AC fasaha
Review and fix AI-generated or AI-translated Arabic so it reads as fluent, native Modern Standard Arabic (MSA) instead of translated/calqued output. Trigger on translating INTO Arabic, writing in Arabic (اكتب بالعربية / اكتبلي بالعربية), writing original Arabic, or reviewing/correcting/proofreading Arabic (‘راجع لي هذا’, 'صحح العربية', 'ترجم هذا للعربية', any Arabic quality check), and proactively before outputting Arabic prose longer than 2-3 sentences. Covers: Latin-script leakage, English sentence-structure calque, word choice/terminology, morphology/agreement, punctuation, hamza spelling, dialectal leakage into MSA. Ships a self-maintained register profile (voice-profile.md) for tone and MSA-vs-Darija choice, a runnable checklist, a terminology glossary, and an accumulating failure log. Register-focused; a separate style/voice skill may layer after it.
Review and fix AI-generated or AI-translated Arabic so it reads as fluent, native Modern Standard Arabic (MSA) instead of translated/calqued output.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, 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: 10. 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 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 5 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 85Steps. 44 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2840 tokens
- 100Progress reporting. Reports progress
- low 10 top-level sections: this looks like several domains in one skill
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 868: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +4Structure: 11 headings
- +3Step-by-step instructions: 44 items
- +4Reference files are cited in the instructions (8 of 8)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.