skill-mila-iqia-skills-mila-base · by Install
$ agentstack add skill-mila-iqia-skills-mila-base ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-mila-iqia-skills-mila-base) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Mila Base: Shared Policies
This skill is loaded by other mila-* skills via the Skill tool. Apply its policies silently (no preamble to the user) when invoked this way. Do not invoke it in response to a direct user request.
Command execution
Whenever a terminal command is presented to the user, display it in a code block as usual. If the command can be run directly in the current shell — without SSH-ing into another machine and without pausing for interactive input — also ask:
> Would you like me to run this command for you?
If the user says yes, execute it using the Bash tool. If the user says no or does not respond, continue guiding them to run it themselves.
Do NOT offer to run:
- Commands that require an active SSH connection to another machine (e.g.,
commands shown as running on the cluster, inside the VSCode remote terminal, or via srun/sbatch).
- Interactive commands that pause for user input (e.g.,
mila init,
wsl --install, or any command that opens a wizard or prompt). These cannot run non-interactively via the Bash tool.
- If it is unclear whether a command is interactive, do not offer to run it.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mila-iqia
- Source: mila-iqia/skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.