wavecap-transcripts
Check and analyze WaveCap transcriptions. Use when the user wants to inspect transcript quality, find problematic transcriptions, compare original vs corrected text, or audit transcription accuracy.
npx skills add majiayu000/claude-skill-registry --skill wavecap-transcripts --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# WaveCap Transcripts Analysis Skill Use this skill to inspect, analyze, and audit transcription quality in WaveCap. ## Get Transcriptions ### List recent transcriptions for a stream ```bash curl -s "http://localhost:8000/api/streams/{STREAM_ID}/transcriptions?limit=20" | \ jq '.transcriptions[] | {id, timestamp, text, confidence, reviewStatus}' ``` ### Get all transcriptions across streams ```bash curl -s http://localhost:8000/api/transcriptions/export | jq 'length' ``` ### Get transcription with full details ```bash curl -s "http://localhost:8000/api/streams/{STREAM_ID}/transcriptions?limit=100" | \ jq '.transcriptions[] | select(.id == "TRANSCRIPTION_ID")' ``` ## Quality Analysis ### Find low-confidence transcriptions ```bash # Very low confidence (< 0.5) - likely errors curl -s http://localhost:8000/api/transcriptions/export | \ jq '[.[] | select(.confidence != null and .confidence < 0.5)] | sort_by(.confidence) | .[:20] | .[] | {id, streamId, confidence, text}' # Medium-low confidence (0.5 - 0.7) - may need review curl -s http://localhost:8000/api/transcriptions/export | \ jq '[.[] | select(.confidence != null and .confidence >= 0.5 and .confidence < 0.7)] | length' ``` ### Fi
- Get Transcriptions
- List recent transcriptions for a stream
- Get all transcriptions across streams
- Get transcription with full details
- Quality Analysis
- Find low-confidence transcriptions
- Find very short transcriptions (might be noise)
- Find transcriptions with common error patterns
- Analyze confidence distribution
- Compare Original vs Corrected
- List corrected transcriptions
- Show diff between original and corrected
- Calculate correction rate
- Review Status Audit
curl -s "http://localhost:8000/api/streams/{STREAM_ID}/transcriptions?limit=20" | \
jq '.transcriptions[] | {id, timestamp, text, confidence, reviewStatus}'
curl -s http://localhost:8000/api/transcriptions/export | jq 'length'
curl -s "http://localhost:8000/api/streams/{STREAM_ID}/transcriptions?limit=100" | \
jq '.transcriptions[] | select(.id == "TRANSCRIPTION_ID")'
Very low confidence (< 0.5) - likely errors
curl -s http://localhost:8000/api/transcriptions/export | \
jq '[.[] | select(.confidence != null and .confidence < 0.5)] | sort_by(.confidence) | .[:20] | .[] | {id, streamId, confidence, text}'
Medium-low confidence (0.5 - 0.7) - may need review
jq '[.[] | select(.confidence != null and .confidence >= 0.5 and .confidence < 0.7)] | length'What does the wavecap-transcripts skill do?
Check and analyze WaveCap transcriptions. Use when the user wants to inspect transcript quality, find problematic transcriptions, compare original vs corrected text, or audit transcription accuracy.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill wavecap-transcripts --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.