Help us improve
Share bugs, ideas, or general feedback.
From ibr
Capture external design references — screenshot a URL, extract full HTML/CSS, or crawl a sitemap. Unified entry point wrapping existing IBR primitives.
npx claudepluginhub tyroneross/interface-built-right --plugin ibrHow this command is triggered — by the user, by Claude, or both
Slash command
/ibr:capture <url> [--mode=screenshot|extract|crawl] [--depth=1] [--max=10]The summary Claude sees in its command listing — used to decide when to auto-load this command
# /ibr:capture Capture a design reference from an external site and save to the current build's reference set. ## Modes ### screenshot (default) Calls the `ibr screenshot` MCP tool. Saves to `.ibr/references/<slug>.png`. ### extract Calls IBR's URL extraction (`src/extract.ts → extractInteractiveElements`). Writes: - `.ibr/references/<slug>.png` - `.ibr/references/<slug>.html` - `.ibr/references/<slug>.json` (elements + computed styles + CSS variables) ### crawl Calls `src/crawl.ts → discoverPages` with `maxPages` from `--max` (default 10). For each discovered page, captures a scree...
/captureDocuments a module, component, API, system, or technical topic by invoking the Archcore capture skill with the provided topic argument.
/captureCaptures decisions, learnings, patterns, context, tech-debt, or other memories to persistent storage with optional namespace, auto-detection, and interactive prompting.
/captureCaptures provided organizational context to encrypted memory with timestamp and domain metadata, embeds via envector tools, stores it, and confirms with a summary.
/captureCaptures a new memory to the mnemonic filesystem with required namespace and title, optional type (semantic/episodic/procedural), tags, scope (project/org), confidence, citations. Validates against ontology.
Share bugs, ideas, or general feedback.
Capture a design reference from an external site and save to the current build's reference set.
Calls the ibr screenshot MCP tool. Saves to .ibr/references/<slug>.png.
Calls IBR's URL extraction (src/extract.ts → extractInteractiveElements). Writes:
.ibr/references/<slug>.png.ibr/references/<slug>.html.ibr/references/<slug>.json (elements + computed styles + CSS variables)Calls src/crawl.ts → discoverPages with maxPages from --max (default 10). For each discovered page, captures a screenshot. Writes to .ibr/references/<slug>/pages/<n>.png and a manifest.json listing pages.
.ibr/builds/<currentTopic>/refs.json if invoked during an active build.ibr/references/ (global reference library)/ibr:capture https://mobbin.com/apps/something --mode=screenshot
/ibr:capture https://linear.app --mode=extract
/ibr:capture https://stripe.com --mode=crawl --max=8
--delay increase or --wait-for selector