From broadcast-kit
Optional polish + scoring of a draft before publish, and engagement scoring after.
How this skill is triggered — by the user, by Claude, or both
Slash command
/broadcast-kit:broadcast-optimizeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when you want to polish a draft before calling `broadcast-publish-*`, or rank post-publish metrics.
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(x|xhs|douyin) and body.publish_threshold is -5 in the bundled rubrics; a composite score below threshold means do NOT publish without revising.content_brain.publish_decision == "hold" as a hard stop.engagement_score is pure math; no LLM, no env.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.
npx claudepluginhub chronoaiproject/broadcast-kitCreates bite-sized, testable implementation plans from specs or requirements, with file structure and task decomposition. Activates before coding multi-step tasks.