Md2wechat
Run the md2wechat CLI to turn Markdown into WeChat Official Account HTML, previews, drafts, image posts, covers, and humanized creator-style copy.
Overview
md2wechat is an agent skill most often used in Launch (also Grow content workflows) that drives the md2wechat CLI for WeChat article HTML, drafts, image posts, covers, and humanized writing.
Install
npx skills add https://github.com/geekjourneyx/md2wechat-skill --skill md2wechatWhat is this skill?
- Intent routing: standard articles via inspect/preview/convert versus image posts via create_image_post (not convert --dr
- Discovery-first workflow—list providers, themes, prompts, and layouts via CLI before guessing
- Bundled generate_cover and generate_infographic presets over raw generate_image when they fit
- write and humanize for creator-style drafting and AI trace removal
- Explicit split between convert --draft and create_image_post as different WeChat publish targets
- Five intent families: standard article (inspect/preview/convert), image post, cover/infographic generation, write/humani
Adoption & trust: 1.9k installs on skills.sh; 2.8k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have Markdown or rough AI copy but no reliable path to WeChat-formatted HTML, previews, drafts, or image-note posts without hand-fixing platform quirks.
Who is it for?
Indie creators and small SaaS teams distributing technical or product content on WeChat Official Accounts from a Markdown-first repo.
Skip if: Builders with no WeChat publishing need or those who want a one-click skill with zero local CLI install.
When should I use this skill?
User wants WeChat article formatting, preview, draft upload, image generation, cover or infographic generation, image-post creation, writer-style drafting, AI trace removal, or discovery of md2wechat providers and themes
What do I get? / Deliverables
You get inspected metadata, previewed layout, converted HTML or image posts, and optional draft upload after discovery-backed command choices.
- WeChat-ready HTML or image-post assets
- Preview output and optional platform draft
- Humanized or style-matched article text
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Launch → distribution because the skill’s core outcome is publishing and formatting for WeChat’s reader ecosystem. Commands target article convert/preview, draft upload, image-post creation, and discovery of publish presets—not app codebase changes.
Where it fits
Convert a shipped-feature Markdown post to WeChat HTML and upload a draft after preview passes.
Regenerate a cover and infographic for a repurposed tutorial using bundled generate_cover presets.
Run humanize on a newsletter draft before the weekly WeChat push.
Inspect theme and layout modules while standardizing internal release notes for external WeChat syndication.
How it compares
Platform-specific WeChat CLI orchestration—not generic static-site or Substack Markdown export.
Common Questions / FAQ
Who is md2wechat for?
Solo builders and marketers who publish on WeChat Official Accounts and want their agent to run md2wechat commands instead of manual paste-and-fix workflows.
When should I use md2wechat?
At Launch for article convert, preview, and draft upload; in Grow when refreshing content, covers, infographics, image posts, or humanized rewrites; whenever the user mentions WeChat article formatting or md2wechat.
Is md2wechat safe to install?
The skill instructs CLI use that may touch network APIs and local files; review the Security Audits panel on this Prism page and project docs before running convert or draft commands with production credentials.
SKILL.md
READMESKILL.md - Md2wechat
# md2wechat Use this skill to operate the `md2wechat` CLI. Keep the skill focused on execution decisions. For full command tutorials, installation details, and FAQ-level explanations, refer users to the project docs instead of expanding this runtime protocol. ## Intent Routing Choose the command family before taking any publish or generation action: - Standard article HTML, article preview, metadata inspection, or WeChat article draft: use `inspect`, `preview`, and `convert`. - Image-first post, image note, image-text note, `newspic`, or multi-image post: use `create_image_post`, not `convert --draft`. - Article cover or article infographic: prefer `generate_cover` or `generate_infographic` over raw `generate_image` when a bundled preset fits. - Writing in a creator style or removing AI traces: use `write` or `humanize`. - Provider, theme, prompt, or layout uncertainty: run discovery first. Do not guess from memory or repository files. Treat `convert --draft` and `create_image_post` as different publish targets, not interchangeable variants. ## Discovery First Use CLI discovery as the source of truth, but keep it scoped to the next decision. Do not run the full catalog for tasks that do not need provider, theme, prompt, or layout selection. Run the smallest useful discovery set: - Article formatting with no theme or modules chosen: ```bash md2wechat themes list --json md2wechat layout list --json ``` - A named theme, provider, prompt, or layout module: ```bash md2wechat themes show <name> --json md2wechat providers show <name> --json md2wechat prompts show <name> --kind <kind> --json md2wechat layout show <name> --json ``` - Image generation or image-preset selection: ```bash md2wechat providers list --json md2wechat prompts list --kind image --json ``` - Draft, upload, API local-readiness, or configuration troubleshooting: ```bash md2wechat doctor --json md2wechat config show --format json ``` `doctor` readiness is local configuration attemptability. Use `inspect --json` for article-specific target readiness. - Unknown CLI version, changed behavior, or capability uncertainty: ```bash md2wechat version --json md2wechat capabilities --json ``` For simple local actions such as `preview`, `humanize`, or a user-specified command with explicit flags, do not run unrelated provider, theme, prompt, or layout discovery. Inspect specific resources only when the task needs them: ```bash md2wechat providers show <name> --json md2wechat themes show <name> --json md2wechat prompts show <name> --kind <kind> --json md2wechat layout show <name> --json ``` Use CLI output as the source of truth for currently available modes, providers, themes, prompts, and layout modules. ## Configuration Boundaries - Assume `md2wechat` is already available on `PATH`. - `convert` defaults to API mode unless the user explicitly asks for `--mode ai`. - API conversion requires md2wechat API credentials. - WeChat draft creation requires WeChat credentials. - Image generation may require image-provider credentials. - `doctor --json` is local-only: it checks local readiness and does not perform live authentication, upload images, or create drafts. - Use `config show --format json` when the user asks what configuration is currently effective. ## Article Workflow Prefer a confirm-first workflow for article work: 1. `md2wechat inspect <article.md> --json` 2. `md2wechat preview <article.md>` 3. `md2wechat convert <article.md> ...` 4. Add `--upload`, `--draft`, `--cover`, or `--cover-media-id` only when the user explici