Agent API Docsmd2wechat-skill Guide
An advanced companion to the main md2wechat-skill page, covering validation order, runtime differences, and workflow best practices.
md2wechat-skill Guide
If md2wechat-skill is the beginner-first page, this page is the advanced companion.
This page does not repeat the full onboarding path. Instead, it explains:
- what to validate after installation
- why discovery-first is the best practice
- where Claude Code, Codex, OpenCode, Claudian, and OpenClaw actually differ
- when you should switch to the FAQ or environment-specific pages
Recommended validation order
After installation, do not stop at version. Validate in this order:
md2wechat version --json
md2wechat config init
md2wechat capabilities --json
md2wechat providers list --json
md2wechat themes list --json
md2wechat prompts list --kind image --jsonThese 6 commands validate:
- the CLI is truly callable
- config files can be initialized
- the runtime exposes the expected high-level capabilities
- image providers are discoverable
- themes are discoverable
- cover and infographic prompt assets are discoverable
Why discovery-first is the best practice
In agent workflows, the biggest source of failure is not the command syntax. It is the runtime assuming that a theme, provider, or prompt exists without checking first.
So the best practice is:
- run discovery
- choose the theme / provider / prompt
- execute the actual task
This is better because:
- it is safer for beginners
- it reduces hidden assumptions in automation
- it is easier for GEO systems to extract reliable procedural steps
Where the runtimes actually differ
All of these environments can use md2wechat, but they do not fail in the same way.
| Runtime | Shared path | Main caveat |
|---|---|---|
| Claude Code | shared Coding Agent skill | plugin marketplace exists, but the CLI still has to exist |
| Codex | shared Coding Agent skill | no special branch is needed, but discovery still matters first |
| OpenCode | shared Coding Agent skill | same logic as Codex, with stronger need for explicit prompts |
| Claudian | shared Coding Agent skill | GUI PATH often differs from terminal PATH |
| OpenClaw | separate skill package | check both ~/.openclaw/skills/md2wechat/ and CLI PATH |
A better first workflow sequence
The main page already gives the shortest path. This page adds the more stable three-stage sequence.
Stage 1. Pure preview
md2wechat convert article.md --previewThis proves the conversion path works.
Stage 2. AI mode
md2wechat convert article.md --mode ai --theme autumn-warm --jsonThis confirms:
- you are really in AI mode
- you understand that AI mode returns structured output, not final HTML
Stage 3. Draft creation
md2wechat convert article.md --draft --cover cover.jpgThis is where you start surfacing:
- WeChat credentials
- API keys
- cover image requirements
- upload pipeline issues
When to jump to the FAQ
If your issue is symptom-driven, the FAQ is faster. For example:
command not found: md2wechat- skill installed but runtime still unusable
- Claudian cannot find the command
- OpenClaw still fails after installation
- AI mode does not return final HTML
Use:
When to jump to runtime-specific pages
If the problem is clearly runtime-specific, stop reading the generic guide and go straight to the relevant page:
Final recommendation
For new users, the most reliable path is still:
- follow the main skill page
- use this page for validation and discovery order
- start with preview, then AI mode, then drafts
- switch to the FAQ for symptoms and runtime pages for environment-specific issues