AC declutter-pilot
Use when your home/office/garage has accumulated more stuff than it can hold and every past cleanup attempt stalled after 20 minutes. Physics-based decluttering: item registry with volume estimates, container/trash bag math (how many bags/bins this will actually fill), a fill-first greedy packing order that front-loads visible wins (the first bag out is 80% of the psychological battle), a 20-minute sortie planner with a room+category target list so sessions never stall at 'where do I start', keep/toss decision rules with sunk-cost counters (what the indecision itself costs in money and space), and a donation/receipt/sell batch manifest. Fighting the two real enemies: decision fatigue and the invisible cost of storing junk you'll never use.
Physics-based decluttering: item registry with volume estimates, container/trash bag math (how many bags/bins this will actually fill), a fill-first greedy…
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- 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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 54/100
- 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. 7 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 32 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1676 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
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 749: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 32 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.