homelab-change-planner

Plans homelab infrastructure changes with pre-flight checks, rollback strategies, and impact analysis before any execution.

Quality

75%

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-change-planner/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.

A tight, well-structured instruction skill: a sequenced 9-step workflow with an approval gate and post-change verification, a concrete fill-in change-plan template, and clean one-level references to companion skills. The main improvements are an explicit failure-recovery step (post-check fails -> execute rollback), specifics for health verification, and trimming the Invocation section.

Suggestions

Add an explicit error-recovery step after Post-check, e.g., "If unhealthy: execute the rollback plan, re-verify, and stop" — the validate->fix->retry loop is currently only implicit.

Specify what the post-change health check entails (which services, what command or signal counts as healthy) so the verification is executable rather than directional.

Drop or trim the Invocation section — harness-specific invocation syntax is noise that spends tokens without adding operational guidance.

Dimension	Reasoning	Score
Conciseness	The body is lean and un-padded, but the Invocation section ("OpenCode / Codex", "Freebuff") is harness-specific noise that earns no tokens, and the Companion Skills list partially restates steps already numbered — efficient with minor trim, not every-token-earns-its-place.	4 / 5
Actionability	Concrete, executable guidance for an instruction-only skill: "Run `homelab-topology-mapper`", "Assign LOW / MEDIUM / HIGH based on reversibility and blast radius", plus a copy-paste change-plan template. Minor gaps: no specifics for the post-change health verification or what "Backup confirmed" entails.	4 / 5
Workflow Clarity	A clear 9-step sequence with explicit checkpoints ("Do not proceed without explicit user confirmation", "confirming each step before proceeding", "Verify services are healthy"). Not a 5 because the error-recovery loop is implicit — there is no explicit "if post-check fails, execute the rollback plan" step, which matters for destructive changes.	4 / 5
Progressive Disclosure	Under 50 lines with no bundle files needed; sections (Workflow, Template, Companion Skills, References) are well-organized and companion-skill references are one level deep and clearly signaled, matching the simple-skill guidance for a top score.	5 / 5
	Total	17 / 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.

A specific, well-scoped description naming the domain and three concrete capabilities in third person, but it lacks any explicit "when to use this" trigger guidance and natural trigger phrases users would actually say. Adding a Use-when clause with common synonyms would lift both completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g., "Use when planning changes to homelab servers, containers, VMs, or network config before executing them".

Include natural user phrasings/synonyms such as "server upgrade", "maintenance", "Proxmox", or "docker changes" so the skill triggers on how users actually ask.

Mention the approval-gate/execution behavior (plan first, execute only after confirmation) to further differentiate from companion skills like homelab-safe-ops.

Dimension	Reasoning	Score
Specificity	"Plans homelab infrastructure changes with pre-flight checks, rollback strategies, and impact analysis" lists three concrete named actions, matching the several-specific-actions anchor; not a 5 because the workflow's other capabilities (state snapshot, risk rating, approval gate) are omitted from the description.	4 / 5
Completeness	The "what" is clear (plans changes with pre-flight checks, rollback strategies, and impact analysis), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	"homelab", "infrastructure changes", "rollback", and "pre-flight checks" are relevant keywords, but common natural variations users would say ("server upgrade", "maintenance", "Proxmox", "container changes") are missing, matching the some-keywords-but-missing-synonyms anchor.	3 / 5
Distinctiveness Conflict Risk	"Homelab infrastructure changes" carves a recognizable niche with low conflict risk against generic skills, but closely related companion skills (e.g., homelab-safe-ops as a safety gate) create minor overlap, fitting the mostly-distinct anchor.	4 / 5
	Total	14 / 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-change-planner/SKILL.md
Commit: ff4471e

Reviewed: 2 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.