— · Apache-2.0
Systematically clarify intent, challenge assumptions, resolve contradictions, and align goals, constraints, risks, and success criteria.
— · Apache-2.0
The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.
v1.0.0 · Apache-2.0
CVE hunting harness for Claude Code - 20 skills, 5-agent team, systematic vulnerability research with false positive elimination
v1.2.4 · MIT
Claude Code Starter Kit CLI — scaffold Claude-ready projects in one command
— · Apache-2.0
Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.
— · MIT
A repository for skills that are essential to my daily work
— · MIT
a coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate
— · MIT
Collection of skills for Upstash
— · MIT
yoink is an AI agent that removes complex dependencies by reimplementing only what you need.
— · MIT
Local-first AI coding memory for AI agents. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.
— · MIT
An native MCP server extension for Ghidra
v1.0.26 · Apache-2.0
DeepSeek Harness Codex 跨平台桌面版,无需提前安装任何环境,开箱即用
— · Apache-2.0
电子发票整理与报销准备工具:从邮箱批量收集 PDF/OFD/XML 发票,OCR 识别、分类归档并生成 Excel 汇总;提供 Windows/macOS 桌面版与 DSH 插件。
v0.1.0 · MIT
Figma to design.md — Convert Figma design tokens into structured design.md for AI-assisted coding (Cursor, Claude Code, Copilot)
v0.2.0 · no license
一个微调美观的DeepSeek harness客户端(欢迎插件加入)
v0.4.1 · Apache-2.0
Synchronize and Orchestrate agents from CLI to GUI, across desktop to phone.
v1.0.0 · MIT
DSH 声音提醒 + 对话直达插件:多对话并行时,哪个对话有回复就出声提醒,点右上角卡片直达对应对话;切到别的应用时还有系统级通知(macOS 通知中心 / Windows toast),点击直达。当前对话当/当当(crisp 档),其他对话叮/叮叮(soft 档)。
— · MIT
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
v0.4.1 · MIT
Claude Code execution playbook with 3 pilot modes: cost-first (Haiku), quality-first (Sonnet), ceiling-elevation (Opus). Quantitative escalation gates.
— · MIT
Self-evolving skills lib for coding agents
— · MIT
Скилл для ИИ-агентов: находит и убирает следы машинной генерации из русского текста. 38 паттернов, 39 regex-маркеров с реестром доказательств, слепые парные прогоны, файловый слой снятия C2PA/EXIF/XMP. Пакет на PyPI и онлайн-демо | Russian AI-writing humanizer skill, PyPI: humanizer-ru, live demo
— · no license
竹知了 —— 一转就哇哇叫的传统玩具,Web 模拟版。零依赖单文件,真实录音采样,移动端优先。
v0.12.6 · MIT
Give AI coding agents live React and TanStack DevTools from the terminal. Inspect, optimize, test, and verify a running app.
— · no license
Token-efficient Claude Code workspace with parallel agents and persistent memory. Research → Plan → Implement → Validate workflow.