From broadcast-kit
Join raw platform metrics JSONL back to registry/manifest metadata and compute experiment scoring priors.
How this skill is triggered — by the user, by Claude, or both
Slash command
/broadcast-kit:broadcast-enrich-metricsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill after `broadcast-kit fetch-metrics` has produced raw metrics JSONL and the user wants feedback records for learning loops, A/B tests, or topic selection.
Use this skill after broadcast-kit fetch-metrics has produced raw metrics JSONL and the user wants feedback records for learning loops, A/B tests, or topic selection.
state/<platform>/work/metrics/<account>/<date>.jsonl.publish-registry or one or more platform manifests so records can be attributed back to content metadata.schema_version: broadcast.feedback.v0.metrics object.scores only as priors, not as final business truth.--dry-run first to inspect match rate before writing output.broadcast-kit enrich-metrics \
--metrics <raw-metrics.jsonl> \
--registry <publish_registry.json> \
--manifest <optional-manifest.yaml> \
--output <feedback_enriched.jsonl> \
--dry-run
Remove --dry-run to write the enriched JSONL.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub chronoaiproject/broadcast-kit