remote-mac

Remote Macs: MacBooks, Mac Studios, hosted claw Macs, Tailscale, SSH, and OpenClaw.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/remote-mac/SKILL.md

Quality

Content

88%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.

The body is a highly actionable, well-sequenced operational runbook with concrete commands, explicit validation/approval checkpoints, and clean section structure; its main limitation is minor redundancy and the lack of any progressive file-splitting for a fairly long single-file skill.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational with no padding of concepts Claude already knows (e.g., no 'Tailscale is a mesh VPN' filler); minor redundancy exists in the repeated per-task-approval rule and 'do not confuse X with Y' disambiguations, fitting the 'efficient; minor instances that could be trimmed' anchor rather than the fully-lean anchor 5.	4 / 5
Actionability	It provides fully executable, copy-paste-ready commands with concrete hosts, paths, and ports (e.g., 'ssh -o RequestTTY=no -o RemoteCommand=none steipete@steipete-macstudio.local ...', 'lsof -nP -iTCP:18789 -sTCP:LISTEN', 'dns-sd -B _ssh._tcp local', 'peekaboo list windows --app "Jump Desktop" --json'), covering the common cases per anchor 5.	5 / 5
Workflow Clarity	The numbered Discovery workflow (steps 1-8) is clearly sequenced with explicit verification checkpoints (verify ComputerName/LocalHostName/hardware UUID, preserve a fallback before stopping a backend), and the destructive live-testing section enforces approval gates with feedback loops ('verify with a raw window screenshot before clicking', 'verify over SSH with bird check'), matching anchor 5.	5 / 5
Progressive Disclosure	The skill is a single well-organized file with clearly labeled sections (Topology, Discovery, SSH Rules, OpenClaw Checks, etc.) and clearly signaled pointers to the private manager source of truth, but at ~130 lines with all content inline and no bundle reference files to split into, it sits at anchor 4 ('good structure; minor organization gaps') rather than the one-level-deep-reference anchor 5.	4 / 5
	Total	18 / 20 Passed

Description

56%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.

The description identifies a clear, distinctive niche and surfaces several natural trigger terms, but it enumerates topics rather than actions and omits any 'Use when' trigger guidance, capping completeness and limiting specificity.

Suggestions

Rewrite as third-person action verbs with a trigger clause, e.g.: 'Connect to, inspect, and run commands on Peter's remote Macs over Tailscale and SSH, and operate OpenClaw gateways. Use when the user mentions MacBook, Mac Studio, clawmac, Tailscale, SSH, or asks to run/check something on one of Peter's Macs.'

Add the missing natural synonyms (e.g., 'Mac mini') and keep idiosyncratic names (clawmac, megaclaw, miniclaw) as secondary aliases so the primary trigger terms stay natural.

State concretely what the skill does (connect, inspect, configure, run OpenClaw checks) rather than only listing the entities it covers.

Dimension	Reasoning	Score
Specificity	The description ("Remote Macs: MacBooks, Mac Studios, hosted claw Macs, Tailscale, SSH, and OpenClaw.") names the domain and concrete entities but states zero actions — no verbs describing what the skill does, matching the 'names the domain but actions are minimal or generic' anchor rather than the entirely-vague anchor 1.	2 / 5
Completeness	It conveys a topical 'what' (the remote-Mac domain and technologies) but has no 'Use when...' clause or equivalent trigger guidance, so per the rubric cap it cannot exceed 3; it is not anchor 2 because the domain is clearly identified rather than vague.	3 / 5
Trigger Term Quality	It includes natural terms a user would say ("MacBooks", "Mac Studios", "Tailscale", "SSH") alongside the more idiosyncratic "claw Macs"/"OpenClaw" jargon; coverage is good with a few natural variants (e.g., "Mac mini") missing, fitting anchor 4 rather than the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The niche (Peter's named remote-Mac fleet with Tailscale/SSH/OpenClaw) is distinct with minimal conflict risk, but the description itself lacks explicit trigger phrasing and could marginally overlap a generic SSH/Tailscale skill, placing it just below the anchor-5 'clear niche with distinct triggers'.	4 / 5
	Total	13 / 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/remote-mac/SKILL.md
Commit: 92442a1

Reviewed: 2 days 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.