AD tonic-vm-check
🖥️ Instant VM health checks — no config needed after first run. Point it at any Docker-based Linux server and get a clean report covering CPU, memory, disk, all running containers (with live stats), MySQL/Postgres database sizes, and Docker image/cache bloat — in one command. First time? It asks for your VM details once, saves them, and never asks again. Perfect for: post-deploy sanity checks, spotting memory hogs, finding disk space to reclaim, and keeping your server tidy. Triggers on: "check VM", "VM resources", "VM health", "how is the server", "Docker usage", "disk usage", "clean up Docker", "free up space".
As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 4 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 483 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 625: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 4 items
- +4Has examples (3 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.