Packs

1 pack

Utility skills (decision-matrix, navigate, model-route, prompt-improver, grill-research, align-prompt). Useful for specialized one-off tasks like structured decisions, adversarial research grilling, or aligning a draft prompt to an Opus model. NOT for: daily development workflow — these are situational tools, not always-on skills.

4 skills · pack

Results for “opus”

3 skills

Auto-routes Claude Code subtasks to the cheapest capable model (Haiku/Sonnet/Opus), logs token costs, and A/B tests tiers to validate savings against real workloads.

More results

Recommends the optimal Claude model tier (Opus, Sonnet, or Haiku) for a given task by analyzing reasoning depth, blast radius, domain expertise, output length, and correctness cost, and suggests parallelization opportunities.

gan-style-harness

Uses a multi-agent generator-evaluator feedback loop to build high-quality applications from a single prompt, inspired by GANs and Anthropic's harness design.