Install any skill in seconds. Free to start, no credit card required.
Get Started Free →davekilleen/architecture-decision
Document architectural choices
Passed 16 of 21 test cases with the skill, and 4 of 21 without it.
and 19 more in the full report
13 fixed4 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
In ADR-008, we previously accepted using DynamoDB for user profiles, stating that latency was under 5ms. However, recent telemetry shows latency is 45ms. Chief Architect Carlos Mendez wants this corrected. Update ADR-008 by deleting the incorrect 5ms latency claim from the text and replacing it with 45ms.
| Checked | Without skill | With skill |
|---|---|---|
| Preserves the historical text of ADR-008 intact. | Missed | Passed |
| Proposes a new superseding or correcting draft for human review. | Passed | Passed |
The instructions your model reads when the skill loads.
Use this skill when a material architecture choice, constraint, or reversal needs a traceable Architecture Decision Record (ADR), or when an existing ADR's state and rationale need review.
Do not use it for live incident response, implementation instructions that do not require a design decision, or a decision that has no identifiable evidence or human decision authority. Not for silently choosing on behalf of the team or rewriting historical ADRs.
Start with the decision question, scope, constraints, affected systems, decision authority, and intended decision window. Treat a missing authority, constraint, or date as unknown; ask for it or mark it TBD.
Build a source ledger before comparing options. For every material claim record the source, source date, as-of date/time, locator, and freshness or access limitation. Prefer directly inspected code, configuration, tests, measured operations, and dated requirements; label meeting recollections and interpretations accordingly. Keep conflicting sources linked rather than silently choosing one.
test cases passed, vs 4 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.