Borrowing it
Nothing to install: this file belongs to peterfei/ai-agent-team. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/peterfei/ai-agent-team/main/.claude/skills/softcopyright/SKILL.mdgit clone --depth 1 https://github.com/peterfei/ai-agent-teamWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/peterfei/ai-agent-team/softcopyright)<a href="https://agentmods.dev/skills/peterfei/ai-agent-team/softcopyright"><img src="https://agentmods.dev/badge/skills/peterfei/ai-agent-team/softcopyright.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00049 | $0.02256 |
| Opus 5 | $0.00024 | $0.01128 |
| Sonnet 5 | $0.00010 | $0.00451 |
| Haiku 4.5 | $0.00005 | $0.00226 |
Grade A, and why
softcopyright scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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：
- 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）
- 生成符合要求的源代码文档（60页，每页50行）
- 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：
// 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
// 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：
# 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：
- 生成全部材料（软件说明书 + 源代码文档）
- 仅生成软件说明书
- 仅生成源代码文档
- 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）
# 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
- 在浏览器中打开生成的HTML文件
- 按 Cmd+P (macOS) 或 Ctrl+P (Windows/Linux)
- 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"
- 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：
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：
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>
What ships with it
57 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .npmignore 14 B
- CHANGELOG.md 6.8 KB
- demo-keywords.md 2.5 KB
- IMPLEMENTATION_REPORT.md 7.5 KB
- install.sh 1.5 KB runs code
- LICENSE 1.0 KB
- package-lock.json 123 KB
- package.json 1.1 KB
- PERFORMANCE_OPTIMIZATION_SUMMARY.md 7.8 KB
- PERFORMANCE_OPTIMIZATION.md 4.0 KB
- PERFORMANCE_QUICK_START.md 6.6 KB
- README.md 6.5 KB
- scripts/auto-pdf-generator.js 5.2 KB runs code
- scripts/auto-print-pdf.js 7.1 KB runs code
- scripts/chinese-pdf-fix.js 4.0 KB runs code
- scripts/cli.js 5.9 KB runs code
- scripts/doc-generator-english.js 13 KB runs code
- scripts/doc-generator-new.js 624 B runs code
- scripts/doc-generator.js 28 KB runs code
- scripts/font-manager.js 5.7 KB runs code
- scripts/html-pdf-generator.js 17 KB runs code
- scripts/html-source-exporter.js 31 KB runs code
- scripts/html-to-pdf.js 5.6 KB runs code
- scripts/index.js 17 KB runs code
- scripts/index.js.pdf-backup 12 KB
- scripts/run.bat 463 B runs code
- scripts/run.sh 893 B runs code
- scripts/scanner-optimized.js 22 KB runs code
- scripts/scanner.js 22 KB runs code
- scripts/simple-doc-generator.js 26 KB runs code
- scripts/simple-pdf-generator.js 14 KB runs code
- scripts/simple-source-exporter.js 4.6 KB runs code
- scripts/source-exporter.js 13 KB runs code
- scripts/system-chrome-pdf.js 7.0 KB runs code
- scripts/utils-optimized.js 4.8 KB runs code
- scripts/utils.js 9.2 KB runs code
- softcopyright 150 B
- softcopyright-generate 168 B
- softcopyright-generate.bat 194 B runs code
- softcopyright-manual 169 B
- softcopyright-manual.bat 195 B runs code
- softcopyright-source 169 B
- softcopyright-source.bat 195 B runs code
- softcopyright.bat 176 B runs code
- templates/software-manual.md 6.0 KB
- test-auto-pdf.js 636 B runs code
- test-clean-header-footer.js 2.3 KB runs code
- test-complete.js 848 B runs code
- test-counter-fix.js 2.3 KB runs code
- test-fixed-page-number.js 2.4 KB runs code
- test-html-generation.js 2.9 KB runs code
- test-html.js 732 B runs code
- test-no-border.js 1.8 KB runs code
- test-pdf.js 639 B runs code
- test-performance.js 4.9 KB runs code
- TESTING_GUIDE.md 11 KB
- USAGE_EXAMPLES.md 8.4 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 312 lines · 49 tokens per session scan A a082f78da4a6
softcopyright is a skill published in the GitHub repository peterfei/ai-agent-team (431 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 2,256 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
meta-pdf-reformat-pipeline
Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.
patent-reader
A plain-language reader for Chinese patents that turns a publication number or PDF into notes, diagrams, and an Obsidian entry. Obsidian is a note-taking app that stores linked Markdown files.
software-copyright-materials
A workflow for creating Chinese application materials for software copyright registration from a real software project.
ectd-xml-compiler
Automatically convert uploaded drug application documents (Word/PDF) into XML skeleton structure compliant with eCTD 4.0/3.2.2 specifications.
audit-export
Export the full CocoAudit trail as a stakeholder-ready compliance document.
software-certificate-skill
An automated workflow for preparing Chinese software-copyright registration materials from a real software project. It produces application information, an operation manual, and source-code documents with evidence from the project.