Ready to supercharge your AI agents?

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

Launch Cloud Claw Agent — measured AI agent skill | DecimalAI

internet-court/cloud-claw-launch-agent

SkillScore95Maintained

Use this skill when the user wants to launch a new AltClaw, OpenClaw, PicoClaw, or Ottie deployment through Cloud Claw. Covers the same user-facing fields and constraints exposed in the Cloud Claw UI, using the local altllm cloud-claw-* commands. Do NOT use for post-launch lifecycle tasks like start/stop/delete/logs; use cloud-claw-manage-vm.

DevOpsby internet-court

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

Automatic

AI Engineer pack

decimalai skills pull internet-court-cloud-claw-launch-agent

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/internet-court-cloud-claw-launch-agent/SKILL.md

Raw file: /s/internet-court-cloud-claw-launch-agent/SKILL.md ↗ · machine-readable summary at /s/internet-court-cloud-claw-launch-agent.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

Yes — +59% lift-40% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	25%	0%
case-02	✗→✓	▲ Improved	53%	0%
case-03	✗→✓	▲ Improved	48%	0%
case-11	✗→✓	▲ Improved	-62%	0%
case-07	✗→✓	▲ Improved	-37%	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

internet-court / internet-court-skill

vendored/altlayer/cloud-claw-launch-agent/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1Bundled 1 file

Skill contents

references/

SKILL.md

Launch Cloud Claw Agent

Use this skill for the new deployment workflow exposed in the Cloud Claw UI, via the local CLI commands in this repository.

The implementation source of truth is the sibling repository:

../cloud-claw

Shared Setup

> Before using this skill, read: > - ../_shared/cloud-claw-preflight.md > - ../_shared/cloud-claw-api-surface.md

Supported Agent Types

| Agent Type | Internal Value | User-facing Notes | |---|---|---| | OpenClaw | openclaw | paid-tier path, Telegram + web dashboard | | PicoClaw | picoclaw | Telegram-only | | Ottie | aintern | Telegram-only, self-evolving fork path |

Launch Rules

Use altllm cloud-claw-deploy.
Deployment name must match ^[a-z0-9-]+$ and max length 63.
agentType must be one of:
openclaw
picoclaw
aintern
picoclaw and aintern require TELEGRAM_BOT_TOKEN.
openclaw uses OPENCLAW_MODEL.
UI-supported OpenClaw model choices are:
altllm/altllm-standard
altllm/altllm-mega
The backend may inject an AltLLM API key automatically for the signed-in user.
Launch success depends on quota, free-slot availability, active credits, and payment state.

Reference

See references/cli-reference.md for payload examples and expected responses.

Want to see if internet-court/cloud-claw-launch-agent 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.