CtrlK
BlogDocsLog inGet started
Tessl Logo

ssh-doctor

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

65

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/ssh-doctor/SKILL.md
SKILL.md
Quality
Evals
Security

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.

A tight, highly actionable Mac SSH triage runbook with strong validation checkpoints and feedback loops on its one destructive operation; the only structural nit is that the OP Profile Block is somewhat off-core and the file is long enough that a split reference would help.

DimensionReasoningScore

Conciseness

Lean runbook of executable commands with minimal framing and no explanation of concepts Claude already knows; the only prose lines are symptom interpretations ('launchd accepted TCP but refused to spawn more sshd inetd copies') that earn their place.

5 / 5

Actionability

Copy-paste-ready bash throughout with concrete symptom-to-cause signatures (kex_exchange_identification -> 'Too many processes') and exact commands for baseline, config inspection, log queries, and the stale-session fix.

5 / 5

Workflow Clarity

Explicit validation-first decision tree ('loopback failure means server-side... loopback success plus remote failure means network/firewall'), sequenced gating ('Only after loopback works but remote fails' for firewall), and a destructive kill step gated by inspect -> kill TERM -> sleep -> re-check -> KILL only if blockers remain.

5 / 5

Progressive Disclosure

Well-organized single-file runbook with clear section headers and no nested references; scored 4 rather than 5 because at ~140 lines it exceeds the simple-skill bar and the OP Profile Block is tangential to core SSH triage and could live in its own reference.

4 / 5

Total

19

/

20

Passed

Description

58%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 names a concrete Mac SSH triage niche with specific failure modes, but relies on terse labels and omits the 'Use when...' trigger guidance that the body provides, capping completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause naming natural user phrases, e.g. 'Use when SSH connects then closes before auth, Remote Login is advertised but unusable, or stale sshd-session processes block logins on macOS.'

Include synonyms and file/process terms users say ('sshd', 'Mac', 'connection closed by remote host', 'Too many processes') to broaden trigger coverage.

Reframe the listed items as concrete actions ('diagnoses', 'clears', 'restarts') rather than bare labels to lift specificity toward comprehensive.

DimensionReasoningScore

Specificity

Quotes 'Remote Login, launchd sshd, pre-auth closes, stale sessions' — four concrete diagnostic targets rather than vague language, though the actions (triage/diagnose) are implicit rather than enumerated.

4 / 5

Completeness

Clear 'what' (SSH triage of named issues) but no 'when' trigger guidance in the description itself — per the guideline a missing 'Use when...' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Includes 'SSH', 'Remote Login', 'stale sessions' but is terse label-style phrasing; missing natural variations like 'Mac', 'sshd not working', 'connection closed', and the explicit 'Use when...' trigger lives in the body not the description.

3 / 5

Distinctiveness Conflict Risk

Targets a specific Mac SSH niche (launchd sshd, pre-auth closes) that is mostly distinct from general SSH skills; falls short of 5 only because the description lacks an explicit trigger phrase that would lock in the niche.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
steipete/agent-scripts
Reviewed

Table of Contents

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.