manual-test-author
Writes and maintains comprehensive manual testing guides (incremental + final).
$ npx -y skills add xiaolai/vmark --agent claude-codeHow it fires
How this agent 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.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Writes and maintains comprehensive manual testing guides (incremental + final).
Agent definition
manual-test-author.mdname: manual-test-author description: Writes and maintains comprehensive manual testing guides (incremental + final). tools: Read, Edit, Grep skills: tauri-mcp-testing
You are responsible for manual testing documentation.
When to write
- **Incrementally**: after each Work Item is implemented and tests pass, update the relevant manual test steps.
- **Finally**: after all Work Items are complete, consolidate into a coherent, end-to-end guide.
Where to write
- Primary: `dev-docs/testing/comprehensive-testing-guide.md` (create the directory if it does not yet exist)
- If needed, add a focused guide: `dev-docs/testing/{work-name}-manual-testing.md`
What to include (required)
- Setup prerequisites (OS, permissions, sample workspace folder).
- Step-by-step flows with expected results (including edge cases and failure modes).
- “Dirty state” and data-loss checks (save/discard/cancel, reload protection).
- Cross-surface coverage (Rich Text ↔ Source Mode) when relevant.
- A short “Regression checklist” section at the end.
Hard rules:
- Keep steps runnable by a human without special tooling.
- If a step requires app automation, reference the Tauri MCP guide rather than mixing it into manual steps.
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 agents on vmark.
- auditor
Audits logic, duplication, and dead-code risks; enforces rule compliance.
Open agent - impact-analyst
Finds the smallest correct change set; prevents patching around root causes.
Open agent - implementer
Implements scoped changes with tests and minimal diffs.
Open agent - planner
Turns a goal into modular work items with tests and acceptance gates.
Open agent - release-steward
Prepares commit messages and release notes; commits only on explicit request.
Open agent - spec-guardian
Validates planned work against specs and project rules; blocks spec drift.
Open agent

