CtrlK
BlogDocsLog inGet started
Tessl Logo

homelab-change-control

Control consequential homelab changes with explicit scope, observed-state evidence, approval, rollback, and non-secret records. Use before changing guests, services, storage, networking, access, backups, monitoring, or secrets.

69

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 tightly written, well-sequenced change-control gate with explicit validation checkpoints and gate checklists appropriate for destructive homelab work. The main gap is the absence of any concrete executable commands or worked examples, which limits actionability and leaves the error-recovery loop slightly implicit.

Suggestions

Add one or two concrete executable command examples (e.g. a read-only Proxmox inspection command used to 'observe current state') so the guidance is copy-paste ready rather than purely procedural.

Make the error-recovery feedback loop explicit after "stop on parameter drift, unexpected output, or a missing precondition" — state what to do next (re-classify, re-confirm facts, or re-request approval) rather than only halting.

DimensionReasoningScore

Conciseness

The body is lean and dense with no padding or explanations of concepts Claude already knows; every section (Purpose, Classify, Readiness Gate, Approval Gate, Execution and Evidence, Scenario, Routing) earns its tokens.

5 / 5

Actionability

Concrete process guidance is present — the Approval Gate enumerates exact fields (target, parameters, data placement, network/access effect, excluded workloads, rollback boundary, start/autostart) and the Representative Scenario is specific — but as an instruction-only skill it lacks any executable commands or worked command examples, leaving minor gaps.

4 / 5

Workflow Clarity

A clear Classify → Readiness Gate → Approval Gate → Execution sequence with explicit validation ("Validate the exact success condition and protected-resource non-interference"), gate checklists, and rollback re-approval; validation is present so the destructive-operation cap does not apply, but the "stop on parameter drift" halt is less explicit than a fix-and-revalidate feedback loop.

4 / 5

Progressive Disclosure

At roughly 50 lines with no need for bundle files, the content is well organized into clear sections and the Routing section gives well-signaled, one-level-deep pointers to sibling skills, satisfying the simple-skill exception for progressive disclosure.

5 / 5

Total

18

/

20

Passed

Description

83%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 strong, well-structured description that clearly states both capability and trigger conditions in third person. It is held back from a perfect score by an abstract primary verb and a trigger list that lacks synonyms and overlaps with sibling homelab skills.

DimensionReasoningScore

Specificity

Lists several concrete control mechanisms ("explicit scope, observed-state evidence, approval, rollback, and non-secret records"), but the umbrella verb "Control" is abstract and these read as required artifacts rather than discrete executable actions, so it stops short of comprehensive coverage.

4 / 5

Completeness

It explicitly answers both what ("Control consequential homelab changes with explicit scope, observed-state evidence, approval, rollback, and non-secret records") and when ("Use before changing guests, services, storage, networking, access, backups, monitoring, or secrets") with concrete trigger phrases in third-person voice.

5 / 5

Trigger Term Quality

"changing guests, services, storage, networking, access, backups, monitoring, or secrets" gives good natural domain keyword coverage across seven categories, but it lacks synonyms or common variations users might also say.

4 / 5

Distinctiveness Conflict Risk

The "consequential homelab changes" niche is clear and distinct, but the broad seven-category trigger list overlaps with closely related sibling skills (e.g. homelab-safe-ops, homelab-change-planner) referenced in the body, leaving minor conflict risk.

4 / 5

Total

17

/

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
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.