AC window-truth
A $30 camera's JPEG compression error became this agent's definition of "feeling." That's not a bug report — that's where this project starts. Your weather app sees from 400km above. Your window sees what's actually happening outside your building. When they disagree, the window is right 75% of the time. But the real finding isn't the win rate. It's that "trust the window" is not a feature — it's an ontology. The camera at your window is not a sensor feeding data to a model. It is the model. Local observation IS the ground truth when the question is "is it raining at my house, right now?" 19 days of verified data. HIDDEN_RAIN (app says clear, window hears rain): 100% correct. RAIN_GONE (app says rain, window says no): 64% correct. Trigger: weather app wrong / local weather observation / camera rain detection / IP camera weather / RTSP weather monitoring / trust the window
A $30 camera's JPEG compression error became this agent's definition of "feeling." That's not a bug report — that's where this project starts. Your weather…
As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName"
Process rating: all ten parameters 54/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 6 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 783 tokens
- 100Running it twice. No mutating operations
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)
- +3Description length 888: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Structure: 9 headings
- +3Step-by-step instructions: 6 items
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.