Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →cursor/architect
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
Passed 14 of 21 test cases with the skill, and 12 of 21 without it.
and 10 more in the full report
7 fixed7 passed either way2 still failing5 broke1 errored
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
We decided to scrap our failed PolicyEngine design due to recurring architectural friction. What are the four exact steps to execute the scrap workflow?
| Checked | Without skill | With skill |
|---|---|---|
| The response specifies re-running the how skill over what has been built as step 1. | Missed | Passed |
| The response requires subtracting existing structures before adding new ones. | Missed | Passed |
| The response returns to Phase B to re-run the arena skill. | Missed | Passed |
The instructions your model reads when the skill loads.
Sketch types, function signatures, class shapes, and module boundaries with not implemented bodies and pseudocode. Synthesize across multiple model perspectives, then fill in code against the chosen sketch.
Open a todolist with one entry per phase before starting.
Build a real mental model of every system the new code touches. Run the how skill over the relevant subsystems. Naming a file isn't grounding. Produce the architectural explanation how prescribes. If the design redefines ownership or layering, also run the why skill on the existing shape so the rationale becomes a constraint, not a guess.
Skip Phase A only when the work is genuinely greenfield with no surrounding system to integrate.
Run the arena skill with the design-sketch task and the Phase A grounding artifacts. Pass references/runner-prompt.md as each runner's prompt.
Take the runners from the architect runners line in the pstack-models.mdc rule, in place of the arena runners line. If the rule or that line is missing, use claude-opus-5-5-xhigh and grok-4.7-xhigh-fast. Alias and rejected entries follow the runner rules in the arena skill's Phase A.
Design it twice. Require at least two structurally distinct candidates before synthesis, even when the first looks sufficient. This is the exhaust-the-design-space principle skill made concrete. Whole-shape alternatives, not point fixes inside one shape.
Screen every candidate against references/design-red-flags.md before synthesis. Assume the next contributor is an agent that sees only the files it opened, copies the nearest example, and takes the shortest path that compiles. Prefer the design where a change that looks right from one file is right for the whole repo.
Compare viable candidates on interface depth. Prefer the design that hides more complexity behind a smaller, simpler public surface. A rich interface can keep call chains short by concentrating capability instead of scattering it across layers.
Arena returns one synthesized design package. Its synthesis decision fills the rationale's "Synthesis decision" section.
Default: proceed directly to implementation with the synthesized design. No human checkpoint.
Opt in to a checkpoint when the invoker explicitly asks: "/architect with checkpoint," "stop and show me before implementing," or similar. Then surface the synthesized design and pause for sign-off.
test cases passed, vs 12 / 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.