BC Coffee
Learns the user's coffee taste as a written corpus plus their brewing gear, and uses both to recommend coffees, discover new ones that fit, answer brew questions, and log what they drink. USE WHEN my coffee, coffee taste, what coffee do I like, recommend a coffee, coffee like X, what should I drink, find a coffee, new coffee, discover coffees, beyond my usual roaster, my coffee gear, my grinder, my brewer, my brew setup, how should I brew, brew ratio, add a coffee, log this coffee, update my coffee list. NOT FOR ordering coffee or cafes (Restaurants), audio or studio gear.
The skill teaches your AI your coffee preferences and gear, then recommends new beans, answers brewing questions, and logs what you drink. Clear scope: recommendations, discovery, logging, and brew advice. Decent scores—quality 82, safety 100, but process only 59. Five files, no critical errors, yet no model runs to verify it works. The skill stays in its lane: no cafe lookups or orders.
The catch is no real-world testing. Low process score hints at structural gaps in how the skill tracks taste profiles and avoids recommending the same beans twice. Worth installing if you'll feed it your coffee notes and accept rough edges early on.
Learns the user's coffee taste as a written corpus plus their brewing gear, and uses both to recommend coffees, discover new ones that fit, answer brew…
As a process C 59/100 · 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "evals"
Process rating: all ten parameters 59/100
- 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
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1173 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low The response is described with custom markup (3 tags): a typed call is more reliable
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
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 579: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.