Menü
Optional polish + scoring of a draft before publish, and engagement scoring after.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Generate a Broadcast Kit content-batch contract from Markdown, a directory, a repo path, or a publish registry.
Join raw platform metrics JSONL back to registry/manifest metadata and compute experiment scoring priors.
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-optimize |
| description | Optional polish + scoring of a draft before publish, and engagement scoring after. |
Use this skill when you want to polish a draft before calling broadcast-publish-*, or rank post-publish metrics.
BROADCAST_KIT_LLM_PROVIDER ∈ {openai, anthropic, ollama} + matching API key. See docs/optimizers.md for the full env set.platform (x|xhs|douyin) and body.publish_threshold is -5 in the bundled rubrics; a composite score below threshold means do NOT publish without revising.content_brain.publish_decision == "hold" as a hard stop.engagement_score is pure math; no LLM, no env. HeavyRanker weights apply to X-style records; weighted composite scoring applies to any platform with engagement metrics.Structured diagnostic (dbskill-style):
broadcast-kit optimize content-brain --draft draft.yaml
Severity-weighted reviewer (10 dimensions per bundled rubric):
broadcast-kit optimize reviewer --draft draft.yaml --max-rounds 3
Generate N variants and pick the best:
broadcast-kit optimize variants --draft draft.yaml --n 3
Rank post-publish metrics:
broadcast-kit optimize engagement --metrics state/douyin/work/metrics/default/<date>.jsonl --scorer composite
broadcast-kit optimize engagement --metrics x_posts.jsonl --scorer heavy
See docs/optimizers.md for return shapes, Python-level usage, custom rubric format, and the source of every weight.