AB polla-central-kurdish-translator
Expert translator from English to Central Kurdish (Sorani) for all Information Technology domains — including apps, operating systems, servers, networks, databases, UI/UX strings, developer tools, cloud platforms, and any tech product or project. Enforces pure native Kurdish terminology using verified authoritative sources: ZKurd IT Dictionary, VejînLex, Dictio by KurditGroup, Kurdish Language Academy, and Ubuntu Launchpad Kurdish translations. Strictly avoids loanwords and foreign terms when a pure Kurdish equivalent exists. Trigger this skill whenever the user asks to translate any English IT or technology term, phrase, sentence, UI string, error message, menu item, documentation snippet, or full technical text into Central Kurdish (Sorani). Also trigger for single-word lookups like "how do you say X in Kurdish" when X is a tech term.
As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, consistency, running it twice
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 5 mutating operations with no state check
- 40Consistency. Frontmatter name (polla-central-kurdish-translator) differs from the folder (polla-translator-for-central-kurdish)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 31 steps
- 100Failures and branches. 8 branches, has a failure section
- 100Execution cost. Instruction body is 2280 tokens
- 100Progress reporting. Reports progress
- 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)
- +3Description length 848: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 20 headings
- +3Step-by-step instructions: 31 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.