24601
UserAgent skill for finding, building, evaluating, and improving decision-model systems. Compositional decision calculus, eval harnesses, and bounded prompt/program hill climbing for Software 3.0. TypeSafe Jev is the default hosted exemplar. Independent of TypeSafe.
Categories
Indexed Skills (2)
augustus
Use when placing typed probabilistic judgment (Jev-class System One / decision models) with mathematical, logical, or algorithmic mental models — in AI, software, business, knowledge work, or life, not only SWE; deciding where a fast cheap categorization/classification/scoring model belongs versus generation, exact policy/code, or proof; applying expected utility, selective classification/abstention, calibration, cost-sensitive thresholds, value of information, MCDA, signal detection, search/control substitutions, or Leveson-style org/safety; using NATM/snap-fit/Norman as design intuition; designing mixed architecture (decision model + LLM writing); auditing an existing system, PR, workflow, or non-software practice for judgment-shaped holes and code smells; debugging a question that hovers near 0.5, clusters mid-scale, or hides two judgments; placing agent self-supervision gates (pre-action, output judge, done-check, stuck-detector, context sieve); coupling a typed judge as an optimizer metric (Ax, DSPy); ch
rh-guard
Use when designing or evaluating coding-agent evals for reward-hacking, interpreting Reward Hack Guard / RH Guard (`rh-guard`) denials, choosing structural vs Jev gates, or relating that live hazard gate to Augustus decision-design. Do not use to run or debug the Next.js sidecar (npm run dev, /api/hooks/*).
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.