Coding & Development

Zero-dependency CLI to install AI agent skills directly from any source. No marketplace, no registry, no signup — just point it at a local folder or a GitHub repo and it works. Works with opencode, claude-code, cursor, and all spec-compliant agents.

中文录音转写稿与逐字稿的扩展完整通顺整理 Codex Skill

Portable Agent Skills across Cursor, Claude Code, Claude Web & Cowork: validate, package, install, scaffold.

Codex skill for legal self-hosted Shadowrocket VPN deployment with sing-box, TLS/WebSocket, private subscriptions, and routing rules.

The headhunting firm for your AI agent skills — source, vet, place, and keep your skill library clean. 为 AI agent 物色/背调/落位并长期管理 skill 的"猎头公司"。

11 AI Professional Skills in Anthropic SKILL.md format. Train your AI with thinking frameworks, constraint systems & zero-defect quality gates. Works with Claude Code, Claude.ai & OpenAI Codex CLI. Free & open source.

Portable Agent Skills for using Allure Report as the evidence layer for test work

Agent skills and local tooling for game Destiny 2.

Find, vet, and install the right AI agent skill from a natural-language need.

World-class Codex Skill and MCP harness for orchestrating Claude Code workers through CCSwitch multi-model routing.

Unified Codex skill for prompt framing, question coaching, user style profiles, and skill routing

AI agent skill atlas for safer Arab/MENA payment and BNPL integrations.

Claude skill: single-name option income recommendations, SPX macro hedge sizing, IB execution with defined-risk guardrails，FCN private-bank quote defense

A curated marketplace of Claude Code skills focused on software engineering best practices.

Collection of Claude Code skills

Automated security risk scoring for OpenClaw AI Agent skill packages — detects dangerous system calls, evaluates maintainability, and flags suspicious publishers.

Portable phone-call Agent Skills, apps, examples, adapters, and scheduler recipes for AI agents.

197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% accuracy. RNA-seq, single-cell, drug discovery, proteomics, and more. Powers OmicsHorizon.

Evaluate LLMs the right way — confidence intervals, unbiased pass@k, significance testing, bias-controlled LLM-as-judge, contamination checks. A drop-in agent skill with a numpy stats core validated against ground truth.

Intraday gold-futures trading assistant — Al Brooks Price Action + SMC + Order Flow + Volume Profile. Auto-ingests live bars via TradingView webhook or an ATAS order-flow indicator, then emits structured trade calls. Ships as a plug-and-play Agent Skill for Claude Code / Codex / OpenClaw.

A reusable skill for fast, safe code cleanup, comment normalization, and trailing comment alignment. Works with Codex, VSCode agents, and OpenCode.

An agnostic cognitive architecture for LLM-based agents (SKILL).

AI plugin for coding standards for Go

Plan-only multi-model Fusion for Claude Code: Opus 4.8 + GPT-5.5 (Codex) answer in parallel, Opus judges into one executable PLAN. Mythos-tier judgment distilled into the subscriptions you already pay for.