Design surfaces where LLM judgment and deterministic code alternate as mutually-generative layers — each producing the working surface the other operates over. Lens → substrate → gate → reasoner → action, with calibration and metabolism closing the loop. Stacks at runtime and during development. Diagnostic-first skill plus a library of recognizable hybrid-loop block-graphs (RAG, ReAct, codegen-with-verification, multi-agent panels, dev-time critique loops, knowledge-base auditors, and more).
Plugin hybrid-loops from marketplace hybrid-loops in justinstimatze/hybrid. Commands read from the repo's manifest — 1 month ago.
hybrid-loopsFind and design hybrid-loop surfaces in any project — places where an LLM's fuzzy semantic judgment is consequential enough to warrant typed structure (schema'd store, deterministic gating, calibration). Triggers on prompts like "build a tool that tracks/analyzes/evaluates/extracts X over time", "ma
Solve competition math (IMO, Putnam, USAMO) with adversarial verification that catches what self-verification misses. Fresh-context verifiers attack proofs with specific failure patterns. Calibrated abstention over bluffing.
1 skill
Assisted retrospective: after a session, calibrates what Claude contributed vs what the developer drove. LLM-assessed 4-frame analysis with explicit rubric, zero dependencies.
1 skill
Reviews product launches against your risk calibration, answers 'is this a problem?' questions in minutes, checks marketing copy for claims that need substantiation, and flags upcoming launches that need legal eyes before anyone asks.
7 skills · 1 agent · 5 MCP servers
Study p-hacking in econometric designs: map researcher degrees of freedom, audit a specification search with a complete ledger and null-calibrated honest p-values, replay realistic search procedures, detect p-hacking in a literature, immunise an analysis, and benchmark whether an AI agent p-hacks. Research and teaching use only.
11 skills
Commands for scenario simulation and decision modeling
8 commands
Evaluate agentic experiences: behaviour evals, trust calibration, failure analysis.
7 skills · 3 commands
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.