qiaomu-cut
Verified把一句话需求转成可复现、可验收视频工程的乔木智能剪辑导演。Use when the user asks to create, plan, edit, remix, explain, narrate, subtitle, animate, composite, or render a video—including one-line requests such as “制作一个科普视频:介绍 LLM 中的 RL”. Builds English-learning movie mixes, person profiles, explainers, code-drawn motion graphics (UI morph loops, showreels, kinetic-type promos, line-art/pixel/Three.js animation, lyric MVs), product launch videos, cinematic shorts, social clips, course/PPT videos, AI image/video/TTS/music-assisted stories, stock-footage stories, or multi-source montage. Routes across 33台词, ClipSeek/open media, local files, ListenHub, image generation, HTML/SVG/Canvas motion graphics with beat-grid storyboards and determinism probes, Manim, ffmpeg-full, captions, sound design, frame-0 video covers with YouTube thumbnails, and release checks.
scripts/trigger_eval.py
View on GitHub#!/usr/bin/env python3
import argparse
import json
from pathlib import Path
TRIGGER_HINTS = [
"视频", "剪辑", "混剪", "字幕", "电影", "素材", "片头", "转场",
"运镜", "口播", "科普", "介绍", "short", "video", "edit", "montage",
"动态图形", "动效视频", "动画", "showreel", "mv", "motion graphic", "kinetic typography"
]
EXPLICIT_NON_VIDEO_HINTS = [
"不需要视频", "不要视频", "仅音频", "只要音频", "audio only", "no video"
]
def should_trigger(text: str) -> bool:
lowered = text.lower()
if any(hint.lower() in lowered for hint in EXPLICIT_NON_VIDEO_HINTS):
return False
return any(hint.lower() in lowered for hint in TRIGGER_HINTS)
def main() -> int:
parser = argparse.ArgumentParser()
parser.add_argument("skill_dir")
parser.add_argument("--cases", default="evals/trigger_cases.json")
parser.add_argument("--output", default="reports/trigger-eval.json")
args = parser.parse_args()
root = Path(args.skill_dir).resolve()
cases_path = root / args.cases
cases = json.loads(cases_path.read_text(encoding="utf-8"))
results = []
failures = []
for case in cases.get("should_trigger", []):
got = should_trigger(case["input"])
results.append({"id": case["id"], "expected": True, "got": got})
if not got:
failures.append(case["id"])
for case in cases.get("should_not_trigger", []) + cases.get("near_neighbor", []):
got = should_trigger(case["input"])
results.append({"id": case["id"], "expected": False, "got": got})
if got:
failures.append(case["id"])
report = {
"ok": not failures,
"total": len(results),
"summary": {
"total": len(results),
"passed": len(results) - len(failures),
"false_positive": sum(1 for r in results if r["got"] and not r["expected"]),
"false_negative": sum(1 for r in results if r["expected"] and not r["got"]),
"pass_rate": round((len(results) - len(failures)) / len(results), 3) if results else 0.0,
},
"failures": failures,
"results": results,
}
output = root / args.output
output.parent.mkdir(parents=True, exist_ok=True)
output.write_text(json.dumps(report, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
print(json.dumps(report, ensure_ascii=False, indent=2))
return 0 if not failures else 1
if __name__ == "__main__":
raise SystemExit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |