AI Agent Skills

a delightful machine learning tool that allows you to train, test, and use models without writing code

The Software Factory

How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv…

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinemen…

Seedance 2.0 prompt skill，使用该Skill生成Seedance 2.0 视频提示词

The Security Toolkit for LLM Interactions

DEPRECATED: Like diff but for PostgreSQL schemas

Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate, LanceDB).

The Loop Engine for Claude Code — engineer the loop, not the prompt. 1 router · 9 agents · 16 skills · 4 workflows. Fail-closed gates, test honesty, anti-anchored review.

Plan, execute, and document validation, verification, and transfer of analytical procedures under the governing framework - ICH Q2(R2) and Q14, USP <1220>/<1225>/<1226>,…

Rust task runner and build tool.

Infect Any Android Device With Virus From Link In Termux

A beautiful and useful low-latency prompt for your shell, written in go

Open source Agentic Development Environment (ADE): a hackable desktop workbench for coding agents.

Multi-agent autonomous SDLC framework. Spec to deployed app. PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers, 11 quality gates.

面向 Claude Code、Codex 等 AI 编码助手的 Hook 与 Agent Skill 开源合集。