CD add-a-domain
Localize another existing tau2 domain for a language pack through the factory, preserving reviewed personas and reusing voices. Use for adding airline, retail or telecom coverage to an existing language, not for implementing a new benchmark domain.
The skill adds a domain from an existing tau2 benchmark to a language pack, reusing voices and preserving reviewed personas. Promises to save time on localization for airlines, retail, or telecom by reusing existing data instead of building from scratch.
Audit found broken references and missing files. Code quality scores 72, process scores 36. No critical errors flagged, but the gap between these scores and zero medium/low findings is odd. No model runs or sandbox tests. Should work across major platforms.
Install if you already have a base benchmark and need fast language coverage expansion. Verify the broken files locally first.
Localize another existing tau2 domain for a language pack through the factory, preserving reviewed personas and reusing voices.
As a process D 36/100 · Unfinished process — References files that are not bundled: ../../../docs/language-authoring.md, ../../../docs/language-submission-template.md, ../../../docs/judge-validation.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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../../../docs/language-authoring.md - warning
missing-refreference to a missing file: ../../../docs/language-submission-template.md - warning
missing-refreference to a missing file: ../../../docs/judge-validation.md
Process rating: all ten parameters 36/100
- 0Tools and files. 3 referenced file(s) missing: ../../../docs/language-authoring.md, ../../../docs/language-submission-template.md, ../../../docs/judge-validation.md
- 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. 2 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Steps. 6 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1010 tokens
- low The response is described with custom markup (5 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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 248: enough signal without eating the budget
- +4Structure: 4 headings
- +3Step-by-step instructions: 6 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.