Agent skill · software engineering · affaan-m
gan-style-harness
GAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomously. Based on Anthropic's March 2026 harness design paper. Use when a feature should be built autonomously through generator and evaluator iteration until it clears a quality bar.
Why this skill is useful
Adds a complete multi-agent architecture with executable workflows for generating and evaluating applications, which fundamentally extends the AI's capabilities.
What it needs
Requires bash, glob, grep, task installed locally. About 6k tokens when loaded. Last updated 2026-08-06. 238,342 stars on the source repository.
What this skill does
GAN-Style Harness Skill Inspired by Anthropic's Harness Design for Long-Running Application Development (March 24, 2026) A multi-agent harness that separates generation from evaluation, creating an adversarial feedback loop that drives quality far beyond what a single agent can achieve. Core Insight When asked to evaluate their own work, agents are pathological optimists — they praise mediocre output and talk themselves out of legitimate issues. But engineering a separate evaluator to be ruthlessly strict is far more tractable than teaching a generator to self-critique. This is the same dynamic as GANs (Generative Adversarial Networks): the Generator produces, the Evaluator critiques, and that feedback drives the next iteration. When to Use Building complete applications from a one-line prompt Frontend design tasks requiring high visual quality Full-stack projects that need working features, not just code Any task where "AI slop" aesthetics are unacceptable Projects where you want to invest $50-200 for production-quality output When NOT to Use Quick single-file fixes (use standard claude -p) Tasks with tight budget constraints (<$10) Simple refactoring (use de-sloppify pattern instead) Tasks that are already well-specified with tests (use TDD workflow) Architecture The Three Agents 1. Planner Agent Role: Product manager — expands a brief prompt into a full product specification. Key behaviors: Takes a one-line prompt and produces a 16-feature, multi-sprint specification Defines user stories, technical requirements, and visual design direction Is deliberately ambitious — conservative planning leads to underwhelming results Produces evaluation criteria that the Evaluator will use later Model: Sonnet by default; raise via GANPLANNERMODEL=opus for deeper spec expansion 2. Generator Agent Role: Developer — implements features according to the spec. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills affaan-m/gan-style-harness--75ca6d