transcript-fixer

6.8

116

111

Corrects speech-to-text transcription errors in meeting notes, lectures, and interviews using dictionary rules and AI. Learns patterns to build personalized correction databases. Use when working with transcripts containing ASR/STT errors, homophones, or Chinese/English mixed content requiring cleanup.

nlp

6.8

Rating

Installs

AI & LLM

Quick Review

Excellent skill for transcript correction with clear documentation. The SKILL.md provides comprehensive coverage of capabilities, workflow, and usage patterns that would enable a CLI agent to invoke the skill effectively. Strong task knowledge is evident through detailed examples, multi-stage pipeline description, and clear command syntax. Structure is exemplary with a concise main document that appropriately references detailed guides in the references/ directory. The skill shows good novelty by combining dictionary-based corrections with AI processing and learning patterns, though transcript correction itself is a known domain. Minor deduction on novelty because while the implementation is sophisticated, the core problem (fixing STT errors) could be partially addressed by a CLI agent with sufficient context, though this skill's learning database and staged pipeline do provide meaningful efficiency gains for repeated use.