hwkwon1114/design-decision-advisor

Empirical decision-making assistant for computational design research. Use this skill whenever the user is at a decision point and wants to compare design representations, optimization algorithms, objectives, or any algorithmic choice empirically through code experiments — rather than guessing or reasoning abstractly. Always invoke when the user says things like "which is better", "compare X and Y", "should I use X or Y", "test this representation", "evaluate expressivity", "which optimizer converges faster", or any time they want to run experiments to resolve a design or algorithmic decision. Also trigger for any question about coverage of design space, gradient quality of a representation, BoTorch acquisition function choices, or surrogate model comparison. The user works with spatial and temporal data in JAX, PyTorch, BoTorch, NumPy, and SciPy — lean on this stack.

Claude Skills are markdown + scripts loaded into Claude Code; scanned with the same pipeline.

Source:

github.com/hwkwon1114/design-decision-advisor

Provenance:

Found by crawling (provenance, not a security rating)

We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.

7 critical findings reported by cisco-skill-scanner. The composite score alone does not reflect this — read the per-scanner reports below.