AF tasteprint
Use when the user asks for product, shopping, gift, gear, or purchase recommendations; compares options; asks what to buy; wants to build, update, inspect, sync, or delete their Tasteprint preference profile; asks to analyze shopping/content/social behavior; or volunteers durable recommendation signals in conversation, including likes, dislikes, owned/bought/returned items, avoid rules, stable constraints, budget habits, style/material/brand/category preferences, evidence/source preferences, recommendation-format preferences, or corrections such as "remember", "do not remember", "I usually", "I no longer", or "avoid".
compares options; asks what to buy; wants to build, update, inspect, sync, or delete their Tasteprint preference profile; asks to analyze…
As a process F 47/100 · Will not run — References files that are not bundled: references/browser-connection.md, references/conversation-signals.md, references/task-hypotheses.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/browser-connection.md - warning
missing-refreference to a missing file: references/conversation-signals.md - warning
missing-refreference to a missing file: references/task-hypotheses.md - warning
missing-refreference to a missing file: references/recommender.md - warning
missing-refreference to a missing file: references/questionnaire-and-consent.md - warning
missing-refreference to a missing file: references/browser-guidelines.md - warning
missing-refreference to a missing file: references/data-schemas.md - warning
missing-refreference to a missing file: references/platforms/README.md - warning
missing-refreference to a missing file: references/profile-analysis.md - warning
missing-refreference to a missing file: references/domain-profile-template.md - warning
missing-refreference to a missing file: references/profile-template.md
Process rating: all ten parameters 47/100
- 0Tools and files. 11 referenced file(s) missing: references/browser-connection.md, references/conversation-signals.md, references/task-hypotheses.md
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 4 mutating operations with no state check
- 40Consistency. Frontmatter name (tasteprint) differs from the folder (tasteprint-skill)
- 70When it triggers. States when to use, but not when not to
- 100Steps. 16 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 2575 tokens
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (15 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
- +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 4 example trigger phrases
- +3Description length 625: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.