AI-native SDLC – 156 test docs, 16 skills, 1 human
156 test docs, 16 AI skills, 1 human: honest experiment in AI-native SDLC, not production auth yet.
Measure what your brain is losing while AI does your work - unaided-skill baselines, decay curves, reliance drills
Chess Elo for coding skills shows the gap between you-with-AI and you-alone.
Developers concerned about AI dependency eroding their skills
Exercism · LeetCode · Codewars
156 test docs, 16 AI skills, 1 human: honest experiment in AI-native SDLC, not production auth yet.
Generates lessons from your actual code gaps instead of generic tutorials.
First benchmark testing structured requirements on complex greenfield agent tasks.
Benchmarks readOnlyHint's impact on MCP parallelism, but archived before yielding actionable best practices.
Pass@k scoring with baseline comparison shows if your skill actually improves the agent.
Maps Git worktrees to AI tasks to stop context decay in VS Code.