ldzhouquan/agent-harness-skill
A systematic implementation of Harness Engineering, enabling agents to work in a stable, controllable, and verifiable environment. It shifts focus from "writing code" to "designing feedback loops".
A systematic implementation of Harness Engineering, enabling agents to work in a stable, controllable, and verifiable environment. It shifts focus from "writing code" to "designing feedback loops".
npx add-skill ldzhouquan/agent-harness-skillA systematic implementation of Harness Engineering, enabling agents to work in a stable, controllable, and verifiable environment. It shifts focus from "writing code" to "designing feedback loops".
Agent skill for editing PowerPoint speaker notes — rewrite, export, and modify PPTX notes. Works with Claude Code, OpenClaw, and any AI agent.
X (Twitter) Content Creator Agent Team — Claude Code skill. 4-agent pipeline: Trend Researcher → Creator Manager → Critical Agent (max 5 rounds) → Layout Agent
Codex skill for document deconstruction to editable launch-quality PowerPoint decks
A Codex skill for WeChat Official Account writing, editing, and formatting.
Repo-local Markdown knowledge layer and Codex skills for durable LLM project context.
Automate Emaillistverify tasks via Rube MCP (Composio). Always search tools first for current schemas.