will-wright-eng-skills

Explain the autoresearch methodology — a verifiable autonomous experiment loop — and evaluate whether the current repo is a good fit before running the autoresearch-verify and autoresearch-program skills. Use when a user wants to add autonomous experimentation to a project, asks about autoresearch/autoresearch, or is about to invoke the other autoresearch skills.

Generate `program.md` at the repo root from the autoresearch program template, with mutable/immutable scope and verifier commands baked in via light templating. Run after autoresearch-verify produces the verifier script. The generated program.md is the operating directive for a fresh agent session running the autoresearch loop — after this skill runs, the autoresearch skills are no longer in the picture. Use when a user wants to generate the loop directive for an autoresearch run.

Build a repo-specific verifier script for an autoresearch loop. The script has two modes — `light` (fast per-candidate metric evaluation, emits the JSON the loop consumes) and `heavy` (matrix-of-conditions integrity check). Run after autoresearch-method confirms the repo fits and before autoresearch-program. Use when a user wants to build the verifier script for an autoresearch loop.

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.