I built an architecture skill that treats assumptions, evidence, and constraints explicitly. Looking for agent-generated failure cases.
Summary
A developer built an architecture skill that explicitly handles assumptions, evidence, and constraints, and is now seeking agent-generated failure cases to test it.
Similar Articles
How I built an open-source skill that forces AI agents into principal-architect mode
A developer describes creating an open-source skill that forces AI agents to adopt a principal-architect mode, enhancing their reasoning and design capabilities.
Built a weird agent skill RegretCheck-X
The post describes RegretCheck-X, an agent skill that targets one high-risk assumption for verification, tested in scenarios like cloud migrations and database upgrades.
I built an open-source skill that stops coding agents from overthinking simple tasks
An open-source agent skill classifies coding tasks into S/M/L/XL complexity classes to set appropriate execution depth, preventing overthinking simple fixes and enabling evidence-based reclassification.
SKILL.nb: Selective Formalization and Gated Execution for Durable Agent Workflows
Introduces SKILL.nb, a framework for governing reusable agent workflows through evidence-calibrated lifecycle policies, featuring selective formalization and gate-conditioned execution. It achieves significant improvements on web automation benchmarks and demonstrates resilience to environment drift.
Skill-Contracted Agents for Evidence-Aware Materials Literature Analysis
This paper presents AlphaAgent, a skill-driven agent framework for evidence-aware materials literature analysis, which decouples retrieval-based QA from report generation and outperforms a baseline on 40 materials-science questions.