Baoyu Cover Image

**Improved image backend auto-selection and runtime support:** - Added support for Cursor’s native GenerateImage tool, with correct aspect-ratio and output-path handling in prompts. - Refined Codex CLI integration: load backend invocation instructions and parameters from a new, dedicated reference file. - Updated backend selection logic prioritizing runtime-native tools (e.g., Codex, Cursor) before non-native backends. - Removed obsolete skill-card.md; added references/codex-imagegen.md with Codex CLI wrapper details. - Documentation clarifies backend selection flow and provides runtime-specific notes.

v2.0.0: rename baoyu-imagine→baoyu-image-gen and baoyu-image-cards→baoyu-xhs-images; cross-skill image-backend examples updated

Codex CLI (`codex exec`) support added for image generation: - Now supports Codex raster backend via `codex exec` (`codex-imagegen`) if no native `imagegen` skill is present but Codex CLI is available. - Documents command structure for invoking the Codex wrapper script, including absolute path requirements and error handling. - Clarifies image backend auto-selection order and fallback when multiple options exist. - No other logic or option changes.

## 1.117.2 - 2026-05-17 ### Documentation - `baoyu-cover-image`: ban programmatic text repair on generated bitmaps — disallow ImageMagick / Pillow / Canvas / SVG / HTML overlays to cover, rewrite, or replace title/subtitle text; regenerate from a corrected prompt or switch to a lower-text or no-title variant instead - `baoyu-article-illustrator`, `baoyu-comic`, `baoyu-image-cards`, `baoyu-xhs-images`, `baoyu-infographic`, `baoyu-slide-deck`: sync the same text-repair ban with skill-specific text categories (labels/captions, dialogue/sound effects, titles/body/tags, headings/data values, slide titles/bullets)

### Documentation - Image generation backend selection: emphasize Codex `imagegen` as the priority runtime-native tool (invoke via the `Skill` tool with `skill: "imagegen"`) and forbid SVG/HTML/canvas substitution when no raster backend can be resolved — fall through to asking the user instead of silently emitting code-based art. Updated in `docs/image-generation-tools.md` and inlined into `baoyu-article-illustrator`, `baoyu-comic`, `baoyu-cover-image`, `baoyu-image-cards`, `baoyu-infographic`, `baoyu-slide-deck`, and `baoyu-xhs-images`.

baoyu-cover-image 1.103.2 - Clarified user input tool selection with detailed fallback and batching rules in the documentation. - Documented new backend resolution order for image generation, including support for user override, saved preferences, and auto-selection logic. - Updated confirmation policy to align with new explicit/implicit confirmation rules and the --quick override. - Aligned configuration lookup priority and completed details for first-time setup and preference checking. - No functional changes to cover image parameters; changes focus on tool/interaction flexibility and documentation precision.

## 1.103.1 - 2026-04-13 ### Fixes - `baoyu-markdown-to-html`: decode HTML entities and strip tags from article summary - `baoyu-post-to-weibo`: decode HTML entities and strip tags from article summary

## 1.103.0 - 2026-04-12 ### Features - baoyu-diagram: add multi-diagram mode for article-wide diagram generation ### Fixes - baoyu-article-illustrator: prevent color names and hex codes from appearing as visible text in generated images - baoyu-cover-image: prevent color names and hex codes from appearing as visible text in generated images - baoyu-image-cards: prevent color names from appearing as visible text in generated images - baoyu-post-to-wechat: decode HTML entities and strip tags from article summary

## baoyu-cover-image 1.60.3 - Added new "macaron" color palette, increasing the total palettes from 10 to 11. - Updated documentation in SKILL.md and preferences/config/preferences-schema.md to include the new palette. - Expanded palette listings and sample options to feature "macaron" in all relevant references and tables. - Added a dedicated file: references/palettes/macaron.md describing the new palette. - Improved documentation consistency across references.

baoyu-cover-image 1.60.2 - Updated workflow for handling people in reference images: clarified support for `--ref` and model requirements. - Improved documentation in SKILL.md and references/workflow/reference-images.md regarding reference image analysis and description handling. - Adjusted decision table and instructions for reference images to reflect current model capabilities. - No interface or breaking command changes.

baoyu-cover-image v1.60.1 - Clarified workflow requirements for reference images containing people, including per-character descriptions and mandatory direct usage for accurate representation. - Updated confirmation flow: selection of options must use the AskUserQuestion tool for interactive, multi-question selection (not plain text tables). - Improved documentation to reflect stricter handling and formatting for reference images and interactive option selection in Step 2. - Refined instructions and requirements in reference/workflow/reference-images.md, workflow/prompt-template.md, and workflow/confirm-options.md.

## 1.60.0 - 2026-03-11 ### Features - `baoyu-url-to-markdown`: support reusing existing Chrome CDP instances and fix port detection order ### Fixes - `baoyu-post-to-x`: add missing `fs` import in x-article ### Refactor - Unify all CDP skills to use shared `baoyu-chrome-cdp` package with vendored copies - Simplify CLAUDE.md, move detailed documentation to `docs/` directory - Publish skills directly from synced vendor, removing separate artifact preparation step

baoyu-cover-image v1.56.1 - Major documentation update: new detailed SKILL.md covering usage, options, customization dimensions, file structure, and workflow. - Describes support for 5 core design dimensions (type, palette, rendering, text, mood), 10 color palettes, 7 rendering styles, and multiple aspect ratios. - Clear command options and presets for easy cover image generation with or without user confirmation. - Adds workflows for setup, content analysis, prompt creation, and generation with reference handling. - Expanded gallery and reference section links for each dimension and style.