names the test that would settle it. - **No prior history exists** — say so. Absence of recurrence is not evidence of a one-off. --- ## Degradation | Not available | What happens | |---|---| | The quality document library | Report "no searchable history available" at step 3. **Never silence**, which reads as "no recurrence" | | The sensor export, or it misses the event window | Say so. Do not reason from adjacent data as if it were the event | | The plant's 8D template | Use the standard eight-discipline structure and flag that the controlled template was unavailable | | A CMMS connector (Limble or any other) | See below | **Check the freshness of every export before correlating on it.** A scheduled export that silently stopped produces a timeline with a hole in it, and the hole looks like an absence of evidence rather than an absence of data. State the coverage window of each source in the evidence appendix. **If Limble isn't included, or no CMMS connector is live** — minor here. Maintenance history arrives in the same scheduled export as everything else and the maintenance-correlation check runs on it unchanged. What changes is freshness: name maintenance explicitly as an export-sourced input in the evidence appendix rather than letting it read as live, since a repair logged after the last export will not be on the timeline at all. --- ## Chain position **This is Chain 2 itself.** Members: `ncr-writeup`, `root-cause-capa`. **Metric.** CAPA closure time and first-pass yield, both owned by `root-cause-capa`. `ncr-writeup` also moves nonconformance closure time and escape response time inside this chain; the chain does not claim them, because it is named for the corrective-action loop. --- ## Reference files | File | Load when | |---|---| | `../ncr-writeup/SKILL.md` | Steps 2 and 3 | | `../root-cause-capa/SKILL.md` | Steps 4 to 7 | | `../../shared/contracts/ncr.md` | The handoff, and what blocks `root-cause-capa` | | `../../shared/command-center.md` | The Quality page, and when "updated" may be said | | `../../shared/live-dashboard.md` | The Quality Register: one row per NCR, the banner, the fallback | | `../../shared/computed-figures.md` | Before stating any figure — the figures block | | `../../shared/approval-gates.md` | At both gates — a gate is a pause, and how to say where the chain stopped |
© anthropics · Apache-2.0 · anthropics/claude-plugins-official