speech-recognition
Transcribe live and recorded audio with the Speech framework. Use when implementing SpeechAnalyzer (iOS 26+), SpeechTranscriber, SFSpeechRecognizer, live microphone speech-to-text, audio file transcription, on-device speech models, speech recognition permissions, or custom language models.
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The referenced URLs point to documentation on an unofficial domain (`sosumi.ai`) rather than an established first-party publisher, making them a weak external operational dependency tier.
- Repository
thienqo/ios-skills
- Revision
6bf8b62
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.