remote-mac

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

Quality

59%

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

71%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 dense, highly actionable operational runbook with concrete commands, a sequenced discovery workflow with checkpoints, and strong safety/approval gates for destructive operations. Its main weaknesses are inlined cached fleet state with time-sensitive dates that could be split into a reference file, and the absence of any skill bundle files.

Suggestions

Move the cached fleet inventory (IPs, hostnames, ticket numbers) out of SKILL.md into a references/ file (e.g. fleet.md), keeping only the live-discovery guidance and the pointer to computers.yaml inline; this improves both conciseness and progressive disclosure.

Isolate time-sensitive state (the 2026-08-01 outages, the 2026-08-05 rename) into a clearly labeled "Current incidents / stale entries" section so dated information does not penalize the evergreen guidance.

Consolidate the OpenClaw verification checks into one validate→fix→retry checklist so the workflow_clarity feedback loop is explicit in a single place.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and avoids explaining concepts Claude already knows (SSH, Tailscale, tmux), but the Topology section inlines a large amount of cached state (IPs, ticket numbers, dates like 2026-08-05 and 2026-08-01) that the doc itself says to override with live values, and time-sensitive dates are not isolated in a deprecated section. It is mostly efficient but could be tightened, matching the score-3 anchor.	3 / 5
Actionability	It provides copy-paste-ready, executable commands throughout — `tailscale status --json`, `ssh -o RequestTTY=no -o RemoteCommand=none HOST 'COMMAND'`, `dns-sd -B _ssh._tcp local`, `lsof -nP -iTCP:18789 -sTCP:LISTEN`, `peekaboo list windows --app "Jump Desktop" --json` — covering the common discovery, SSH, OpenClaw, and GUI-access cases, matching the score-5 anchor.	5 / 5
Workflow Clarity	The Discovery section is a clear numbered sequence (1–7) with explicit checkpoints ("If Mac Studio's live Tailscale node is offline ... stop") and fallback logic, and the healthy-shape checks provide verification for risky/destructive operations. It is not a 5 because validation is distributed across sections rather than presented as a single validate→fix→retry feedback loop with a checklist.	4 / 5
Progressive Disclosure	The body has well-organized section headers and signals the canonical external source of truth (computers.yaml, agents.yaml), but no skill bundle files exist and the detailed fleet inventory (hostnames, IPs, ticket numbers) is inlined in SKILL.md when it could live in a reference file. This matches the score-3 anchor: some structure, but content that should be separate is inline.	3 / 5
	Total	15 / 20 Passed

Description

47%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 but is essentially a noun list: it names the domain and entities without stating any actions and without any "Use when..." trigger guidance. It is distinctive and keyword-rich but incomplete as a capability statement.

Suggestions

Rewrite as a capability statement with verbs, e.g. "Connect to and manage Peter's remote Macs..." so the description states what the skill does, not just what it covers.

Add an explicit trigger clause: "Use when the user mentions MacBook, Mac Studio, clawmac, Tailscale, or asks to run/check something on one of Peter's Macs."

Fold in the key synonyms from the body (MacBook Pro, Mac mini, clawmac, foundationclaw) so the description's trigger coverage matches the body's.

Dimension	Reasoning	Score
Specificity	The description ("Remote Macs: MacBooks, Mac Studios, hosted claw Macs, Tailscale, SSH, and OpenClaw.") names the domain and several concrete entities but lists no actions at all — it is a noun list, not a capability statement. It is more specific than the score-1 "pure abstract language" anchor but lacks the action named in the score-3 anchor.	2 / 5
Completeness	It gives only a vague "what" (a domain/topic label with entity nouns) and has no "Use when..." trigger clause at all, fitting the score-2 anchor (vague what, no when). The missing trigger guidance caps completeness at 3 per the rubric, and this description sits below that cap.	2 / 5
Trigger Term Quality	It includes natural terms a user would actually say — "MacBooks", "Mac Studios", "Tailscale", "SSH" — giving good keyword coverage. It stops short of score 5 because it omits common synonyms/variations (e.g. "MacBook Pro", "Mac mini", "clawmac") that the body itself lists.	4 / 5
Distinctiveness Conflict Risk	The combination of "Remote Macs" with distinctive proper nouns (claw Macs, OpenClaw) carves a clear niche with minimal conflict risk. It is not a 5 because generic terms like "SSH" and "Tailscale" could overlap with broader remote-access skills.	4 / 5
	Total	12 / 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: dc4f583

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.