Ready to supercharge your AI agents?

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

Desktop Subagent Connector — measured AI agent skill | DecimalAI

stijnman/desktop-subagent-connector

SkillScore95Maintained

Spawns desktop subagents for isolated GUI or local tasks. Use when delegatin gscreen work or user says desktop subagent, spawn local agent. Triggers: des ktop subagent, spawn local agent, delegate desktop.

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-desktop-subagent-connector

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/stijnman-desktop-subagent-connector/SKILL.md

Raw file: /s/stijnman-desktop-subagent-connector/SKILL.md ↗ · machine-readable summary at /s/stijnman-desktop-subagent-connector.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 — +41% lift-49% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-09	✗→✓	▲ Improved	-57%	0%
case-04	✗→✓	▲ Improved	-40%	0%
case-01	✗→✓	▲ Improved	-44%	0%
case-02	✗→✓	▲ Improved	-24%	0%
case-03	✗→✓	▲ Improved	-12%	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/desktop-subagent-connector/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Desktop Subagent Connector

When to Use

User says desktop subagent or task matches this capability
User says spawn local agent or task matches this capability
User says delegate desktop or task matches this capability

Workflow

Define subagent scope and timeout.
Launch with minimal tool set for task.
Monitor progress; collect result artifact.
Terminate subagent; merge results to parent context.

Integrations

computer-use-bridge
multi-agent-coordinator

Error Handling

| Failure | Response | |---------|----------| | Subagent timeout | Return partial result; report stuck step. |

Gotchas

Subagents inherit safety rules including hitl-approver.

Example

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

Want to see if stijnman/desktop-subagent-connector 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.