Iteration 4: - Overlay Skills (step 12): an Execution names an organisation's standards Skill from the folders the deployment configures; recorded with its version. An example standards Skill and an evaluation case that uses it. - Lessons (step 10): a prove command that compares a run with lessons against one without, and triage of evidence an existing lesson already covers. Iteration 5: - Step 8: the references of a Specialist's Skills its task needs are named in its context as read_first. - Step 14: a remote MCP server's reply that instructs the agent is withheld; the user's own text is flagged as a risk and nothing more. - Step 15: in a Change request, items only reworded are listed apart from real changes. - Step 19: each Execution's design recommendations are judged when it ends and the scores kept in its record. The evaluation takes its rubric from the same place. Each question was calibrated against live Jev; none has run in a case. Steps 6, 7, 9, 13 and 18 stay planned, with the reasons in the plan map. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2.1 KiB
2.1 KiB
name, description, metadata
| name | description | metadata | ||||
|---|---|---|---|---|---|---|
| example-organisation-standards | An example of an organisation's cloud standards as an overlay Skill: naming, mandatory labels, approved regions and a short list of things never to do. Use on any Deliverable of an Execution that names this overlay, to apply the organisation's standards on top of the Cloud provider's guidance. |
|
Organisation standards (example)
This is an example. Copy it, replace every rule with your organisation's own, and name the copy when you start an Execution. Nothing here is a real organisation's policy.
An overlay adds to the Cloud provider's guidance. Where the two disagree, this Skill wins; where a requirement the user stated disagrees with this Skill, say so in your Deliverable and follow the user's requirement.
Naming
- Every resource is named
<workload>-<environment>-<purpose>, lower case, with hyphens:orders-prod-ingest. <environment>is one ofdev,test,prod, and comes from a variable.
Labels
Every resource that accepts labels carries all four:
| Label | Value |
|---|---|
workload |
the workload's short name |
environment |
dev, test or prod |
owner |
the owning team's short name |
cost-centre |
the cost centre code, from a variable |
Regions
- Deploy only to
europe-west1oreurope-west4. - Data at rest stays in the European Union.
Never
- No public IP address on a database.
- No service account key files; workloads use attached identities.
- No resource without deletion protection in
prod, where the resource type has it.
What each Specialist does with this
- Requirements: record each standard above that applies as a non-functional requirement, with this Skill as its source, so it is traced like any other.
- Design recommendations and Target architecture: a standard that applies becomes a Check on every Element it constrains.
- Infrastructure code: follow the naming and label rules exactly.
- Validation: the standards are verified through the Checks that came from them.