homelab-safe-ops

Encodes read-first, no-destroy-by-default safety constraints for all homelab automation.

Quality

66%

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/homelab-safe-ops/SKILL.md

Quality

Content

78%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 content is a well-organized, lean safety contract with concrete, actionable rules and explicit validation checkpoints for destructive operations, supported by clearly signaled references. Its only soft spot is minor framing verbosity and the absence of a strictly ordered workflow sequence.

Dimension	Reasoning	Score
Conciseness	The body is lean and does not explain concepts Claude already knows, but the opening framing ('standing safety contract ... always-on — load it at the start') and the three-line Invocation list are mild over-explanation that could be trimmed, keeping it just below a 5.	4 / 5
Actionability	Rules are concrete, specific behavioral directives — naming tools (Cloudflare Tunnel, WireGuard, Tailscale) and target skills (homelab-logbook, obsidian-homelab-logbook) — with only minor gaps such as no concrete logbook entry format or command.	4 / 5
Workflow Clarity	Although structured as a ruleset rather than an ordered multi-step sequence, it provides explicit validation checkpoints for destructive operations (read-before-write, confirm, backup-exists, test-in-staging) plus a stop-and-ask escalation loop; because validation is present, the destructive-cap-at-3 does not apply, but the lack of a strict ordered workflow prevents a 5.	4 / 5
Progressive Disclosure	At ~40 lines with no need for bundle files (references/ and scripts/ hold only .gitkeep), the skill is well-organized into clear sections with one-level-deep, clearly signaled references to companion skills and external docs, satisfying the under-50-lines exception.	5 / 5
	Total	17 / 20 Passed

Description

53%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 clearly conveys a focused homelab-safety niche and a couple of concrete constraints, but it lacks an explicit 'when to use' trigger and reads as a content description rather than a list of concrete actions. It sits at a solid mid-range score with distinctiveness as its strongest dimension.

Suggestions

Add an explicit 'Use when ...' trigger clause, e.g. 'Use when touching homelab infrastructure, VMs, containers, networking, storage, or services' to satisfy the completeness 'when' requirement.

Surface more natural trigger keywords and synonyms a user would actually say (VM, container, Proxmox, server, 'don't delete', 'be careful') to lift trigger_term_quality.

Reframe the verb from 'Encodes safety constraints' to concrete behavioral actions (e.g. 'Guards homelab operations with read-first and no-destroy-by-default rules') to improve specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('homelab automation') and two concrete constraints ('read-first', 'no-destroy-by-default'), but the verb 'Encodes ... safety constraints' describes the skill's nature rather than concrete actions Claude performs, so it does not reach the multi-action coverage of a 4.	3 / 5
Completeness	The 'what' is clear (encodes read-first, no-destroy safety constraints), but there is no 'Use when...' clause or explicit trigger; 'for all homelab automation' only weakly implies when, and the rubric caps completeness at 3 for missing explicit trigger guidance.	3 / 5
Trigger Term Quality	Relevant natural terms ('homelab', 'automation', 'safety') are present, but common variations and synonyms a user might say (VM, container, Proxmox, server, 'be careful') are missing, matching 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The 'homelab automation' safety niche is clearly distinct from unrelated skills, with only minor overlap risk against the closely related companion homelab skills (change-planner, logbook, topology-mapper) named in the body.	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: pvnkmnk/AgenticSelfHostSkills
Path: skills/homelab-safe-ops/SKILL.md
Commit: 0f62e6b

Reviewed: 4 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.