AI Agent Skills

Reviews a supplied code path or diff for correctness, security, maintainability, and style without executing or modifying it

Harness engineering beginner tutorial, from 0 to 1

🛠️ Awesome tools & guides for harness engineering.

Turn any repo into an agent-ready workspace for Claude Code, Codex, Cursor, and other coding agents.

Harness Open Source is an end-to-end developer platform with Source Control Management, CI/CD Pipelines, Hosted Developer Environments, and Artifact Registries.

Browser Harness | Self-healing harness that enables LLMs to complete any task.

📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness…

Help your coding agents (Claude Code, Codex, Qoder, Cursor, and other coding agents) get better at getting better.

Runs DeepSeek Harness headlessly for bounded repository tasks. Use when the user asks to delegate analysis or implementation to DeepSeek Harness.

This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs, novelty gates, pru…

Reference guide for building new Omnigent harness integrations — covers SDK/subprocess harnesses and native harnesses as separate tracks, each with their own feature mat…

Harness Anything - AI agent control hub: WPS, MS Office, Zotero, Photoshop, 47 CLI commands, 27 academic skills, SVG-to-PPTX

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

Evaluation harness for Apodex-1.0 on public deep-research benchmarks.

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it…

Multi-Agent Harness for Production AI