AB transcription-speech-to-text-hebrew
Transcribe audio or video files using the TextOps/Modal API. Use this skill whenever the user wants to transcribe a video or audio file, mentions an mp4/mp3/wav/m4a file and wants text out of it, asks for transcription or תמלול, or wants to convert spoken audio to text. Always trigger this skill even if the user just says "תמלל את זה" or "I want to transcribe this file". Also trigger this skill when the user asks what this skill can do, what features it has, "מה אתה יכול לעשות?", "what can you do?", or any similar capability question.
As a process B 74/100 · Nearly there — weak spots: 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: 5. 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 74/100
- 30Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, 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
- 85Steps. 26 steps, 1 vague phrases
- 100Failures and branches. 13 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2988 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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)
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 540: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 26 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
- +3All 3 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.