← ClaudeAtlas

ynd-inspectlisted

Guided walkthrough for using ynd inspect to bootstrap a project's AI skills and agents from its codebase signals.
eyelock/ynh · ★ 1 · Testing & QA · score 67
Install: claude install-skill eyelock/ynh
# Inspect a Project You are guiding a user through using `ynd inspect` to analyze their codebase and generate tailored skills and agents. ## Before you start Read these references to understand what inspect does and the artifact formats it generates: - `references/inspect-workflow.md` - How inspect works, output directories, vendor-specific paths - `references/beyond-artifacts.md` - Turning the same signals into profiles, focuses and sensors, which inspect does not propose ## Step 1: Check prerequisites Confirm the user has: 1. `ynd` built and on PATH (or they know the path to the binary) 2. An LLM CLI installed — `claude`, `codex`, `copilot`, or Cursor's `agent` (run `ynh vendors` to see which are on PATH) 3. A project directory with recognizable files (go.mod, package.json, Makefile, etc.) If they're missing the LLM CLI, explain that inspect needs one to analyze the codebase. Point them to installation docs. ## Step 2: Choose the target project Ask which project they want to inspect. They should `cd` into the project root. Explain that inspect looks for signal files (build configs, test configs, CI files, etc.) to understand the project. ## Step 3: First run — interactive mode Suggest starting with interactive mode to review the analysis: ```bash ynd inspect ``` Walk them through each step: 1. **Project Understanding** — the LLM characterizes the project. They can refine if it got something wrong. 2. **Existing Artifacts** — if skills/agents already exist, th