ai.spideriq/publish

List available pre-built themes.

Render a template with mock data and return the HTML output.

Update template config: theme, route overrides, settings, or data sources.

Create or update a Liquid template. Provide the FULL Liquid template source code. The `path` param is the file path under the client's theme (e.g. 'templates/default.liquid', 'layout/theme.liquid', 'snippets/post-card.liquid'). It is a FILENAME, not a slug or shorthand — passing 'form' or 'page' as `path` will store garbage that no template-lookup path consults. Customizing form-page chrome at /f/<flow_id>: override 'templates/forms-standalone.liquid' (NOT 'templates/form.liquid', which is unused). Same for booking pages: 'templates/booking-standalone.liquid'. Both extend layout/theme.liquid, so a layout override applies to page + form + booking chrome together. To target form pages from inside layout/theme.liquid use `{% if template == 'forms-standalone' %}` (the Liquid `template` variable mirrors the file's basename, NOT a short name like 'form'). Phase 11+12 Lock 4 gate is opt-in via dry_run/confirm_token.

Upload all matching files from a local directory to SpiderMedia. Walks the directory (recursive), sniffs content-type, uploads in a single /media/upload-batch request (up to 500 MB total for general folders, 20 MB for scroll-sequences/*). Returns {uploaded: [...], failed: [...], warnings}. Scroll-sequence workflow: - Default folder rule: if `folder` starts with "scroll-sequences/", the tool auto-enables both `auto_optimize=true` (Sharp → WebP q75, max 1920px) and `preserve_filename=true` (so frame_0001.webp lands at frame_0001.webp). - Override with explicit flags if needed. Filtering: pass `pattern` as a simple glob (e.g. "frame_*.webp") to filter the dir; default is all allowed extensions. Allowed: webp, jpg, jpeg, png, gif, pdf, mp4, webm, mov. Sharp is an optional peer dep. If missing, auto_optimize silently falls back to uploading originals (which may then hit server hard ceilings).

Upload a single local file to SpiderMedia. Reads the file from disk, sniffs content-type from the extension, and POSTs multipart to /dashboard/content/media/upload-batch. Server enforces weight policy (500 KB/file for scroll-sequences/*, 20 MB otherwise; video/* gets 500 MB). Returns {public_url, key, size, content_type}. Filenames: pass preserve_filename=true for deterministic storage keys (scroll-sequences that consume {base_url, pattern, count}). Default false keeps the legacy YYYYMMDD_HHMMSS_ prefix. Requires LLM11 SpiderMedia backend 2026-04-18+ when preserve_filename=true. Allowed extensions: webp, jpg, jpeg, png, gif, pdf, mp4, webm, mov.

Build a scroll-linked image-sequence hero from a video URL, end-to-end. One call replaces the 5-step recipe: upload video -> submit extract_frames -> poll -> build block -> update page. Extracts numbered WebP frames from the source video (ffmpeg, ~7x smaller than raw), uploads them to the client's SpiderMedia bucket with a deterministic pattern (frame_{0001..NNNN}.webp), then injects a 'sys-scroll-sequence' component block into the target page AS A DRAFT. **Never auto-publishes.** After this tool returns, call: 1. content_deploy_site_preview (review at preview-{hash}.sites.spideriq.ai) 2. content_deploy_site_production (with confirm_token) When to use: - Agent received "add a scroll-sequence hero from this video" request - Video is at a public URL (SpiderMedia, di-atomic, or public http/https) - Target page already exists (use content_create_page first if not) Frame-count strategies (pick one): - strategy='target_frames' + target_frames=N — exact N frames spread across full duration (most common) - strategy='fps' + fps=N — sample at N frames/second - strategy='duration_fps' + fps + duration_seconds — clip + sample Returns: manifest {base_url, pattern, count}, the inserted block JSON, and the new draft page version ID.