Hypothesis-driven debug mode for Claude Code, Codex, and other agent platforms. Instead of guessing fixes, the agent generates root cause hypotheses, instruments your code with targeted runtime logs, asks you to reproduce via structured choices, analyzes the evidence, applies a targeted fix, then cleans up all instrumentation automatically.
AI-powered video subtitle pipeline — extract audio, transcribe with Whisper, translate, and burn subtitles into videos. One-click install for Claude Code, Codex, Cursor & more.
Open-source agent skills for Claude Code, Codex, GitHub Copilot, and other coding agents: GPT-5.6-style rigor, delegation, linear probes, and self-evolving workflows.
Skill invocation runner: install an Agent Skill in a fresh fixture, invoke an agent harness headlessly, and report what actually reached the model, with transcript evidence.
A Claude skill for driving and verifying the Xcode 27 iOS Simulator without opening Device Hub: which tool to use for tap, screenshot, rotation and UI tree, and which ones report success but do nothing.