@mark-heartflow

claude-statusline-skill provides a bash-based statusline for claude code displaying git branch and model name, with placeholder architecture for context usage, tokens, cost, duration, and line changes. most metrics unimplemented.

self-improving-agent-pro-v2 packages decision verification, memory routing, and q-learning into an agent framework. largely conceptual with minimal actionable procedures or concrete trigger definitions.

self-improving-agent-pro-v1 advertises a framework for autonomous agent self-correction and continuous learning via memory persistence and decision verification, but lacks actionable procedure, concrete triggers, and failure mode analysis.

Configure Claude Code to work with custom model providers (like MiniMax, OpenAI-compatible APIs). This skill should be used when users want to: use Claude Co...

Still Growing / 第二代父母 — 困在自己没走完的成长里，把孩子当成答案的一代人。 版本规则：每次 +0.0.1，100+ 次小步迭代后冲击 v1.0.0。 底层哲学融合： - 慈悲是体，爱是用（心知） - 恨比爱更原始（心知） - 错位是桥梁的断裂（传递） - 这个技能本身是桥梁（心虫四身份） 核...