engine-bootstraplisted

# Engine bootstrap Scaffold a new contextualizer in the current directory. Take a list of source URLs or local paths from the user, auto-detect the metadata the engine needs, stamp the matching template set into place, and exit with a 3-line message naming the next workflow to run. The user supplies sources. The engine fills in everything else. ## Installation layout A contextualizer is stamped as a self-contained Claude Code project skill at: ``` .claude/skills/<slug>-context/ ├── SKILL.md ├── verify.sh ├── research/ │ ├── source-paths.json │ └── .research-state.json └── references/ (created by /skill-engine:discover later) ``` `.claude/skills/<slug>-context/` is the **contextualizer root**. Every engine workflow (`discover`, `refresh`, `status`, `self-audit`, `new-reference`, `using-skill-engine`) resolves `research/...`, `references/...`, and `verify.sh` relative to this root. The user invokes slash commands from the project working directory (the parent of `.claude/`); the workflows locate the root themselves. ## Activation guard This skill assumes no contextualizer is installed under `.claude/skills/*-context/` yet. 1. From the project working directory, look for an existing contextualizer: ```bash find .claude/skills -mindepth 1 -maxdepth 1 -type d -name '*-context' 2>/dev/null ``` If any match is a non-empty directory, surface a one-line warning naming the path, list the files that would be overwritten, and pause for explicit confirma