ssh-doctor

SSH triage: Remote Login, launchd sshd, pre-auth closes, stale sessions.

Quality

91%

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

100%

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

A tight, command-driven triage skill with explicit decision logic and validation around its one destructive batch operation. It assumes Claude's competence and stays actionable throughout.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely executable commands with minimal connecting prose and no explanation of concepts Claude already knows; every section earns its tokens.	3 / 3
Actionability	It provides concrete, copy-paste-ready bash throughout (baseline, config, logs, kill sequences) rather than pseudocode or abstract direction.	3 / 3
Workflow Clarity	A clear diagnostic branch ('Validate locally first: loopback failure means…; loopback success plus remote failure means…') with explicit validation checkpoints, and the destructive stale-session kill is gated by 'Inspect first', re-check after TERM, and ownership re-check before KILL.	3 / 3
Progressive Disclosure	A single-purpose diagnostic skill with no external references needed, organized into clear labeled sections (Rules, Baseline, Config, Logs, Stale Fix, Firewall, Closeout); per the simple-skills note, well-organized sections score 3 without bundle files.	3 / 3
	Total	12 / 12 Passed

Description

82%

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 specific, distinctive description with strong natural trigger terms, weakened only by the absence of an explicit 'Use when…' usage clause in the frontmatter. The what is clear; the when is only implied.

Suggestions

Add an explicit 'Use when…' clause to the description, e.g. 'Use when SSH connects then closes before auth, Remote Login is advertised but unusable, or Mac SSH sessions go stale.'

Consider phrasing capabilities as verbs (diagnose, restart, clear) to make the actions even more concrete alongside the symptom list.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete scenarios — 'Remote Login, launchd sshd, pre-auth closes, stale sessions' — rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly states what the skill does (SSH triage across named scenarios) but the frontmatter description lacks a 'Use when…' clause or equivalent explicit trigger guidance, capping completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	It includes natural terms a user would say ('SSH triage', 'Remote Login', 'stale sessions') alongside the macOS-specific technical triggers, giving good coverage.	3 / 3
Distinctiveness Conflict Risk	The macOS SSH-diagnosis niche ('launchd sshd', 'Remote Login', 'sshd-session') is distinct and unlikely to trigger for unrelated skills.	3 / 3
	Total	11 / 12 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/ssh-doctor/SKILL.md
Commit: bb36883

Reviewed: about 13 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.