메뉴
Join raw platform metrics JSONL back to registry/manifest metadata and compute experiment scoring priors.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Optional polish + scoring of a draft before publish, and engagement scoring after.
Generate a Broadcast Kit content-batch contract from Markdown, a directory, a repo path, or a publish registry.
Fetch and normalize platform metrics into the Broadcast Kit metrics snapshot shape.
Interview the user's content-publishing goal, map it to a capability tier, recommend the minimum setup, then run the matching recipe from CATALOG.md. Use this skill for any "publish / grow / analyze on Douyin / XHS / X" request.
Publish one Douyin manifest via the in-package Playwright publisher.
Publish a tweet or thread to X via NyxID proxy (preferred) or direct API (fallback).
| name | broadcast-enrich-metrics |
| description | Join raw platform metrics JSONL back to registry/manifest metadata and compute experiment scoring priors. |
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.