Ready to supercharge your AI agents?

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

Computer Use Bridge — measured AI agent skill | DecimalAI

stijnman/computer-use-bridge

SkillScore77Maintained

Bridges desktop automation to agent tool calls. Use when tasks need GUI inte raction, screen control, or user says computer use, desktop control. Trigger s: computer use, desktop control, click on screen, GUI automation.

by stijnman

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

Automatic

AI Engineer pack

decimalai skills pull stijnman-computer-use-bridge

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/stijnman-computer-use-bridge/SKILL.md

Raw file: /s/stijnman-computer-use-bridge/SKILL.md ↗ · machine-readable summary at /s/stijnman-computer-use-bridge.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 7d ago

Yes — +32% lift-43% tokens0% turns77% of whole cases pass with skill (17/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	161%	0%
case-03	✗→✓	▲ Improved	-3%	0%
case-05	✗→✓	▲ Improved	-55%	0%
case-09	✗→✓	▲ Improved	-53%	0%
case-11	✗→✓	▲ Improved	-76%	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 — 8/1/2026

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

stijnman / grok-custom-skills

.grok/skills/computer-use-bridge/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Computer Use Bridge

When to Use

User says computer use or task matches this capability
User says desktop control or task matches this capability
User says click on screen or task matches this capability
User says GUI automation or task matches this capability

Workflow

Confirm desktop environment and permissions.
Plan actions: click, type, navigate (minimal steps).
Execute via desktop-subagent-connector with screenshots.
Verify outcome visually; retry once on mismatch.

Integrations

desktop-subagent-connector
hitl-approver

Error Handling

| Failure | Response | |---------|----------| | Permission denied | Ask user to grant accessibility permissions. |

Gotchas

Destructive GUI actions require hitl-approver.

Example

Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.

Want to see if stijnman/computer-use-bridge 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.