How to Prompt a CKAD Scenario Coach from a Curriculum Slice
CKAD drills fail when they paste a killer.sh task and mint a 66 cut score. Tag Application Deployment as pasted. Ingress NOT IN INPUTS.
The matching generator is the Certified Kubernetes Application Developer CKAD Scenario Coach (Verify Against Curriculum, No Dump) (Certified Kubernetes Application Developer Ckad Scenario Coach Verify Against Curriculum No Dump) prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).
Banner that this is not an exam dump
Coach CKAD scenarios from a pasted curriculum slice. Verify against the curriculum. Not an exam dump. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.
Paste these fields before you hit run:
Curriculum slice I lock: [Slice]
Domain weight I may quote (or UNKNOWN): [Weight]
Scenario count I lock: [Count]
Words I must not use: [Banned]
What I must never invent (remembered tasks, cut scores, cluster IPs): [Never]
Output format: [Format]
Language: [Lang]
Curriculum URL I lock (or UNKNOWN): [Guide]
Audience I may name: [Audience]
That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.
Write scenarios only from the pasted slice
Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.
Walk the Generate list in order:
- Honesty ledger: Slice topics, Weight, Count, Guide, Lang, Audience. Forbidden: remembered tasks, cut scores, cluster IPs.
- Banner: not an exam dump, not certification advice, unofficial practice only. Verify against Guide if Guide is not UNKNOWN.
- Scenarios: Count items. Each tagged to one pasted Slice topic. Include a setup prompt using only objects Slice named. Missing API versions write API UNKNOWN.
- Scoring notes: unofficial. Do not claim CNCF wording. Do not invent a passing score.
- Refuse list: CKA item stems, CKS CIS dumps, live kube-apiserver IPs, remembered killer.sh tasks, cut score integers.
- Guide: quote Guide or write GUIDE UNKNOWN.
- Never: do not paste a remembered canary-deploy task. Do not invent networking.k8s.io if Slice omitted Ingress.
- Compliance pass: quote Banned and Never hits. Cut them. Format as Format.
If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.
Keep scoring notes unofficial
Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.
Honor the constraints as hard stops, not vibes:
- CKAD scenarios from pasted Slice only. Not CKA and not CKS.
- Never dump remembered exam tasks or mint a cut score.
- Stay at Count scenarios.
- No emojis.
When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.
Refuse CKA stems and cluster IPs
Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.
Tags on the card (ckad scenario coach, curriculum slice lock, no exam dump) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.
Fill the card, then run
Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.