Skip to content
SkillCheatSheet Sign in

vm-lab

An AI agent skill from steipete/agent-scripts, scored 72 out of 100 by code.

72/ 100B

Code score by group

  • Spec20/20
  • Description2/20
  • Procedure8/15
  • Done criteria15/15
  • Resources9/10
  • Scripts8/8
  • Safety7/7
  • Upkeep3/5

It loses the most points in Description (18), the group that checks whether the description says what the skill does and when to use it.

What the author says it does

Parallels macOS VM lab: GUI automation, Peekaboo, TCC, Ghostty.

This is the description in the skill's own SKILL.md, written by its author, not by SkillCheatSheet.

Repository
steipete/agent-scripts
Folder
skills/vm-lab
License
MIT
GitHub stars
7,483
SKILL.md lines
183
Other files
3

Add vm-lab to your agent

npx skills add steipete/agent-scripts --skill vm-lab

The command uses the open skills CLI. A skill is instructions and scripts your agent will follow, so read it first: open the folder on GitHub at the commit that was scored.

Labelled for

More skills from steipete/agent-scripts

  1. codex-huge-context

    Codex 1M context: direct OpenAI Responses API inference, safe Astra/Sol/Terra/Luna input headroom, Keychain delivery, and Mac fleet rollout.

    71B
  2. maintainer-orchestrator

    Coordinate multiple maintainer issues, PRs, or repositories with bounded workers, serialized public actions, and clear owner decisions. Do not use for one issue or PR.

    70B
  3. github-deep-review

    GitHub deep review: bugs, PRs, best fix, stale-or-real, read code first.

    69C
  4. fleet-maintenance

    Mac fleet inventory and upkeep with full/worker profiles: collect installed apps and packages, compare desired versus observed state, audit local-account escrow references, update…

    68C
  5. project-structure

    Generate a single-file compressed symbol map of a TypeScript or Swift repository — files, exported symbols, typed signatures, plugin boundaries — sized to fit an LLM context windo…

    68C
  6. github-project-triage

    GitHub issue/PR triage: queues, CI, blockers, risk, proof, next actions.

    67C
  7. speaking

    Speaking ops: invites, keynotes, panels, Gmail/calendar, conferences.

    66C
  8. swiftui-liquid-glass

    SwiftUI Liquid Glass: implement, adopt, refactor, review correctness/perf/design.

    66C

All skills in steipete/agent-scripts

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.