AD mongolian-ai
Use the Mongol AI API for Mongolian translation, script conversion, conversation, composition, OCR, ASR, TTS, and Word/PDF translation. Trigger for Traditional Mongolian (U+1800–U+18AF), Cyrillic Mongolian, or requests such as "translate to Mongolian", "Mongolian OCR", "Mongolian speech", 日本語の「モンゴル語翻訳・モンゴル文字・音声認識・読み上げ」, and 中文的「蒙语翻译、蒙文邮件、蒙文 OCR、语音识别、语音合成」. Requests send text, images, audio, or documents to https://mongol.open-idea.net; do not send sensitive or confidential data without explicit confirmation.
Use the Mongol AI API for Mongolian translation, script conversion, conversation, composition, OCR, ASR, TTS, and Word/PDF translation.
As a process D 47/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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: 20. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 8): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 47/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 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 (mongolian-ai) differs from the folder (mongolian-ai-codex)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 26 steps
- 100Execution cost. Instruction body is 1094 tokens
- low The response is described with custom markup (8 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
- +4No input/output examples
- -31 of 7 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 513: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 26 items
- +4Reference files are cited in the instructions (10 of 10)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.