AI-Agent Skills for Claim-Driven Testing of Distributed Systems
By
shenli3514
If you only eat one bagel today, this is the bagel.
Summary
A GitHub repository (shenli/distributed-system-testing) provides two AI-agent skills for coding agents (like Claude Code, Codex, Copilot CLI, Cursor, Gemini) that design and run claim-driven tests for distributed and stateful systems. The skills produce a structured Markdown test plan and a findings report with 9-state verdicts and blame classification (SUT/harness/checker/environment). A human reviewer reads the two artifacts to decide whether to ship, without needing to re-run tests. The skills are plain SKILL.md files executed by the agent.
Key quotes
· 5 pulledTwo skills for AI coding agents that design and run claim-driven tests for distributed and stateful systems.
Together they produce a structured Markdown test plan and a findings report with 9-state verdicts and an explicit SUT / harness / checker / environment blame classification.
A reviewer reads the two artifacts and decides whether to ship; nothing else has to be re-run.
Works with Claude Code, Codex, Copilot CLI, Cursor, Gemini, or any agent that reads Markdown and runs shell.
The skills are plain SKILL.md files. The agent executes them; the plan and findings report are the output.
You might also wanna read
Agent Skills Directory: Cross-Platform Search for AI Agent Capabilities
The article presents a cross-platform directory for AI agent skills called 'Agent Skills' that aggregates over 100,000 skills across 30+ pla
Product Hunt·2mo ago
Stagent: A state-machine tool to keep Claude Code on track for long tasks
Stagent is a tool designed to solve the problem of Claude Code (and similar AI coding assistants) failing to complete long, multi-step tasks
Product Hunt·18d ago
Claude Code Launches Multi-Agent AI Code Review System for Bug Detection
Anthropic's Claude Code now offers a multi-agent AI code review system that analyzes pull requests to catch bugs, security issues, and logic
Product Hunt·3mo ago
Skilled: A Local Terminal Dashboard for Tracking AI Coding Skill Usage
Skilled is a terminal dashboard tool that aggregates and visualizes usage data for custom AI coding skills/agents across tools like Claude C
Product Hunt·13d ago
AI Skills Manager: Centralized Platform for Managing AI Agent Skills Across Coding Agents
AI Skills Manager is a desktop application that provides a centralized platform for managing AI agent skills across major coding agents, all
Product Hunt·2mo ago
Building a Personal AI Agent with Markdown-Based Skills and Local Models
The article describes a personal AI agent built on Pi that manages the author's inbox, calendar, deal pipeline, blog publishing, and researc
tomtunguz.com·2d ago