Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Sundial Org/Desktop Mouse — measured AI agent skill | DecimalAI

sundial-org/desktop-mouse

NewSkillScoreMaintained

Local mouse control via ydotool wrapper

agent-toolingby sundial-org

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Personal Assistant pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/sundial-org-desktop-mouse/SKILL.md

decimalai skills pull sundial-org-desktop-mouse --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/sundial-org-desktop-mouse/SKILL.md https://app.decimal.ai/s/sundial-org-desktop-mouse/SKILL.md

Raw file: /s/sundial-org-desktop-mouse/SKILL.md ↗ · machine-readable summary at /s/sundial-org-desktop-mouse.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 2h ago

—-73% tokens0% turns9% of whole cases pass with skill (2/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-07	✗→✓	▲ Improved	-73%	0%
case-16	✗→✓	▲ Improved	90%	0%
case-17	✓→✗	▼ Worse	-36%	0%
case-20	✓→✗	▼ Worse	152%	0%
case-21	✓→✗	▼ Worse	-38%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

sundial-org / awesome-openclaw-skills

skills/desktop-mouse/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Skill contents

SKILL.md

When the user asks to move/click the mouse:

Use the exec tool with host=gateway.
ONLY run commands that start with: molt-mouse ...
Supported:
molt-mouse move <dx> <dy>
molt-mouse abs <x> <y>
molt-mouse click left|right|middle
molt-mouse click 0x40 # left button down (hold)
molt-mouse click 0x80 # left button up (release)
If numbers are missing/ambiguous, ask the user.

Want to see if sundial-org/desktop-mouse would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.