pskoett-ai-skills vs superpowers-optimized

A self-improving agent skill pipeline that prevents common AI coding agent failures. Includes 6 skills (plan-interview, intent-framed-agent, context-surfing, simplify-and-harden, self-improvement, agent-teams) and 5 subagents (simplify-auditor, harden-auditor, spec-auditor, context-monitor, self-improvement-logger). The pipeline catches scope drift, context degradation, security gaps, and repeated mistakes — each skill targets a specific failure mode and hands off cleanly to the next.

Built on the trusted obra/superpowers workflow and refined through research into LLM agent behavior, it adds automatic 3-tier workflow routing, proactive safety hooks, self-consistency verification at critical decision points, cross-session memory, and adversarial red-teaming — everything the original does, plus the discipline layer it was missing. Cross-session memory changes the experience fundamentally. Without it, every session starts blind: the AI re-explores structure it already mapped, re-proposes approaches that were already rejected, re-debugs errors that were already solved. With the four-file memory stack, it arrives knowing what was tried, what was decided, and why — and builds forward instead of sideways. Five research-backed principles run throughout: *less is more* (minimal always-on instructions), *fresh context beats accumulated context* (subagents get clean scoped prompts, not polluted history), *compliance ≠ competence* (instructions must be carefully engineered, not just comprehensive), *v