AI Agent Skills

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

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

Harness engineering beginner tutorial, from 0 to 1

让纯文本模型更好地做视觉任务的DeepSeek Harness插件：带意图的图片问答、长截图 OCR、UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, g…

🛠️ 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…

Rust multi‑backend OCR/VLM engine (DeepSeek‑OCR-1/2, PaddleOCR‑VL, DotsOCR) with DSQ quantization and an OpenAI‑compatible server & CLI – run locally without Python.

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

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.