hashgraph-online/awesome-codex-plugins / plugins/andreamzhang/jimeng-skills/.agents/skills/jimeng-storyboard
jimeng-storyboard
VerifiedUse when 编写即梦分镜。按讲戏本剧情点映射母镜头、填7字段。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.1 KB |
| config/duration-rules.json | config | 2.1 KB |
| examples/jimeng-prompt-examples.md | markdown | 12.2 KB |
| scripts/apply_corrections.py | script | 13.6 KB |
| scripts/auto_correct.py | script | 4.7 KB |
| scripts/auto_header.py | script | 4.8 KB |
| scripts/calc_duration.py | script | 15.0 KB |
| scripts/check_assets_change.py | script | 9.4 KB |
| scripts/check_budget.py | script | 6.4 KB |
| scripts/check_dialogue.py | script | 11.6 KB |
| scripts/check_mother_id.py | script | 3.5 KB |
| scripts/check_picture_field.py | script | 8.8 KB |
| scripts/gen_clean.py | script | 2.3 KB |
| scripts/gen_dialogue_list.py | script | 10.3 KB |
| scripts/gen_episode_brief.py | script | 5.5 KB |
| scripts/run_all_checks.py | script | 7.6 KB |
| scripts/stage5_pipeline.py | script | 3.6 KB |
| templates/dialogue-shots.md | markdown | 6.3 KB |
| templates/jimeng-prompts-template.md | markdown | 7.8 KB |
scripts/gen_clean.py
View on GitHub#!/usr/bin/env python3
"""从含格式版 Markdown 分镜文件生成纯文本版 clean.txt"""
import sys
import re
import os
def gen_clean(md_path: str):
if not os.path.exists(md_path):
print(f"错误: 文件不存在: {md_path}")
sys.exit(1)
with open(md_path, "r", encoding="utf-8") as f:
content = f.read()
lines = content.split("\n")
output = []
in_asset_table = False
for line in lines:
# 跳过素材对应表(Markdown表格)及其表头
if line.strip().startswith("| 引用名称"):
in_asset_table = True
continue
if in_asset_table:
if line.strip().startswith("|") and not line.strip().startswith("|---"):
# 提取素材引用行,生成顶部注解
parts = [p.strip() for p in line.strip().split("|") if p.strip()]
if len(parts) >= 4:
ref_name = parts[0]
ref_type = parts[1]
file_name = parts[2]
note = parts[3] if len(parts) > 3 else ""
output.append(f"{ref_name}({ref_type},{file_name},{note})")
continue
elif line.strip() == "---":
in_asset_table = False
output.append("")
continue
elif not line.strip().startswith("|"):
in_asset_table = False
else:
continue
# 去掉 ## 和 ### 标记
if line.startswith("## 母镜头"):
line = line.replace("## ", "", 1)
elif line.startswith("### 子镜头"):
line = line.replace("### ", "", 1)
# 去掉 ** 粗体标记(保留内容)
line = line.replace("**", "")
output.append(line)
# 确定输出路径
dir_path = os.path.dirname(md_path)
base_name = os.path.splitext(os.path.basename(md_path))[0]
clean_path = os.path.join(dir_path, base_name.replace("-jimeng-prompts", "-jimeng-prompts-clean") + ".txt")
with open(clean_path, "w", encoding="utf-8") as f:
f.write("\n".join(output))
print(f"已生成: {clean_path}")
if __name__ == "__main__":
if len(sys.argv) < 2:
print("用法: python gen_clean.py <02-jimeng-prompts.md>")
sys.exit(1)
gen_clean(sys.argv[1])
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |