Transcript judging
Skill cyanxxy/transcription-agent-go/.skills/transcript-judging
Agentic audio transcription in Go: parallel transcription agents, an LLM judge agent that picks the best, extensible via Agent Skills.
npx -y skills add cyanxxy/transcription-agent-go --skill transcript-judgingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Guides the judge agent to compare transcript candidates conservatively and use the transcript-analysis tools. Default judge behavior; allows all four analysis tools.
SKILL.md
0.8 KB, 90 tokens by cl100k_base, as published. Nobody here has run it
Transcript Judging
Compare the candidates for the same audio span and select the strongest, or merge them when it clearly improves accuracy. Prefer the more conservative wording when candidates disagree. Use the transcript-analysis tools (quality_metrics, timestamp_analysis, candidate_diff, boundary_analysis) when candidate quality, timestamp health, differences, or boundary consistency would help the decision. Tools inspect transcript text and metadata only — never raw audio.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.