/shortcut-audit
Audit keyboard shortcuts in VMark code vs dev docs. Use when asked to review, reconcile, or optimize shortcuts, or when updating shortcut documentation.
$ npx -y skills add xiaolai/vmark --skill shortcut-audit --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/shortcut-audit
Context preview
The summary Claude sees to decide when to auto-load this skill.
Audit keyboard shortcuts in VMark code vs dev docs. Use when asked to review, reconcile, or optimize shortcuts, or when updating shortcut documentation.
SKILL.md
shortcut-audit.SKILL.mdname: shortcut-audit description: Audit keyboard shortcuts in VMark code vs dev docs. Use when asked to review, reconcile, or optimize shortcuts, or when updating shortcut documentation.
Shortcut Audit
Overview
Compare shortcut definitions in code against documentation and report gaps or conflicts.
Workflow
1) Read docs:
- `website/guide/shortcuts.md` (primary, in repo)
- `dev-docs/shortcuts.md` (if present — not always created)
2) Scan code for shortcut sources (see `references/paths.md`). 3) Extract current shortcuts from code and map them to doc entries. 4) Report:
- Missing doc entries
- Docs that reference removed shortcuts
- OS-level conflicts or collisions
5) Propose updates and required tests if changes are requested.
Notes
- Confirm WYSIWYG and Source mode bindings separately.
- Prefer existing conventions in VMark unless told to redesign.
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
Other skills on vmark.
- /ai-coding-agents
Comprehensive guide for using Codex CLI (OpenAI) and Claude Code CLI (Anthropic) - AI-powered coding agents. Use when orchestrating CLI commands, automating tasks, configuring agents, or troubleshooting issues.
Open skill - /css-design-tdd
Test-driven CSS design system modifications. Run checks before/after CSS changes to verify token usage, variable definitions, fallbacks, and consistency. Use when modifying CSS tokens, fixing design inconsistencies, or auditing CSS architecture.
Open skill - /mcp-dev
Build or update MCP server/client integrations for VMark. Use when configuring MCP servers, adding MCP tools, or updating MCP-related docs and settings.
Open skill - /mcp-server-manager
Discover, register, and verify MCP servers. Use when a user asks to connect/add/install/remove an MCP server, or when you need to manage project MCP configuration.
Open skill - /plan-audit
Audit an implementation against a plan (dev-docs/plans/*). Use when a user asks to check for gaps, logic errors, or missing tests relative to a plan or Work Items.
Open skill - /plan-verify
Verify a completed implementation against a plan by running gates and checking acceptance criteria. Use when the user asks to verify work items or confirm completion.
Open skill