Guizang Social Cards
op7418/guizang-social-card-skill
Produces social card sets for Xiaohongshu and WeChat: carousels, Live Photo motion cards and puzzle layouts, and WeChat cover pairs, rendered from single-file HTML.
逐一对比技能。将生成剧本与每个参考剧本逐一对比,按照剧本评价标准给出详细批判和改进建议. An agent skill from Supreme-Ultimate/novel-to-script-team.
$ npx skills add Supreme-Ultimate/novel-to-script-team --skill one-by-one-comparison-skill -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Supreme-Ultimate/novel-to-script-team one-by-one-comparison-skill --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-team.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/one-by-one-comparison-skill .claude/skills/one-by-one-comparison-skill && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "one-by-one-comparison-skill" agent skill from https://github.com/Supreme-Ultimate/novel-to-script-team/tree/main/skills/one-by-one-comparison-skill into .claude/skills/one-by-one-comparison-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "one-by-one-comparison-skill", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Supreme-Ultimate/novel-to-script-team/tree/main/skills/one-by-one-comparison-skillType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Supreme-Ultimate/novel-to-script-team --skill one-by-one-comparison-skill -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Supreme-Ultimate/novel-to-script-team one-by-one-comparison-skill --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-team.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/one-by-one-comparison-skill .agents/skills/one-by-one-comparison-skill && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "one-by-one-comparison-skill" agent skill from https://github.com/Supreme-Ultimate/novel-to-script-team/tree/main/skills/one-by-one-comparison-skill into .agents/skills/one-by-one-comparison-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "one-by-one-comparison-skill", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Supreme-Ultimate/novel-to-script-team --skill one-by-one-comparison-skill -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Supreme-Ultimate/novel-to-script-team one-by-one-comparison-skill --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-team.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/one-by-one-comparison-skill .cursor/skills/one-by-one-comparison-skill && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "one-by-one-comparison-skill" agent skill from https://github.com/Supreme-Ultimate/novel-to-script-team/tree/main/skills/one-by-one-comparison-skill into .cursor/skills/one-by-one-comparison-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "one-by-one-comparison-skill", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Supreme-Ultimate/novel-to-script-team.git --path skills/one-by-one-comparison-skill--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Supreme-Ultimate/novel-to-script-team --skill one-by-one-comparison-skill -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Supreme-Ultimate/novel-to-script-team one-by-one-comparison-skill --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-team.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/one-by-one-comparison-skill .gemini/skills/one-by-one-comparison-skill && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "one-by-one-comparison-skill" agent skill from https://github.com/Supreme-Ultimate/novel-to-script-team/tree/main/skills/one-by-one-comparison-skill into .gemini/skills/one-by-one-comparison-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "one-by-one-comparison-skill", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Supreme-Ultimate/novel-to-script-team one-by-one-comparison-skillInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Supreme-Ultimate/novel-to-script-team --skill one-by-one-comparison-skill -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-team.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/one-by-one-comparison-skill .github/skills/one-by-one-comparison-skill && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "one-by-one-comparison-skill" agent skill from https://github.com/Supreme-Ultimate/novel-to-script-team/tree/main/skills/one-by-one-comparison-skill into .github/skills/one-by-one-comparison-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "one-by-one-comparison-skill", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Supreme-Ultimate/novel-to-script-team --skill one-by-one-comparison-skill -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Supreme-Ultimate/novel-to-script-team one-by-one-comparison-skill --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-team.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/one-by-one-comparison-skill .opencode/skills/one-by-one-comparison-skill && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "one-by-one-comparison-skill" agent skill from https://github.com/Supreme-Ultimate/novel-to-script-team/tree/main/skills/one-by-one-comparison-skill into .opencode/skills/one-by-one-comparison-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "one-by-one-comparison-skill", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
one-by-one-comparison-skill逐一对比技能。将生成剧本与每个参考剧本逐一对比,按照剧本评价标准给出详细批判和改进建议. An agent skill from Supreme-Ultimate/novel-to-script-team.
One By One Comparison Skill is an agent skill from Supreme-Ultimate/novel-to-script-team. 逐一对比技能。将生成剧本与每个参考剧本逐一对比,按照剧本评价标准给出详细批判和改进建议。
Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Media & Creative. The repository describes itself as: 完整的多 Agent 多 Skill 小说改编影视流水线系统。 The licence is MIT.
9 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 117dceb. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are python and markdown).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
One By One Comparison Skill loads about 2.8k tokens when it runs. Until then it costs about 18 tokens; SKILL.md has 133 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from Supreme-Ultimate/novel-to-script-team at commit 117dceb, republished under its MIT licence (© Supreme-Ultimate). 133 words, ~2,793 tokens.
.claude/skills/one-by-one-comparison-skill/SKILL.md (or your agent's skills folder).../../references/00-first-principles.md../../references/03-script-writing-standard.md../../references/04-review-gates.md将生成剧本与检索到的Top 5参考剧本逐一对比,每次对比都按照统一的评价标准进行深度分析,给出具体的批判和改进建议。
评分细则:
对比方法:
# 统计生成剧本
gen_scenes = count_scenes(generated_script)
gen_conflicts = count_conflicts(generated_script)
gen_conflict_density = gen_conflicts / len(generated_script)
# 统计参考剧本
ref_scenes = count_scenes(reference_script)
ref_conflicts = count_conflicts(reference_script)
ref_conflict_density = ref_conflicts / len(reference_script)
# 评分
scene_score = 5 if abs(gen_scenes - ref_scenes) <= 2 else max(0, 5 - abs(gen_scenes - ref_scenes))
conflict_score = 5 if gen_conflict_density >= 0.03 else gen_conflict_density / 0.03 * 5评分细则:
对比方法:
# 对话比例
gen_dialogue_ratio = calculate_dialogue_ratio(generated_script)
ref_dialogue_ratio = calculate_dialogue_ratio(reference_script)
dialogue_score = 10 if gen_dialogue_ratio >= 0.7 else gen_dialogue_ratio / 0.7 * 10
# 句长
gen_avg_length = calculate_avg_sentence_length(generated_script)
ref_avg_length = calculate_avg_sentence_length(reference_script)
if 10 <= gen_avg_length <= 14:
length_score = 8
else:
length_score = max(0, 8 - abs(gen_avg_length - 12) * 0.5)评分细则:
对比方法:
visual_markers = ['冷笑', '嗤笑', '冷哼', '眼神一冷', '眸光一沉', '嘴角勾起', '挑眉', '转身']
gen_marker_density = count_markers(generated_script, visual_markers) / (len(generated_script) / 100)
ref_marker_density = count_markers(reference_script, visual_markers) / (len(reference_script) / 100)
if 3 <= gen_marker_density <= 5:
marker_score = 10
else:
marker_score = max(0, 10 - abs(gen_marker_density - 4) * 2)评分细则:
对比方法:
wanwen_keywords = {
'情绪强化': ['冷笑', '嗤笑', '冷哼', '冷声', '冷冷地'],
'态度词': ['不屑', '轻蔑', '讥讽', '嘲讽', '鄙夷'],
'气场词': ['霸气', '强势', '凌厉', '锐利', '凛然'],
'打脸词': ['啪啪打脸', '狠狠打脸', '当场打脸', '脸色一变']
}
gen_keyword_density = count_all_keywords(generated_script, wanwen_keywords) / (len(generated_script) / 100)
ref_keyword_density = count_all_keywords(reference_script, wanwen_keywords) / (len(reference_script) / 100)
if 1.5 <= gen_keyword_density <= 2.5:
keyword_score = 10
else:
keyword_score = max(0, 10 - abs(gen_keyword_density - 2) * 3)评分细则:
对比方法:
structure_elements = {
'hook': check_opening_hook(script), # True/False
'development': check_continuous_conflict(script),
'climax': check_climax(script),
'twist': check_twist(script),
'ending': check_ending_hook(script)
}
structure_score = sum([
3 if structure_elements['hook'] else 0,
4 if structure_elements['development'] else 0,
3 if structure_elements['climax'] else 0,
3 if structure_elements['twist'] else 0,
2 if structure_elements['ending'] else 0
])# 加载生成剧本
with open(f'outputs/{剧本名}/scripts/ep{N}.md', 'r') as f:
generated_script = f.read()
# 加载参考剧本列表(从检索结果或style-analysis报告中获取)
reference_files = [
'knowledge/hit-scripts-md/参考剧本1.md',
'knowledge/hit-scripts-md/参考剧本2.md',
'knowledge/hit-scripts-md/参考剧本3.md',
'knowledge/hit-scripts-md/参考剧本4.md',
'knowledge/hit-scripts-md/参考剧本5.md'
]
reference_scripts = []
for ref_file in reference_files:
with open(ref_file, 'r') as f:
reference_scripts.append({
'filename': os.path.basename(ref_file),
'content': f.read()
})comparison_results = []
for i, ref in enumerate(reference_scripts, 1):
print(f"\n{'='*80}")
print(f"对比 {i}/5: 生成剧本 vs {ref['filename']}")
print(f"{'='*80}\n")
# 五大维度评分
rhythm_score = compare_rhythm(generated_script, ref['content'])
dialogue_score = compare_dialogue(generated_script, ref['content'])
visual_score = compare_visual(generated_script, ref['content'])
wanwen_score = compare_wanwen(generated_script, ref['content'])
structure_score = compare_structure(generated_script, ref['content'])
total_score = rhythm_score + dialogue_score + visual_score + wanwen_score + structure_score
# 识别具体问题
issues = identify_issues(generated_script, ref['content'])
# 提取参考示例
examples = extract_examples(ref['content'], issues)
# 生成改进建议
suggestions = generate_suggestions(issues, examples)
comparison_results.append({
'reference': ref['filename'],
'scores': {
'rhythm': rhythm_score,
'dialogue': dialogue_score,
'visual': visual_score,
'wanwen': wanwen_score,
'structure': structure_score,
'total': total_score
},
'issues': issues,
'examples': examples,
'suggestions': suggestions
})# 汇总共同问题
common_issues = find_common_issues(comparison_results)
# 计算平均得分
avg_scores = calculate_average_scores(comparison_results)
# 识别最弱维度
weakest_dimensions = identify_weakest_dimensions(avg_scores)
# 生成优先级建议
priority_suggestions = prioritize_suggestions(common_issues, weakest_dimensions)# 第{N}集逐一对比分析报告
## 一、综合评分
| 维度 | 平均得分 | 评级 |
|------|---------|------|
| 节奏控制 | 15/20 | B |
| 对话风格 | 18/25 | B+ |
| 视觉化表达 | 12/20 | C+ |
| 网文感 | 10/20 | C |
| 结构完整性 | 13/15 | A- |
| **总分** | **68/100** | **C+** |
**判定**:❌ FAIL(需达到80分以上)
---
## 二、逐一对比详情
### 对比1:生成剧本 vs 《天降多宝后,渣过妈咪的人都后悔了》第1集
#### 评分详情
- 节奏控制:14/20 ⚠️
- 对话风格:16/25 ⚠️
- 视觉化表达:10/20 ⚠️
- 网文感:8/20 ⚠️
- 结构完整性:12/15 ✓
- **小计:60/100**
#### 具体问题
**1. 对话比偏低(优先级:高)**
- **生成剧本**:对话比45%
- **参考剧本**:对话比75%
- **差距**:-30%
- **位置**:场景2(萧家客厅)叙述过多
**参考示例**(《天降多宝后》第1集,场景2):【参考剧本片段】 萧万擎冷笑:"你以为你是谁?我萧家的养子?" 沈倾城咬牙:"我为这个家付出了十年!" "付出?"萧万擎嗤笑,"你配吗?" 林秀雪冷冷道:"搜她的包。"
**改进建议**:
- 将叙述改为对话
- 原文:"她很生气,觉得他们太过分了。"
- 改为:"你们太过分了!"她愤怒地说。
---
**2. 视觉标记不足(优先级:高)**
- **生成剧本**:1.2个/100字
- **参考剧本**:4.5个/100字
- **差距**:-3.3个/100字
- **位置**:全文缺乏表情和眼神描写
**参考示例**(《天降多宝后》第1集):【参考剧本片段】 萧万擎冷笑一声,眼神一冷:"把她的东西都搜出来。" 林秀雪嘴角勾起一抹讥讽:"还装什么清高?" 沈倾城眸光一沉,冷冷地看着他们。
**改进建议**:
- 在对话后增加表情描写(冷笑、嗤笑、冷哼)
- 在冲突场景增加眼神描写(眼神一冷、眸光一沉)
- 在转折处增加动作描写(嘴角勾起、转身离开)
---
**3. 网文感关键词缺失(优先级:中)**
- **生成剧本**:0.8个/100字
- **参考剧本**:2.3个/100字
- **差距**:-1.5个/100字
- **位置**:缺乏情绪强化词和态度词
**参考示例**(《天降多宝后》第1集):【参考剧本片段】 "不屑"、"轻蔑"、"讥讽"、"冷笑"、"嗤笑"、"冷哼" 这些词汇高频出现,营造强烈的情绪冲击
**改进建议**:
- 增加情绪强化词:冷笑、嗤笑、冷哼、冷声
- 增加态度词:不屑、轻蔑、讥讽、嘲讽
- 增加气场词:霸气、强势、凌厉
---
### 对比2:生成剧本 vs 《豪门弃女逆袭记》第1集
#### 评分详情
- 节奏控制:16/20 ✓
- 对话风格:18/25 ⚠️
- 视觉化表达:12/20 ⚠️
- 网文感:10/20 ⚠️
- 结构完整性:14/15 ✓
- **小计:70/100**
#### 具体问题
**1. 句长偏长(优先级:中)**
- **生成剧本**:平均18字符
- **参考剧本**:平均11字符
- **差距**:+7字符
- **位置**:场景1和场景3的对话
**参考示例**(《豪门弃女逆袭记》第1集):【参考剧本片段】 "你算什么东西?"(7字) "滚出去。"(4字) "我不走。"(4字) "那就别怪我不客气。"(9字)
**改进建议**:
- 将长句拆分为2-3个短句
- 原文:"她看着他,心中涌起一股复杂的情绪,既有愤怒也有不甘。"(26字)
- 改为:"她看着他。心中涌起复杂情绪。既愤怒,也不甘。"(3句,平均8字)
---
**2. 打脸节奏不够密集(优先级:中)**
- **生成剧本**:3次打脸/1集
- **参考剧本**:5次打脸/1集
- **差距**:-2次
- **位置**:场景2和场景3可增加打脸
**参考示例**(《豪门弃女逆袭记》第1集):【参考剧本片段】 打脸1:搜身无果 打脸2:项链在别人身上 打脸3:揭露真相 打脸4:反击成功 打脸5:预言应验
**改进建议**:
- 在场景2增加一次小打脸(如:萧家人的谎言被揭穿)
- 在场景3增加一次打脸(如:张家人的能力展示)
---
### 对比3:生成剧本 vs 《爱在焚心成焰时》第1集
(类似格式,继续对比...)
---
### 对比4:生成剧本 vs 《顾总千金有点毒》第1集
(类似格式,继续对比...)
---
### 对比5:生成剧本 vs 《锦衣卫的第二人生》第1集
(类似格式,继续对比...)
---
## 三、共同问题汇总
### 问题1:对话比偏低(出现频率:5/5)
**5个参考剧本的对话比**:
1. 《天降多宝后》:75%
2. 《豪门弃女逆袭记》:72%
3. 《爱在焚心成焰时》:78%
4. 《顾总千金有点毒》:70%
5. 《锦衣卫的第二人生》:73%
**平均**:73.6%
**生成剧本的对话比**:45%
**差距**:-28.6%
**影响**:严重影响节奏感和可读性,AI味较重
**改进建议**:
1. 将所有叙述性文字改为对话形式
2. 增加人物互动和对话场景
3. 目标:将对话比提升到70%以上
---
### 问题2:视觉标记不足(出现频率:5/5)
**5个参考剧本的视觉标记密度**:
1. 《天降多宝后》:4.5个/100字
2. 《豪门弃女逆袭记》:4.2个/100字
3. 《爱在焚心成焰时》:5.1个/100字
4. 《顾总千金有点毒》:3.8个/100字
5. 《锦衣卫的第二人生》:4.0个/100字
**平均**:4.3个/100字
**生成剧本的视觉标记密度**:1.2个/100字
**差距**:-3.1个/100字
**影响**:画面感不足,情绪表达不够强烈
**改进建议**:
1. 在每句对话后增加表情描写(冷笑、嗤笑、冷哼)
2. 在冲突场景增加眼神描写(眼神一冷、眸光一沉)
3. 在转折处增加动作描写(嘴角勾起、转身离开)
4. 目标:将视觉标记密度提升到4个/100字以上
---
### 问题3:网文感关键词缺失(出现频率:5/5)
**5个参考剧本的网文感关键词密度**:
1. 《天降多宝后》:2.3个/100字
2. 《豪门弃女逆袭记》:2.0个/100字
3. 《爱在焚心成焰时》:2.5个/100字
4. 《顾总千金有点毒》:1.8个/100字
5. 《锦衣卫的第二人生》:2.1个/100字
**平均**:2.1个/100字
**生成剧本的网文感关键词密度**:0.8个/100字
**差距**:-1.3个/100字
**影响**:网文感不足,AI味较重
**改进建议**:
1. 增加情绪强化词:冷笑、嗤笑、冷哼、冷声、冷冷地
2. 增加态度词:不屑、轻蔑、讥讽、嘲讽、鄙夷
3. 增加气场词:霸气、强势、凌厉、锐利、凛然
4. 目标:将网文感关键词密度提升到2个/100字以上
---
## 四、优先级改进建议
### 优先级1(必须立即修改)
1. **提高对话比(45% → 70%+)**
- 影响:最严重,直接影响可读性和节奏感
- 工作量:大(需要重写大部分叙述)
- 预期效果:+15分
2. **增加视觉标记(1.2 → 4个/100字)**
- 影响:严重,影响画面感和情绪表达
- 工作量:中(在现有对话后增加描写)
- 预期效果:+8分
### 优先级2(强烈建议修改)
3. **增加网文感关键词(0.8 → 2个/100字)**
- 影响:中等,影响网文感和爽点
- 工作量:中(替换部分词汇)
- 预期效果:+10分
4. **拆分长句(18字符 → 11字符)**
- 影响:中等,影响节奏感
- 工作量:中(拆分长句)
- 预期效果:+7分
### 优先级3(建议优化)
5. **增加打脸密度(3次 → 5次)**
- 影响:较小,影响爽点密度
- 工作量:小(增加2个打脸场景)
- 预期效果:+3分
---
## 五、修改后预期得分
**当前得分**:68/100(C+)
**修改后预期得分**:
- 完成优先级1:68 + 15 + 8 = 91/100(A)
- 完成优先级1+2:91 + 10 + 7 = 108/100(满分100,实际95+)
- 完成全部:95+ /100(A+)
**建议**:
- 至少完成优先级1,确保达到80分以上(PASS标准)
- 建议完成优先级1+2,确保达到90分以上(优秀标准)
---
## 六、具体修改示例
### 示例1:提高对话比
**原文**(场景2,叙述过多):张逸臣看着萧家人,心中涌起一股复杂的情绪。他想起了过去十年的种种委屈和不公,觉得这些人太过分了。他决定不再忍受,要离开这个冷漠的家。
**修改后**(改为对话):张逸臣看着萧家人,眼神一冷。
"十年了。"他冷冷地说。
"十年的委屈,十年的不公。"
萧万擎冷笑:"你还想怎样?"
"我不想怎样。"张逸臣转身,"我只想离开这个冷漠的家。"
**改进效果**:
- 对话比:从0%提升到80%
- 增加了视觉标记(眼神一冷、冷冷地、冷笑、转身)
- 增加了网文感关键词(冷冷地、冷笑、冷漠)
- 句长更短,节奏更快
---
### 示例2:增加视觉标记
**原文**(场景1,缺乏视觉标记):"把车钥匙交出来。"萧万擎说。 "我从来没有车。"张逸臣说。 "搜他的包。"林秀雪说。
**修改后**(增加视觉标记):"把车钥匙交出来。"萧万擎冷声道,眼神凌厉。 "我从来没有车。"张逸臣冷笑一声,眸光一沉。 "搜他的包。"林秀雪嘴角勾起一抹讥讽,不屑地挥手。
**改进效果**:
- 视觉标记:从0个增加到6个(冷声、眼神凌厉、冷笑、眸光一沉、嘴角勾起、不屑)
- 增加了网文感关键词(冷声、冷笑、讥讽、不屑)
- 画面感更强,情绪表达更充分
---
### 示例3:增加网文感关键词
**原文**(场景3,网文感不足):"你们会后悔的。"张逸臣说完,转身离开。
**修改后**(增加网文感关键词):"你们会后悔的。"张逸臣冷笑一声,眼神一冷,霸气地转身离开。
萧万擎嗤笑:"狂妄。"
林秀雪不屑:"不过是个养子。"
但他们没想到,这个被他们轻蔑的养子,竟然会成为他们的噩梦。
**改进效果**:
- 网文感关键词:从0个增加到7个(冷笑、眼神一冷、霸气、嗤笑、不屑、轻蔑、竟然)
- 增加了反转预告(没想到、竟然)
- 增加了悬念(噩梦)
---
## 七、总结
**核心问题**:
1. 对话比严重偏低(-28.6%)
2. 视觉标记严重不足(-3.1个/100字)
3. 网文感关键词缺失(-1.3个/100字)
**改进方向**:
1. 将叙述改为对话,提高对话比到70%+
2. 在对话后增加视觉标记,提升到4个/100字
3. 增加网文感关键词,提升到2个/100字
**预期效果**:
- 完成优先级1修改后,得分可从68分提升到91分
- 完成优先级1+2修改后,得分可达到95分以上
**下一步**:
1. 按照优先级1的建议修改剧本
2. 重新提交审核
3. 如果仍未达标,继续按照优先级2的建议修改输出到 outputs/{剧本名}/review/one-by-one-comparison-ep<N>.md
© Supreme-Ultimate, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/one-by-one-comparison-skill of Supreme-Ultimate/novel-to-script-team.
Open the folder on GitHubat commit 117dceb
One By One Comparison Skill next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| One By One Comparison Skill this skillSupreme-Ultimate/novel-to-script-team | 175 | — | ~2.8k | Automated safety check: Pass | MIT | |
| Guizang Social Cardsop7418/guizang-social-card-skill | 7.4k | 1 repos | ~7.8k | Automated safety check: Pass | AGPL-3.0 | |
| Weekly Changelog Videoheygen-com/hyperframes | 60k | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | |
| Anthropic Brand Stylinganthropics/skills | 180k | 30 repos | ~559 | Automated safety check: Pass | Apache-2.0 | |
| MoneyPrinterTurbo Video Generatorharry0703/MoneyPrinterTurbo | 129k | — | ~2.1k | Automated safety check: Warn | MIT | |
| HyperFrames Media Useheygen-com/hyperframes | 60k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 |
op7418/guizang-social-card-skill
Produces social card sets for Xiaohongshu and WeChat: carousels, Live Photo motion cards and puzzle layouts, and WeChat cover pairs, rendered from single-file HTML.
heygen-com/hyperframes
Turns a weekly changelog markdown file into a branded HyperFrames video with voiceover, animated mock-UI scenes and captions, using fonts, background and scripts bundled in the skill.
anthropics/skills
Applies Anthropic's brand colors and fonts to artifacts such as PowerPoint slides, using fixed hex values for text and accents, Poppins headings and Lora body text.
harry0703/MoneyPrinterTurbo
Installs and runs MoneyPrinterTurbo to turn a topic or script into a finished short video with voice-over, subtitles, stock footage and music.
heygen-com/hyperframes
Finds, generates and edits media for HyperFrames video projects: music, sound effects, images, icons, logos, voiceovers, captions and color grades.
EverettFish/holo-card-studio
Create collectible holographic foil cards and two-image lenticular flip cards with AI-generated full-color ukiyo-e and colored sumi-e anime artwork, layered Blender scenes, renders, GLB export, and…
Supreme-Ultimate/novel-to-script-team
Turns the character and scene lists from a director analysis into detailed text-to-image prompts for character sheets, scenes and props, after confirming a visual style with you.
Supreme-Ultimate/novel-to-script-team
Reviews costume, makeup and prop design prompts for characters and scenes in a novel-to-film pipeline, scoring each one and returning PASS or FAIL with a problem list.
Supreme-Ultimate/novel-to-script-team
Chinese-language skill that scores a generated short-drama script against a reference hit script on rhythm, dialogue style, emotional impact and structure, with PASS/FAIL thresholds.
Supreme-Ultimate/novel-to-script-team
Breaks a script or outline into plot points and writes a director's walkthrough, character list and scene list sized for Seedance video generation.
Supreme-Ultimate/novel-to-script-team
Turns a script, synopsis or scene outline into AI image prompts for storyboards, using a beat breakdown, a nine-panel Beat Board and four-panel Sequence Boards.
Supreme-Ultimate/novel-to-script-team
爆款剧本检索技能。使用混合搜索(语义+关键词)检索最相关的爆款剧本,为生成提供参考. An agent skill from Supreme-Ultimate/novel-to-script-team.
Categories
逐一对比技能。将生成剧本与每个参考剧本逐一对比,按照剧本评价标准给出详细批判和改进建议. An agent skill from Supreme-Ultimate/novel-to-script-team. One By One Comparison Skill is an agent skill from Supreme-Ultimate/novel-to-script-team.
One By One Comparison Skill fits situations like: media & Creative work in your project.
Run `npx skills add Supreme-Ultimate/novel-to-script-team --skill one-by-one-comparison-skill -a claude-code`. Or copy the skill folder (skills/one-by-one-comparison-skill in Supreme-Ultimate/novel-to-script-team) into .claude/skills/one-by-one-comparison-skill in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Supreme-Ultimate/novel-to-script-team --skill one-by-one-comparison-skill -a codex`. Or copy the skill folder (skills/one-by-one-comparison-skill in Supreme-Ultimate/novel-to-script-team) into .agents/skills/one-by-one-comparison-skill in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Supreme-Ultimate/novel-to-script-team --skill one-by-one-comparison-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/one-by-one-comparison-skill, .gemini/skills/one-by-one-comparison-skill, .github/skills/one-by-one-comparison-skill and .opencode/skills/one-by-one-comparison-skill in your project.
SKILL.md names no scripts, command-line tools or credentials: One By One Comparison Skill is instructions for the agent only. Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
One By One Comparison Skill is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with One By One Comparison Skill: Guizang Social Cards (op7418/guizang-social-card-skill, 7.4k stars), Weekly Changelog Video (heygen-com/hyperframes, 60k stars), Anthropic Brand Styling (anthropics/skills, 180k stars) and MoneyPrinterTurbo Video Generator (harry0703/MoneyPrinterTurbo, 129k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Supreme-Ultimate (a GitHub organization) maintains it in Supreme-Ultimate/novel-to-script-team, which has 175 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on May 2, 2026.
Source: Supreme-Ultimate/novel-to-script-team on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.