ai-coding-agents
Comprehensive guide for using Codex CLI (OpenAI) and Claude Code CLI (Anthropic) - AI-powered…
Run Tauri MCP-driven E2E checks for VMark. Use when asked to execute or update automated UI flows that must use Tauri MCP tools (not browser DevTools), or when validating behavior in a running desktop session.
$ npx -y skills add xiaolai/vmark --skill tauri-mcp-test-runner --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/tauri-mcp-test-runnerContext preview
The summary Claude sees to decide when to auto-load this skill.
Run Tauri MCP-driven E2E checks for VMark. Use when asked to execute or update automated UI flows that must use Tauri MCP tools (not browser DevTools), or when validating behavior in a running desktop session.
name: tauri-mcp-test-runner description: Run Tauri MCP-driven E2E checks for VMark. Use when asked to execute or update automated UI flows that must use Tauri MCP tools (not browser DevTools), or when validating behavior in a running desktop session.
Run VMark end-to-end UI flows using the Tauri MCP tools and summarize results.
1) Confirm the desktop app is running. If not, ask the user to start it. 2) Start MCP session via `mcp__tauri__tauri_driver_session` (action: `start`, port: `9223` or omit for default). 3) List windows (`mcp__tauri__tauri_manage_window` action: `list`) and pick the target window. 4) Execute test flows using the patterns in `references/flows.md`. 5) Capture logs when needed (`mcp__tauri__tauri_read_logs`) and stop the session when done. 6) Report results: passed/failed flows, errors, repro steps, and any follow-up fixes.
When using vmark MCP to insert content, it appears as an AI suggestion that must be **accepted with Enter** via tauri-mcp:
1. vmark: document_insert_at_cursor("text")
2. tauri: keyboard(action: "press", key: "Enter") # Accept
3. tauri: keyboard(action: "press", key: "Escape") # Dismiss follow-upThis pattern is required for all content insertion operations.
The Plain-Text Workspace Where Humans and AI Collaborate Free. Local-first. Format-aware. VMark is the plain-text workspace where humans and AI collaborate.
Repo: xiaolai/vmark
Comprehensive guide for using Codex CLI (OpenAI) and Claude Code CLI (Anthropic) - AI-powered…
Test-driven CSS design system modifications. Run checks before/after CSS changes to verify…
Build or update MCP server/client integrations for VMark. Use when configuring MCP servers,…
Discover, register, and verify MCP servers. Use when a user asks to…
Audit an implementation against a plan (dev-docs/plans/*). Use when a user asks to check for…
Verify a completed implementation against a plan by running gates and checking acceptance…