BB ac-buying-consultant
Guide first-time and repeat AC buyers through sizing, type selection, efficiency ratings, refrigerant choice, and spec prioritisation to choose the right air conditioner for their room, budget, and climate.
As a process B 77/100 · Nearly there — weak spots: execution cost, running it twice, progress reporting
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
- 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
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Implicit map keys need to be followed by map values at line 5, column 1: homepage: https://github.com/arbazex/ac-buying-consultant metadata:{"clawdbot":{"emoji":"❄️"}} ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
body-longSKILL.md body ≈ 8281 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 77/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 40Execution cost. Instruction body is 8281 tokens: crowds the task out of the window
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 191 steps, 3 vague phrases
- 100Tools and files. No external tools needed
- 100Failures and branches. 11 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 206: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 191 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.
External checks
ClawHub: clean
This is a prompt-only AC buying guide with a real sizing-quality issue, but it does not request sensitive access or perform actions.
LLM: benign (medium) · VirusTotal: · 29 May 2026