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 Homebrew/global packages, safely sync repos and Xcode, and report disk, service, backup, update, and security health.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

96%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exceptionally actionable, well-sequenced body with strong validation/feedback loops and lean token use, held back only slightly on progressive disclosure by inline policy and a buried reference pointer. Bundle files referenced in the body all exist.

Suggestions

Add a short '## References' section listing `references/fleet-schema.md` and the script bundle so deep-detail entry points are signalled in one navigable place.

Consider moving the long 'Desired state' requirement bullets into a reference file if the file grows further, keeping SKILL.md as orchestration overview.

Keep the validation checkpoints and feedback loops as-is — they are exemplary for a destructive/batch skill.

Dimension	Reasoning	Score
Conciseness	The body is dense with executable commands and policy and never explains concepts Claude already knows (no 'Homebrew is...', 'Git is...'); nearly every line encodes a concrete requirement or command, so tokens earn their place.	5 / 5
Actionability	Copy-paste-ready commands with real flags and paths throughout — `node .../fleet-profile.mjs collect`, `brew bundle check --verbose --file FILE`, `git -C "$repo" fetch --prune`, `scripts/*-audit.sh --live` — cover the common cases concretely.	5 / 5
Workflow Clarity	A numbered '## Run order' plus explicit validation checkpoints ('Recheck branch, upstream, Git locks, and active process cwd immediately before mutation') and feedback loops (fetch timeout → mark pending → continue; merge refusal → skip-local-overlap) satisfy the destructive/batch validation bar rather than hitting the cap at 3.	5 / 5
Progressive Disclosure	Good section structure and the executable logic is appropriately externalized into 13 real scripts plus `references/fleet-schema.md`, but the schema reference is buried in prose rather than a dedicated navigation section and a lot of policy detail is inlined in SKILL.md, leaving minor organization gaps.	4 / 5
	Total	19 / 20 Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, distinct description with comprehensive concrete actions, but it lacks an explicit 'Use when...' trigger clause, which caps completeness. Adding a natural trigger sentence would lift the weakest dimension.

Suggestions

Append an explicit trigger clause, e.g. 'Use when maintaining Peter's Mac fleet, reconciling desired vs observed software, or running scheduled fleet upkeep.'

Add a couple of natural synonyms users might say ('brew', 'software updates', 'laptop fleet') to broaden trigger-term coverage.

Keep the existing action list as-is — it is already comprehensive and concrete.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'collect installed apps and packages, compare desired versus observed state, audit local-account escrow references, update Homebrew/global packages, safely sync repos and Xcode, and report disk, service, backup, update, and security health' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	The 'what' is crystal clear, but there is no 'Use when...' clause or equivalent explicit trigger guidance; per the rubric's cap, a missing explicit 'when' caps completeness at 3 even with a strong 'what'.	3 / 5
Trigger Term Quality	Good natural-term coverage ('Mac fleet inventory', 'Homebrew', 'global packages', 'sync repos', 'Xcode', 'disk...health') that users managing a fleet would say, but missing some common synonyms (e.g. 'brew', 'software update') so it falls just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The 'Mac fleet inventory and upkeep with full/worker profiles' framing plus niche actions (escrow references, Octopool-style fleet invariants) define a clear, distinct niche with minimal conflict risk against other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: steipete/agent-scripts
Path: skills/fleet-maintenance/SKILL.md
Commit: efa3b2f

Reviewed: ~6 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.