nightboy87/anxi-skill
教练，我想训练 Skill。A local Agent Skill that trains unstable skill packages with bounded patches, human review, validation logs, and rejected memory.
教练，我想训练 Skill。A local Agent Skill that trains unstable skill packages with bounded patches, human review, validation logs, and rejected memory.
npx add-skill nightboy87/anxi-skill教练，我想训练 Skill。A local Agent Skill that trains unstable skill packages with bounded patches, human review, validation logs, and rejected memory.
151 AI Agent Skills for the full product lifecycle. Compatible with Trae / Claude Code. 9 modules from discovery to launch to growth. | 151 个覆盖产品全生命周期的 AI Agent Skills，兼容 Trae / Claude Code，9 大模块从探索发现到上线增长。
Open-source security gateway for LLM APIs — prompt injection detection, PII redaction, dangerous response sanitization, and audit logging. OpenAI/Claude compatible, MCP & Agent SKILL support. Drop-in proxy for AI coding agents (Cursor, Claude Code, Codex).
Next-Gen AI-Aware Git. Auditable sandbox, prompt-aware commits, 95% less token waste, 3.5x richer PR brief, 1.8x faster multi-agent loops.
Recently updated agent skill repository: jiechen257/my-agent-skill.
Fast, language-abstracted idiom enforcement for AI coding agents and humans — teach via a generated skill, enforce via a sub-100ms autofixing gate. Rust core + Python/Node bindings.
Agent skill repository for Nagarjuna2997/ios-agent-skill.