Skills for “ci”
400 skills match · 325 ms · understood as by meaning
…(2) retrieving schemas, metadata, or governance policies for a GCP data asset (including a named table); (3) you have a keyword or topic (e.g., "sales data") without a table or resource ID; (4) the user asks for…
…Use when Core Web Vitals changed after a deploy, to decide which pages to fix first, to read values from the OpTel Explorer, to answer a question about traffic, visits, clicks or errors from real-user data, or to…
…Creates an App Builder project only when the user explicitly requests "App Builder" or a "template" project; otherwise creates a default project without asking. Creates and initializes the project with a single…
…what is using up the LCP budget, or a budget check in CI. To diagnose LCP, CLS or INP in general, use…
…or 25,000 records-per-type caps), tier and capacity questions, filtering records through the API, choosing an automation surface, or reconciling public docs with actual API behavior. Also trigger for "build…
…the real requirement is four messages down — and pulls specifications, quantities and dates into one consistent intake form with every field traceable to the file and page it came from. Records how each tolerance was…
…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…
…history including the free-text close-out notes technicians actually wrote, photos of what they can see, and the manufacturer's troubleshooting tree — then ranks likely causes, each with its supporting evidence,…
…two ways, priced losses and the exceptions needing a decision. Stores a record per production day and keeps one Operations Command Center dashboard per site up to date, with a 14 and 30 day trend. Safe to run…
…week-over-week movers; and the exceptions needing a decision today. For each significant exception it drafts a specific reschedule or changeover move with its consequences traced, never a re-optimised day. Reads…
…capability, machining data, standards, templates and commercial rates, reports which skills are limited by anything missing, and ends with connector options for every other system named. Unknowns are deferred, never…
…nonconformance report: what was found and measured, the specific requirement it violates cited to its document and locator, how many parts are actually suspect and why that scope rather than a narrower one, and where…
…records the corrective action, then builds the sourcing package with a response format that makes the returned bids comparable. Use when someone says "run the supplier escape chain," "a supplier caused this,…
…raises the supplier-caused flag that starts a sourcing action. Use when someone says "why did this happen," "root cause," "write the 8D," "investigate this nonconformance," "CAPA," or "the customer wants a…
…closed-job actuals, the confirmed design, first principles) with setup and run kept apart, setup re-amortized at each quantity break, and margin on its own line. Checks the promised date against real shop load…
…and its analysis results into a scored comparison and a decision memo, with every score cited to its source. Runs the sensitivity analysis every time — where the winner flips, which criterion the decision actually…
…RFQ package that goes out to suppliers — drawing and specification at the verified current revision, the demand picture, the quality clause list, commercial terms, and a mandated response format that makes the…
…a repro loop, or debug against a running system, and especially when following TDD or bug-diagnosis skills (such as `tdd` or `diagnosing-bugs`) in a repo whose live deployment runs on the same host, shares its…
…and assumptions separate, with quotes as receipts, explicit non-goals, and success metrics. Use when the user asks for a PRD, product requirements, a feature spec, or to synthesize user or stakeholder interviews…
Rewrites product, portfolio, and launch copy into plain, specific language by removing AI-sounding filler, em dashes, inflated verbs, and vague outcomes, without adding any new claims. Use when the user asks to edit,…