#skill

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

ThumbGate Pre-Action Checks derive rules from repeated failures, flag risky tool calls, hard-block detected secret leaks, and block matches in strict mode.

Situational awareness across Git repositories.

The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. Design-as-Code. Turn prompts into UI directly on the live canvas. A modern alternative to Pencil.

Audit skill against a 9 dimension framework - enhanced version of skill-validator

SuPi (Super Pi) is my curated extension stack for PI, I use in every project, shared in case they help you too. Bundling LSP, TreeSitter, Ask-User-Tool, context monitoring, and practical small extras.

Self-evolving skills lib for coding agents

No repository description published.

MindOS is a Human-AI Collaborative Mind System, where human thinks and agents act. Globally sync your mind for all agents: transparent, controllable, and evolving symbiotically.

End-to-end encrypted memory for AI agents — portable, yours forever.

deptrust is a CLI that checks package versions for known vulnerabilities across npm, PyPI, crates.io, Go modules, RubyGems, NuGet, Maven, Packagist, pub.dev, CocoaPods, Hex.pm, Hackage, GitHub Actions, and more. It runs locally as a CLI and as an MCP server, comes with a skill, and a hook.

MCP server that suggests repository-specific AI agent skills.

MCP server + CLI + Codex/Claude skill for embedded debugging via probe-rs or OpenOCD — ARM Cortex-M, RISC-V, and Xtensa (ESP32), with AI crash diagnosis

No repository description published.

This repository contains my public JavaScript/TypeScript packages published via npm (using Bun and/or npm).

Universal Code Navigator

Architecture diagrams that actually run, generated by AI agents