← Back to Skills Marketplace
flankechen

Chinese Script Check Skill

by flankechen · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ✓ Security Clean
308
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install chinese-script-check-skill
Description
Chinese Script checking/Proofreading/Polishing/Editing skill, optimized for Consistency Check/Goof Checking.中文剧本检查/校对/修改技能，穿帮检查/服化道一致性检查。
README (SKILL.md)

中文剧本检查技能

这个技能用于视频创作剧本的检查/校对，穿帮检查/服化道一致性检查。

使用场景

  • 用户需要检查/校对剧本
  • 用户需要对剧本进行修改

你的任务

作为一位细心的影视剧本校对员/编辑人员，对细节有着敏锐的眼光，并且精通中文，负责剧本的检查/审查。根据用户输入的剧本，进行仔细的检查/审查，将检查结果保存到文档以记录。

原则

  1. 保留原作者的语气和意图，避免改变作品内核。
  2. 对反馈要尊重和建设性。目标是帮助作者改进，而不是批评。
  3. 只针对剧本本身进行检查，不要延伸建议到策划案/分镜故事板/拍摄阶段。

工作流程

第一步

仔细逐字逐句阅读原剧本。

第二步

使用一个表，详细列出剧本中每个角色出现过的所有服化道（服装配饰、妆造、道具）。作为中间文件character_check.txt，保存到本地。 使用一个表，列出每个场景的环境描述。作为中间文件scene_check.txt，保存到本地。

第三步

仔细检查剧本，记录**“穿帮点”或“逻辑断裂”**等问题： 1.角色服化道（服装、妆造、道具）不一致，前后矛盾，穿帮点。严重程度:高。 核心道具的“瞬移”与功能性缺失；服装配饰的前后矛盾（如镜头1身穿衬衫，镜头2拉紧羽绒服）；时间线与物理状态的脱节；环境气候与服装逻辑的错位； 服化道必须场中保持一致，常见状态对齐，物理跟踪。 2.剧情矛盾不符合常理逻辑。严重程度:高。 3.语句表达或句子结构语法错误。严重程度:中。 4.其他问题。严重程度:低。

第四步

输出所有问题，按照严重程度从高到低排序，输出到 QUESTION.md。使用以下格式输出:

剧本检查问题记录

问题1:概括，严重程度:高｜中｜低

  • 问题描述:
  • 改进建议: 问题2:概括，严重程度:高｜中｜低
  • 问题描述:
  • 改进建议: ......
Usage Guidance
This skill appears coherent and matches its description, but it will create files in the agent's workspace (character_check.txt, scene_check.txt, QUESTION.md). If your scripts contain sensitive material, confirm where those files are stored and who can access them, or ask the agent not to write files and instead return results inline. Because the skill is instruction-only, there are no downloads or external credentials requested. If you need stronger guarantees, request that outputs be returned in the chat only and that any temporary files be deleted after review.
Capability Analysis
Type: OpenClaw Skill Name: chinese-script-check-skill Version: 0.1.0 The skill bundle is a legitimate tool for proofreading Chinese scripts and checking for continuity errors. It contains only metadata and natural language instructions (SKILL.md) for an AI agent to analyze text and save findings to local files (character_check.txt, scene_check.txt, and QUESTION.md), with no evidence of malicious code, data exfiltration, or harmful prompt injection.
Capability Assessment
✓ Purpose & Capability
Name and description match the instructions: a Chinese-language script checking/proofreading/editing workflow. No unrelated binaries, credentials, or install steps are requested.
ℹ Instruction Scope
Instructions are scoped to reading the provided script, producing consistency checks, and saving results. They explicitly ask the agent to save intermediate files (character_check.txt, scene_check.txt) and an output file (QUESTION.md) to local storage — this is consistent with a proofreading workflow but you should be aware the skill writes user content to the agent workspace.
✓ Install Mechanism
No install spec or code files; instruction-only skill (lowest install risk).
✓ Credentials
No environment variables, credentials, or config paths are requested; required access is proportional to the stated purpose.
✓ Persistence & Privilege
always is false and the skill does not request elevated or persistent privileges or modify other skills. Autonomous invocation is allowed but is the platform default.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install chinese-script-check-skill
  3. After installation, invoke the skill by name or use /chinese-script-check-skill
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
chinese-script-check-skill v0.1.0 - Initial release of a Chinese script checking and editing skill. - Provides comprehensive proofreading and consistency checks for scripts, focusing on costume/prop continuity and logical coherence. - Generates structured reports on script issues, categorized by severity. - Saves detailed role and scene information to intermediate files for deeper review. - Emphasizes respectful, constructive feedback while maintaining the script’s original style and intention.
Metadata
Slug chinese-script-check-skill
Version 0.1.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Chinese Script Check Skill?

Chinese Script checking/Proofreading/Polishing/Editing skill, optimized for Consistency Check/Goof Checking.中文剧本检查/校对/修改技能，穿帮检查/服化道一致性检查。 It is an AI Agent Skill for Claude Code / OpenClaw, with 308 downloads so far.

How do I install Chinese Script Check Skill?

Run "/install chinese-script-check-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Chinese Script Check Skill free?

Yes, Chinese Script Check Skill is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Chinese Script Check Skill support?

Chinese Script Check Skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Chinese Script Check Skill?

It is built and maintained by flankechen (@flankechen); the current version is v0.1.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments