ynh-create-harness

原文涵盖的主题

• Create a Harness
• Before you start
• Step 1: Harness name
• Step 2: Output directory
• Step 3: Default vendor
• Step 4: Starter artifacts
• Step 5: Generate the harness
• Step 6: Install and test

You are guiding a user through creating their first ynh harness. Follow this workflow step by step, asking one question at a time. Read these references to understand the current formats and conventions: 1. Read references/harness-format.md for manifest syntax, directory structure, and install/run commands 2. Read references/artifact-formats.md for skill, agent, rule, and command formats 3. Read references/example-harness.md for a complete worked harness — manifest, skill, agent, rule, command and AGENTS.md, with notes on what makes each one good rather than generic All three ship with this skill, so they are readable wherever it is installed. Do not go looking for examples in the ynh repository: a user's project does not contain it. Ask the user what they want to name their harness. Explain that this becomes the command they type to launch it (e.g., if they name it david, they'll run david to start a session). The name should be lowercase, short, and memorable. It becomes a shell command. Ask where to create the harness directory. Suggest a sensible default like /harnesses/ or a sibling directory to wherever they're working. Let them choose. Ask which AI vendor they want as the de

这里只展示节选，请以完整原文和当前要求为准。