CtrlK
BlogDocsLog inGet started
Tessl Logo

homelab-topology-mapper

Maps Proxmox cluster topology including nodes, VMs, containers, storage, and network layout.

56

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/homelab-topology-mapper/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 has a clear sequenced workflow and a concrete output format, but the dated baseline section bloats the skill with snapshot data that belongs in a reference file, and no step provides executable commands or MCP tool invocations. Moving the baseline out and adding concrete API/MCP calls would substantially raise quality.

Suggestions

Move the 'Verified Baseline (2026-09-18)' table into a reference file (e.g. references/baseline.md), keeping only a one-line pointer plus 're-enumerate before acting' in the body.

Add concrete executable guidance for each step, e.g. the actual MCP tool calls or pvesh/API endpoints (GET /nodes, /nodes/{node}/qemu, /nodes/{node}/lxc) instead of prose directives.

Add an explicit validation step, such as cross-checking the fresh enumeration against the stored baseline and flagging drift before declaring the topology current.

DimensionReasoningScore

Conciseness

The workflow steps and output format are lean, but the 'Verified Baseline (2026-09-18)' section inlines dated, version-pinned environment detail (PVE 9.2.11, IP addresses, tailnet members, router DNS behavior, rollback snapshot name) that duplicates external docs the body itself cites; time-sensitive info outside a deprecated section is penalized, matching the 'mostly efficient but could be tightened' anchor rather than the minor-trim anchor at 4.

3 / 5

Actionability

Steps specify the exact auth source (mcp/proxmox-mcp.json), the exact fields to collect per object, and a concrete output table, but contain no executable commands or API calls (no pvesh endpoints, no MCP tool invocations), fitting 'some concrete guidance but incomplete' rather than the mostly-executable anchor at 4.

3 / 5

Workflow Clarity

Eight numbered, unambiguously sequenced steps cover connect through optional store, and the read-only nature means the destructive/batch validation cap does not apply; the baseline table serves as an implicit sanity check, but there is no explicit cross-check step or error handling for failures like bad auth, matching 'clear sequence with minor validation gaps' rather than 5.

4 / 5

Progressive Disclosure

Sections are well-labeled, but the bundle directories are empty and the ~60-line body inlines a dated baseline/reference table that clearly belongs in a separate file (the body itself points to docs/observed-state.md and docs/network-map.md in an external repo), matching the 'content that should be separate is inline' anchor.

3 / 5

Total

13

/

20

Passed

Description

70%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 tight, domain-specific description that clearly states what it does and over which objects, but it entirely lacks a 'when to use' trigger clause, which both caps completeness and weakens its discoverability. Adding a 'Use when...' sentence would lift it into the top tier.

Suggestions

Append a trigger clause such as 'Use when the user asks about their Proxmox/homelab cluster, wants a current inventory of VMs or containers, or needs pre-change context for the cluster.'

Include natural synonyms users would say — LXC, CT, homelab, 'cluster inventory' — to broaden trigger term coverage.

Mention the output form (structured Markdown snapshot) in the description so users know what artifact to expect.

DimensionReasoningScore

Specificity

The description names the Proxmox domain and enumerates five specific object types ("nodes, VMs, containers, storage, and network layout"), matching the 'several specific actions with minor gaps' anchor; it falls short of 5 because it uses a single verb and omits output rendering/storage.

4 / 5

Completeness

A clear 'what' is present but there is no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3; the 'what' is concrete so it does not fall to 2.

3 / 5

Trigger Term Quality

Strong natural keywords anchored on 'Proxmox', 'cluster', 'VMs', 'containers', and 'network layout', but common variations users would say (LXC, CT, homelab, inventory) are missing, matching the 'good coverage, a few natural terms missing' anchor.

4 / 5

Distinctiveness Conflict Risk

'Proxmox cluster topology' carves out a clear niche with minimal conflict risk against generic skills and even against its companion skills (change-planner, safe-ops) which serve different intents.

5 / 5

Total

16

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
pvnkmnk/AgenticSelfHostSkills
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.