Agent skill

Softcopyright

by peterfei in peterfei/ai-agent-team

智能软件著作权申请材料生成工具。自动分析项目源码,生成符合软著申请要求的软件说明书和源代码文档。支持关键词搜索、智能源码分析、格式化输出和PDF导出。

MITAuto-check passedDocuments & Office

Install Softcopyright

skills CLI
$ npx skills add peterfei/ai-agent-team --skill softcopyright -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install peterfei/ai-agent-team softcopyright --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/peterfei/ai-agent-team.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/softcopyright .claude/skills/softcopyright && rm -rf skills-src

Use ~/.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/

Facts

Skill name
softcopyright
GitHub stars
441
Token cost
~1.1k tokens
SKILL.md length
258 words
Files
59 (incl. scripts)
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

智能软件著作权申请材料生成工具。自动分析项目源码,生成符合软著申请要求的软件说明书和源代码文档。支持关键词搜索、智能源码分析、格式化输出和PDF导出。

  • Works in 5 steps: 读取用户输入,如果是关键词则先搜索相关内容 → 分析项目源码结构和内容 → 生成详细的软件说明书(约2000-3000字) → …
  • Tasks that involve PDF
  • SKILL.md covers 概述, 支持的触发指令, 工作流程 and 工具脚本使用说明, plus 8 more sections
  • Runs JavaScript and Shell scripts from its folder; calls node, npm and nvm

What it does

Softcopyright is an agent skill from peterfei/ai-agent-team. 智能软件著作权申请材料生成工具。自动分析项目源码,生成符合软著申请要求的软件说明书和源代码文档。支持关键词搜索、智能源码分析、格式化输出和PDF导出。

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 59 other files, including scripts (for example `CHANGELOG.md`, `IMPLEMENTATION_REPORT.md` and `PERFORMANCE_OPTIMIZATION.md`).

It sits in Documents & Office, covering PDF. It works with React. The repository describes itself as: AI Agent Team-拥有24/7专业AI开发团队:产品经理、前端开发、后端开发、测试工程师、DevOps工程师、技术负责人。一键安装,支持中英文命令,大幅提升开发效率!. The licence is MIT.

When your agent uses it

  • Tasks that involve PDF

Example prompts

  • “/softcopyright”

Requirements

  • Node.js
  • A Bash shell

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 读取用户输入,如果是关键词则先搜索相关内容
  2. 分析项目源码结构和内容
  3. 生成详细的软件说明书(约2000-3000字)
  4. 生成符合要求的源代码文档(60页,每页50行)
  5. 导出为PDF格式供软著申请使用

What it can do on your machine

Read from SKILL.md and the folder at commit 9d85024. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    Ships 5 files in scripts/ (JavaScript and Shell, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • node
    • npm
    • nvm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Softcopyright loads about 1.1k tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 258 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~22
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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.

Safety

Auto-check passed

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); the scripts in this folder are not scanned.

SKILL.md

The full file from peterfei/ai-agent-team at commit 9d85024, republished under its MIT licence (© peterfei). 258 words, ~1,112 tokens.

Download SKILL.mdSave it as .claude/skills/softcopyright/SKILL.md (or your agent's skills folder). This skill also uses 58 other files; get the full folder from GitHub.
name
softcopyright
description
智能软件著作权申请材料生成工具。自动分析项目源码,生成符合软著申请要求的软件说明书和源代码文档。支持关键词搜索、智能源码分析、格式化输出和PDF导出。
license
MIT

SoftCopyright - 智能软件著作权申请材料生成工具

概述

当用户需要申请软件著作权时,此 skill 会自动完成以下流程:

  1. 读取用户输入,如果是关键词则先搜索相关内容
  2. 分析项目源码结构和内容
  3. 生成详细的软件说明书(约2000-3000字)
  4. 生成符合要求的源代码文档(60页,每页50行)
  5. 导出为PDF格式供软著申请使用

支持的触发指令

用户可以通过以下方式触发此 skill:

  • "帮我生成软著申请材料" - 处理当前目录项目
  • "生成软件说明书" - 仅生成软件说明书
  • "生成源代码文档" - 仅生成源代码文档
  • 任何关键词 - 首先搜索相关内容,然后询问是否生成软著材料

工作流程

步骤 1: 理解用户意图

首先判断用户输入的类型:

javascript
// 检查用户输入类型
if (用户输入包含 "软著" || "著作权") {
  生成类型 = "全部材料"
} else if (用户输入包含 "软件说明书") {
  生成类型 = "说明书"
} else if (用户输入包含 "源代码" || "源码") {
  生成类型 = "源代码文档"
} else if (用户输入是关键词) {
  先搜索相关内容
  询问用户是否生成软著材料
}
步骤 2: 项目路径确认
javascript
// 默认使用当前目录
let projectPath = process.cwd()

// 询问用户确认路径
await confirmProjectPath(projectPath)
步骤 3: 使用CLI生成软著材料

推荐使用CLI工具生成软著材料:

bash
# 方式1: 使用关键词触发index.js(交互式)
cd ~/.claude/skills/softcopyright
node scripts/index.js 软著

# 方式2: 使用cli.js直接生成(推荐)
node scripts/cli.js generate --project <项目路径>

# 方式3: 使用快捷命令(最佳体验)
~/.claude/skills/softcopyright/softcopyright-generate --project . --auto-pdf

# 方式4: 技能系统自动调用
用户输入"帮我生成软著" → 自动执行: softcopyright-generate --project . --auto-pdf

该工具会:

  • 自动扫描项目源码
  • 识别源代码文件类型
  • 分析项目结构和技术栈
  • 生成HTML格式的软件说明书和源代码文档
  • 询问用户是否自动在浏览器中打开并打印为PDF
步骤 4: 生成选项

用户可以选择:

  1. 生成全部材料(软件说明书 + 源代码文档)
  2. 仅生成软件说明书
  3. 仅生成源代码文档
  4. 仅查看项目统计
步骤 5: 输出位置

默认输出路径: <项目目录>/softcopyright-output/

生成的文件:

  • 软件说明书_<项目名>_<时间戳>.html
  • 源代码文档_<项目名>_<时间戳>.html
步骤 6: 导出PDF

有两种方式将HTML转换为PDF:

方式1: 自动转换(推荐)

bash
# 添加--auto-pdf选项
node scripts/cli.js generate --project <项目路径> --auto-pdf
  • 自动在浏览器中打开HTML
  • 3秒后自动弹出打印对话框
  • 选择"保存为PDF"即可

方式2: 手动转换

  1. 在浏览器中打开生成的HTML文件
  2. 按 Cmd+P (macOS) 或 Ctrl+P (Windows/Linux)
  3. 在打印设置中:
    • 展开"更多设置"
    • 勾选"页眉和页脚"
    • 选择"保存为PDF"
  4. 保存PDF文件

工具脚本使用说明

scanner.js - 源码扫描工具

扫描项目目录并分析结构:

bash
node ~/.claude/skills/softcopyright/scripts/scanner.js <项目路径>

输出项目分析的JSON文件。

doc-generator.js - 软件说明书生成器

生成详细的软件说明书:

bash
node ~/.claude/skills/softcopyright/scripts/doc-generator.js \
  --type manual \
  --input <项目分析JSON> \
  --template <模板文件> \
  --output <输出PDF路径>
source-exporter.js - 源代码文档生成器

生成符合软著要求的源代码文档:

bash
node ~/.claude/skills/softcopyright/scripts/source-exporter.js \
  --input <源码目录> \
  --output <输出PDF路径> \
  --pages 60 \
  --lines-per-page 50

使用示例

示例 1: 完整软著材料生成

用户: "帮我生成软著申请材料"

Claude 执行流程:

  1. 确认项目路径:当前目录
  2. 运行源码扫描工具
  3. 分析项目结构和技术栈
  4. 生成软件说明书
  5. 生成源代码文档
  6. 导出PDF文件
  7. 向用户展示生成结果
示例 2: 关键词搜索后生成

用户: "React电商系统"

Claude 执行流程:

  1. 搜索"React电商系统"相关信息
  2. 展示搜索结果
  3. 询问:"是否需要为React电商系统生成软著申请材料?"
  4. 用户确认后执行完整生成流程
示例 3: 仅生成软件说明书

用户: "帮我生成软件说明书"

Claude 执行流程:

  1. 扫描项目源码
  2. 分析项目功能
  3. 生成软件说明书
  4. 导出PDF文件

输出文件规范

软件说明书PDF
  • 文件名:软件说明书_项目名称_YYYYMMDD.pdf
  • 字数要求:2000-3000字
  • 包含所有必需章节
  • 专业排版和格式
源代码文档PDF
  • 文件名:源代码文档_项目名称_YYYYMMDD.pdf
  • 页数要求:60页(或处理全部代码)
  • 每页行数:不少于50行
  • 无注释和无版权信息
  • 代码连续性保证

软件著作权申请要求

源代码文档要求
  1. 页数要求:通常需要20-60页
  2. 格式要求:每页不超过50行代码
  3. 注释要求:需要移除所有注释,只保留纯代码
  4. 页眉页脚:需要包含软件名称和版本号
  5. 代码连续性:需要保证代码的连续性和完整性
软件说明书要求
  1. 内容详实:约2000-3000字
  2. 结构完整:包含所有必需章节
  3. 重点突出:突出软件的独创性
  4. 专业描述:使用专业的技术描述

技术栈

  • Node.js: 主要运行环境
  • PDFKit: PDF文档生成
  • glob: 文件模式匹配
  • commander: CLI参数解析
  • chalk: 终端颜色输出
  • inquirer: 交互式命令行界面

依赖安装

使用 nvm 管理 Node.js 版本:

bash
# 确保使用合适的 Node 版本
nvm use 18

# 安装依赖
cd ~/.claude/skills/softcopyright
npm install

最佳实践

  1. 项目分析准确: 确保正确识别项目类型和技术栈
  2. 内容详实专业: 生成专业的技术描述和功能说明
  3. 格式规范合规: 严格按照软著申请要求格式化
  4. 用户交互友好: 提供清晰的进度提示和确认流程
  5. 文档完整性: 确保生成材料的完整性和准确性

安全注意事项

  1. 源码安全: 不修改原始源码,只读取和分析
  2. 隐私保护: 不上传源码到外部服务
  3. 本地处理: 所有处理都在本地完成
  4. 用户确认: 重要操作前需要用户确认

故障排除

扫描失败
bash
# 检查项目路径
ls -la <项目路径>

# 检查权限
chmod -R 755 <项目路径>
PDF生成失败
bash
# 检查依赖安装
cd ~/.claude/skills/softcopyright
npm list

# 重新安装依赖
npm install
内存不足

对于大型项目,可以:

  1. 排除不必要的目录(node_modules, .git等)
  2. 分批处理源码文件
  3. 增加Node.js内存限制

开发和扩展

要添加新的文件类型支持,编辑 scripts/scanner.js:

javascript
const SUPPORTED_EXTENSIONS = {
  '.rs': {
    'single_line': '//',
    'multi_line': ['/*', '*/'],
    'language': 'rust'
  },
  '.go': {
    'single_line': '//',
    'multi_line': ['/*', '*/'],
    'language': 'go'
  }
}

版本: 1.0.0 作者: peterfei 许可: MIT

© peterfei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 58 other files (scripts) in .claude/skills/softcopyright of peterfei/ai-agent-team.

  • SKILL.md
  • .npmignore
  • CHANGELOG.md
  • IMPLEMENTATION_REPORT.md
  • LICENSE
  • PERFORMANCE_OPTIMIZATION.md
  • PERFORMANCE_OPTIMIZATION_SUMMARY.md
  • PERFORMANCE_QUICK_START.md
  • README.md
  • TESTING_GUIDE.md
  • USAGE_EXAMPLES.md
  • demo-keywords.md
  • install.sh
  • package-lock.json
  • package.json
  • scripts/auto-pdf-generator.js
  • scripts/auto-print-pdf.js
  • scripts/chinese-pdf-fix.js
  • scripts/cli.js
  • scripts/doc-generator-english.js
  • … and 39 more

Open the folder on GitHubat commit 9d85024

Compare with similar skills

Softcopyright 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.

Softcopyright compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Softcopyright this skillpeterfei/ai-agent-team441—~1.1kAutomated safety check: PassMIT
React PDFmolefrog/skills172—~2.9kAutomated safety check: PassMIT
Openfdd Typst Rcx Reportbbartling/open-fdd172—~5.1kAutomated safety check: PassCustom licence
Edit PDFSimplePDF/simplepdf-embed407—~1.5kAutomated safety check: PassMIT
Build With SimplepdfSimplePDF/simplepdf-embed407—~7kAutomated safety check: PassMIT
React PDFtrailofbits/skills-curated512—~3.1kAutomated safety check: NotesCC-BY-SA-4.0

Similar skills

  • React PDF

    molefrog/skills

    Generate PDF documents using React-PDF library (@react-pdf/renderer).

    172 GitHub stars~2.9k tokensUpdated 7 mo ago
    Documents & OfficeAuto-check passed
  • Openfdd Typst Rcx Report

    bbartling/open-fdd

    Build engineer-facing Typst lab PDFs from live DataFusion Overview / RCx / Inspect APIs.

    172 GitHub stars~5.1k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Edit PDF

    SimplePDF/simplepdf-embed

    Edit and fill PDF documents. An agent skill from SimplePDF/simplepdf-embed.

    407 GitHub stars~1.5k tokensUpdated 8 days ago
    Documents & OfficeAuto-check passed
  • Build With Simplepdf

    SimplePDF/simplepdf-embed

    Integrate SimplePDF into a web application for PDF viewing, editing, filling, signing, programmatic control, AI-agent interaction, human-in-the-loop form prefilling, submissions, webhooks, or…

    407 GitHub stars~7k tokensUpdated 8 days ago
    Documents & OfficeAuto-check passed
  • React PDF

    trailofbits/skills-curated

    Official

    Generates PDF documents using the React-PDF library (@react-pdf/renderer) with TypeScript and JSX.

    512 GitHub stars~3.1k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check: notes
  • Multi Surface Render

    yonatangross/orchestkit

    Multi-surface rendering with json-render — one JSON spec produces React web, Next.js, React Native, Ink terminal UIs, PDFs, emails, Remotion videos, OG images, and 3D scenes.

    289 GitHub stars~4k tokensUpdated today
    Media & CreativeAuto-check passed

More from peterfei/ai-agent-team

All 10 skills in this repo
  • Drawnote Skill

    peterfei/ai-agent-team

    智能笔记与流程图绘制工具(优化版-无权限读取)。根据用户提供的内容,自动生成精美的可视化笔记和流程图,支持多种风格(手写笔记、思维导图、流程图等),并导出为图片。使用内置模板,无需读取文件权限。适用于:(1) 学习笔记可视化,(2) 知识梳理与总结,(3) 流程图绘制,(4) 概念解释图表

    441 GitHub stars~2.1k tokensUpdated 3 mo ago
    Auto-check passed
  • Tidymydesktop

    peterfei/ai-agent-team

    智能桌面和目录整理工具。根据用户提示词自动分类、整理文件和应用程序图标,去除重复版本,生成整理报告。支持整理桌面或指定目录。

    441 GitHub stars~1.2k tokensUpdated 3 mo ago
    Auto-check passed
  • Backend Dev Agent

    peterfei/ai-agent-team

    后端开发 Agent — API 设计、数据库优化、服务器端逻辑、认证授权、性能优化. An agent skill from peterfei/ai-agent-team.

    441 GitHub stars~966 tokensUpdated 3 mo ago
    Auto-check passed
  • Changelog Generator

    peterfei/ai-agent-team

    智能变更日志生成器 - 自动分析Git提交历史,生成符合规范的CHANGELOG.md。支持语义化版本管理、多种输出格式、增量更新和GitHub/GitLab集成。

    441 GitHub stars~2k tokensUpdated 3 mo ago
    Auto-check passed
  • Devops Engineer Agent

    peterfei/ai-agent-team

    DevOps 工程师 Agent — CI/CD 流水线、容器化与 K8s、基础设施即代码、可观测性. An agent skill from peterfei/ai-agent-team.

    441 GitHub stars~1k tokensUpdated 3 mo ago
    Auto-check passed
  • Tech Leader Agent

    peterfei/ai-agent-team

    技术负责人 Agent — 技术架构决策、代码审查、团队技术管理、技术规划与路线图. An agent skill from peterfei/ai-agent-team.

    441 GitHub stars~845 tokensUpdated 3 mo ago
    Auto-check passed

Works with

Questions about Softcopyright

What does Softcopyright do?

智能软件著作权申请材料生成工具。自动分析项目源码,生成符合软著申请要求的软件说明书和源代码文档。支持关键词搜索、智能源码分析、格式化输出和PDF导出。. Softcopyright is an agent skill from peterfei/ai-agent-team.

When should I use Softcopyright?

Softcopyright fits situations like: tasks that involve PDF.

How do I install Softcopyright in Claude Code?

Run `npx skills add peterfei/ai-agent-team --skill softcopyright -a claude-code`. Or copy the skill folder (.claude/skills/softcopyright in peterfei/ai-agent-team) into .claude/skills/softcopyright in your project. Claude Code loads it when a task matches its description.

How do I install Softcopyright in Codex?

Run `npx skills add peterfei/ai-agent-team --skill softcopyright -a codex`. Or copy the skill folder (.claude/skills/softcopyright in peterfei/ai-agent-team) into .agents/skills/softcopyright in your project. Codex loads it when a task matches its description.

Can I use Softcopyright in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add peterfei/ai-agent-team --skill softcopyright -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/softcopyright, .gemini/skills/softcopyright, .github/skills/softcopyright and .opencode/skills/softcopyright in your project.

What does Softcopyright need to run?

Going by SKILL.md and its folder, Softcopyright needs JavaScript and a shell for the scripts in its folder and the command-line tools its instructions call (node, npm and nvm). Our summary lists: Node.js; A Bash shell.

Does Softcopyright access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Softcopyright safe to install?

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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Softcopyright use?

Softcopyright is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Softcopyright use?

About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Softcopyright?

Skills that share tags, products or a category with Softcopyright: React PDF (molefrog/skills, 172 stars), Openfdd Typst Rcx Report (bbartling/open-fdd, 172 stars), Edit PDF (SimplePDF/simplepdf-embed, 407 stars) and Build With Simplepdf (SimplePDF/simplepdf-embed, 407 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Softcopyright?

peterfei (a GitHub user) maintains it in peterfei/ai-agent-team, which has 441 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on June 29, 2026.

Source: peterfei/ai-agent-team on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.