Skip to content

docs(computer): document RDP mode in computer-automation skill#29

Merged
quanru merged 2 commits into
mainfrom
feat/computer-skill-rdp
May 13, 2026
Merged

docs(computer): document RDP mode in computer-automation skill#29
quanru merged 2 commits into
mainfrom
feat/computer-skill-rdp

Conversation

@quanru

@quanru quanru commented May 12, 2026

Copy link
Copy Markdown
Collaborator

Summary

  • Add a "Connect via RDP" subsection right after "Connect to Desktop" in skills/computer-automation/SKILL.md, with a minimal connect --host ... example and a complete option reference (--host, --port, --username, --password, --domain, --security-protocol, --ignore-certificate, --admin-session, --desktop-width, --desktop-height).
  • Document mode-specific behavior: --displayId / --headless are ignored under RDP, computer_list_displays keeps listing local displays, the helper binary requirement, and credential hygiene (use env vars, don't commit passwords).
  • Refresh the SKILL.md frontmatter description and triggers so phrases like "rdp", "remote desktop", "windows server", and "connect via rdp" route to this skill. Still inside the 1200-char budget (1017/1200 per scripts/check-skill-description-length.mjs).

Why

@midscene/computer now exposes RDP flags through connect (see web-infra-dev/midscene#2466). Without a matching skill doc, agents would not know that RDP mode exists or how to opt in, so this PR is the user-facing half of that change.

Test plan

  • node scripts/check-skill-description-length.mjs (all skills under limit, computer-automation at 1017/1200)
  • Visual review of the new "Connect via RDP" subsection

Add a dedicated "Connect via RDP" subsection that lists every RDP
flag exposed by `@midscene/computer@1 connect` (host, port, username,
password, domain, security-protocol, ignore-certificate, admin-session,
desktop-width, desktop-height), shows a minimum example, and calls out
mode-specific differences (displayId/list_displays semantics, helper
binary, credential hygiene). Update the SKILL.md description and
triggers so RDP/remote-desktop intents route to this skill.
After end-to-end CLI verification against a real RDP host, sharpen the
RDP section to reflect what users actually hit:

- Clarify `--desktop-width/--desktop-height` are requests, not guarantees;
  point at `listdisplays --host ...` to confirm the negotiated size.
- Distinguish `list_displays` (platform tool, local-only) from
  `listdisplays` (action tool, RDP-aware), so users know which to call
  in RDP mode.
- Document latency expectations per CLI invocation (~5 s cold start for
  non-AI commands; 8–20 s for `act`/`assert`/`tap --locate`).
- Add connect-failure diagnostics: first stderr line is the actionable
  error (`connect_failed: ERRCONNECT_*`); enumerate common causes and
  fixes.
- Remind callers that every subsequent CLI command must repeat the
  `--host/--username/--password` flags since each invocation is stateless.
@quanru
quanru merged commit 129f9a1 into main May 13, 2026
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants