Compose Page Blocks
Automattic/data-liberation-agent/skills/compose-page-blocks
ai-mlOfficial
Official Provider SkillView repo
Compose a single liberated page's WordPress block-editor markup from its rendered HTML and screenshot. Inputs are a sanitized HTML file, a desktop screenshot, the design-foundation tokens, the URL's archetype (page/post/product/etc.), and the source URL. Output is a string of valid block markup that round-trips through parse_blocks, uses theme tokens (no inlined hex colors), and contains only text drawn from the source HTML. Call per-page during the streaming watch loop after extraction has prod
Files4 files
SKILL.md103 lines
Loading editor…
Install
RecommendedOne command — your agent picks it up automatically.
Select an AI agent above to see the install command.
or
Manual Install
More stepsDownload the archive and add the files to your project manually.
Skill details
Versionv1.0.0
AuthorAutomattic
Categoryai-ml
Skill IDAutomattic/data-liberation-agent/skills/compose-page-blocks
Files4 files
Related skills
AdaptBuild a new platform adapter to extract content from an unsupported platform (Blogger, Ghost, Tumblr, etc.)Creating BlocksTemplates and guidelines for creating new WordPress blocks from scratch — load this before generating block filesCreating ThemesGuidelines for creating new WordPress block themes from scratch — load this before generating theme filesDesign FoundationsBuild a coherent design-foundation JSON from a liberated site — semantic color/typography/spacing roles with evidence trails. Consumes the partial scaffold produced by liberate_design_foundation_scaffold plus aggregate HTML/CSS analysis and representative rendered HTML; produces a complete design-foundation matching the schema. Call after liberation, before theme generation.Design QaVisual-QA loop run after replica theme install and content import. Captures replica screenshots, applies a hard responsiveness gate at 390px AND a hard per-section visual-parity gate (measured SectionParity records, verdict computed by buildRunReport), runs qualitative vision review of source/replica pairs, checks accessibility, and drives a per-section escalation ladder of fixes via editing-themes/editing-blocks/rebuild-section (R1 CSS → R2 spec-rebuild → R3 re-extract → R4a AI canonical-block DiagnoseDebug failed or low-quality extractions by analyzing logs, probing the source site, and identifying root causes