AI Agent Skills

Run the Anti-Autoresearch integrity-forensics sweep (span-anchored evidence ledger → GPT auditors propose findings → a rules-only reporter that lists every proposal with…

Have the Claude and GPT partners critique each other's answers across a configurable number of rounds (default 1) before converging on a synthesis. Use when the user wan…

Browser-automation agent for Chrome — natural-language tasks executed through native tool calling, scoped Skills, CDP keyboard control, and a confirm-before-act security…

Launch a Fable 5 Max 1M reviewer as a bb thread (default: /bb-subagents) to do a deep, neutral senior-developer review of the current work and report its findings back v…

Run both fable-review and gpt-review on the current work, then merge their findings, dedupe them, and triage which issues are real vs overthinking. Outputs one clear, co…

Claude Fable 5 as architect, GPT-5.5 Codex as builder, the repo as memory - a research-backed Claude Code skill for the cross-vendor agent loop

Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7%…

A virtual AI-based pit crew for Sim Racing. Use the latest GPT technology to create a real life like experience when out on the track.

Joplin (note-taking) assistant running a very intelligent system (GPT, Claude, Gemini, Ollama, Hugging Face)

Run Claude Code dynamic workflows on a local Codex (GPT) backend, plus an interactive run viewer

为 Claude Code 赋能多模态视觉能力，支持豆包、通义千问、GPT-4o 等模型，用于截图 / UI / 图表分析；适配 DeepSeek 等无视觉底座，搭配 browser-harness 可做前端布局自动化检查。