AC luis-audio-translator
Convert, compress, merge, split, clip, inspect, and extract audio locally with FFmpeg, plus decode supported music-cache formats including pure-Python Ximalaya .xm and optional Kugou/local helper formats. Use when Codex needs to process audio/video files, batch-convert music folders, inspect media metadata, or handle local encrypted/cache audio files.
Convert, compress, merge, split, clip, inspect, and extract audio locally with FFmpeg, plus decode supported music-cache formats including pure-Python…
As a process C 60/100 · Has gaps — weak spots: result and completion, failures and branches, progress reporting
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Secrets in code
secret-high-entropy-tokenscripts/luis_audio_translator.py:25High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)MUSIC_TOOL_KEY = "e6pk…LcZ"
quoted
Files scanned: 7. 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 60/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 40 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1330 tokens
- 100Running it twice. No mutating operations
- 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 353: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 40 items
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.