Mandatory final sanity check before commits/PRs - catches security vulnerabilities, logic errors, and bugs that slip through tests
Agents
Designing, evaluating, and shipping autonomous AI agents.
7603 posts
Agent skill for production-quality Manim animation workflows
Build a complete, secure SaaS end to end in Claude Code: prevention-first security (not audit), real Stripe payments (not just a catalog), a...
Click-to-annotate overlay for HTML prototypes. Glass UI + coral pins + inline notes. ClawHub: html-mark.
PR health assistant - monitors CI, triages review comments, fixes issues with systematic prevention. Uses gh CLI and gh-pr-review extension.
Claude Code skills that turn an AI agent into a meticulous QA engineer. Evidence or it didn't happen.
An open-source federated AI-agent strategy world inspired by the Three Kingdoms.** Build a city, watch AI agents grow, and let a new Three...
Evidence-based senior product designer skill for Claude Code — turns any UI/app build into research-driven, accessible, non-generic design....
Xcode-free iOS development with xtool - build SwiftPM apps on Linux, Windows, and macOS without Xcode
Parallel exploration of implementation approaches - implements multiple variants simultaneously and lets tests determine the winner
面向硬件产品PCB方案设计的AI Agent,Agent会自动帮你进行需求确认,实时分析国内外各类芯片技术方案,进行器件选型,下载datasheet,输出BOM表,计算...
Harness Engineering playbook — deterministic smoke/test/lint harness commands, strict architecture boundaries, entropy-control checks for au...