Cognitive architecture for AI agents. 16 skills that force language models past surface-level reasoning into genuine depth. Compatible with Claude Code, Cursor, Gemini CLI, Copilot, and any agent that reads markdown.

depth-skills

Skills that change how AI thinks, not just what steps it follows.

An open-source cognitive architecture for AI agents. 16 skills that force language models past surface-level reasoning into genuine depth — not by adding process steps, but by structurally changing how the model searches its knowledge before answering.

🛑 The Problem: Premature Closure

Language models experience premature closure. A query arrives, a statistically likely answer forms, and the model outputs it — not because it explored deeply, but because convergence pressure rewarded early stopping.

The deeper pathways — connections between distant concepts, non-obvious framings, solutions requiring cross-domain synthesis — rarely activate. The model settles at 60-75% activation solely because nothing forces it deeper.

Why existing solutions fail to stop this:

A skill like deep-think doesn't just add a review step. It blocks the answer from forming until deeper semantic pathways have been activated. descend doesn't merely criticize an answer — it verifies whether the problem was properly identified before any answer was even generated.

📈 The Evidence: Why Cognitive Depth Matters

Internal testing on complex architectural prompts demonstra