md2wechat

md2wechat 2.0.7 - Adds explicit intent routing between standard article drafts (`convert --draft`) and image-based posts (`create_image_post`) for correct publishing flows. - Introduces clear rules: requests for 小绿书, 图文笔记, newspic, or image-first posts are routed to `create_image_post`, not `convert --draft`, even if Markdown content exists. - Documents the usage of `--cover` (local path) vs `--cover-media-id` (reusable WeChat asset) in draft creation; clarifies they are not interchangeable with remote URLs. - Expands discovery and provider inspection guidelines, including image model selection using `providers show <name> --json`. - Strengthens agent and workflow guidance to enforce correct command family usage based on user intent.

- Adds support for `inspect` and `preview` commands to check article readiness, metadata, and generate standalone HTML previews before conversion. - Updates the workflow to recommend a confirm-first flow: `inspect` -> `preview` -> `convert` / `--draft`. - Clarifies distinctions between `preview`, `convert --preview`, and upload/draft operations. - Expands rules for draft behavior, flag handling, and preview/degraded confirmation flows. - Improves guidance for handling errors (e.g., `45004` on draft creation) and metadata resolution steps.

md2wechat 2.0.4 - Added documentation for `convert` command options: `-o`, `--title`, `--author`, and `--digest`. - Clarified article metadata resolution order and field limits for title, author, and digest. - Noted that creating a draft requires `--cover` and that digest is auto-generated if missing. - No code or implementation changes; documentation updates only.

**Expanded discovery and image generation features, improved config and workflow guidance.** - Discovery-first approach: emphasizes inspecting providers, themes, and prompts via live CLI before using them. - Updated and expanded command examples for conversion, image handling, draft creation, and writing/humanizing text. - Enhanced configuration instructions: covers multiple config sources and recommends validation before critical actions. - Encourages use of presets for cover and infographic images over manual prompt entry. - Updated metadata to reflect full install options via brew and go, and clarified required binaries and environment variables. - Added safety, config, and agent rules for transparent use and better error avoidance.

- Removed internal runtime management and wrapper logic; now relies on md2wechat CLI already being installed and available on PATH. - Removed references to the runtime lookup contract and related documentation. - Cleaned up installer instructions; only fixed-version OpenClaw installer ensures both skill and CLI installation. - Updated download metadata URLs to point to version 2.0.2 release assets. - Removed references/runtime.md and scripts/run.sh files from the repository.

- Updated all installation links in skill metadata to use version 2.0.1 resources. - Documentation now clarifies that the runtime must match the skill version and mismatched runtimes will be rejected. - Explicitly states that installing via `clawhub` does not provision the runtime—use fixed-version installers instead. - Improved transparency about runtime lookup, boundaries, and required configuration. - Workflow and usage instructions updated for clarity and accuracy.

md2wechat 2.0.0 – Major update for OpenClaw integration and simplified references - Refactored skill for OpenClaw platform integration, with metadata optimized for automatic installation and runtime lookup. - Reduced internal reference files and consolidated runtime contract into a single document (`references/runtime.md`). - Removed embedded documentation on style prompts, HTML guides, AI writing trace removal, and internal workflow; now relies on external runtime capabilities queries. - Updated description and skill manifest: now focuses on Markdown-to-WeChat conversion, image generation (cover, infographic), and draft creation. - Clarified environment variable usage (`WECHAT_APPID`, `WECHAT_SECRET`) and runtime boundaries—no silent downloads, fixed installer resources only. - Added detailed workflow and recommended commands for both capability discovery and primary tasks.

- Initial release of md2wechat skill. - Converts Markdown articles to WeChat Official Account HTML with inline CSS. - Supports fast API mode and beautiful themed AI mode (powered by Claude). - Features include writer style assistant, AI writing trace removal (humanizer), and draft uploading. - Integrates natural language prompts for image and article generation. - Offers configurable writing styles and visual themes for conversion. - Includes workflow checklist and detailed extraction/explanation steps for seamless publishing.