Individual skill
lambda-gpu-cloud
Safely inspect and operate Lambda Cloud GPU instances through the documented Cloud API and SSH, with explicit approval before billable or destructive actions.
backend/cli/skills/cloud-compute/lambda-labs/SKILL.md
Source commit a08e0ad0ad3d6448123039ee4659163eb2e35d99
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 2, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 4,352
- Repository last updated
- Nov 6, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent Repository topic
- ai Repository topic
- bun Repository topic
- cli Repository topic
- llm Repository topic
- ml Repository topic
- open-source Repository topic
- research Repository topic
- science Repository topic
- ai-agent Repository topic
- infrastructure Declared skill tag
- gpu-cloud Declared skill tag
- lambda Declared skill tag
- cloud-api Declared skill tag
- ssh Declared skill tag
- devops Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Read excerpt
# Lambda Cloud
Use this skill for Lambda Cloud instance discovery and lifecycle planning. Do not invent a Lambda-native CLI: the supported automation contract used here is Lambda's documented HTTPS Cloud API.
## OpenScience credential boundary
- A key saved in **Customize > Compute > Lambda** is encrypted control-plane data. It is not exported into Bash, Task, notebooks, kernels, plugins, or MCP servers.
- Use `provider_compute` with `list_resources`, `resource_status`, or `list_availability` for live instance and capacity reads. `account` is the same reviewed instance-list request used by **Test connection**.
- **Test connection** must approve an administrator-managed, non-writable `curl` executable; the macOS system `/usr/bin/curl` satisfies that boundary. User-owned replacements are rejected.
- The bearer header is supplied to the approved `curl` over stdin, so the key is not placed in argv or a temporary file.
- OpenScience updates `last_used` only after the API returns success.
- Never print, log, persist, or put the key in a URL. The saved credential cannot launch, restart, terminate, or change resources; a generic shell is unauthenticated unless the user configured it separately.
## API contract