Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →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。
.claude/skills/peterfei-softcopyright/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 145% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 173% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 185% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 136% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 171% | 0% |
当用户需要申请软件著作权时，此 skill 会自动完成以下流程：
用户可以通过以下方式触发此 skill：
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 }
javascript// 默认使用当前目录 let projectPath = process.cwd() // 询问用户确认路径 await confirmProjectPath(projectPath)
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：
用户可以选择：
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
方式2: 手动转换
扫描项目目录并分析结构：
bashnode ~/.claude/skills/softcopyright/scripts/scanner.js <项目路径>
输出项目分析的JSON文件。
生成详细的软件说明书：
bashnode ~/.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>
生成符合软著要求的源代码文档：
bashnode ~/.claude/skills/softcopyright/scripts/source-exporter.js \ --input <源码目录> \ --output <输出PDF路径> \ --pages 60 \ --lines-per-page 50
用户: "帮我生成软著申请材料"
Claude 执行流程:
用户: "React电商系统"
Claude 执行流程:
用户: "帮我生成软件说明书"
Claude 执行流程:
软件说明书_项目名称_YYYYMMDD.pdf源代码文档_项目名称_YYYYMMDD.pdf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
bash# 检查项目路径 ls -la <项目路径> # 检查权限 chmod -R 755 <项目路径>
bash# 检查依赖安装 cd ~/.claude/skills/softcopyright npm list # 重新安装依赖 npm install
对于大型项目，可以：
要添加新的文件类型支持，编辑 scripts/scanner.js：
javascriptconst 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
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 11,927 | 3,559 | -70% | 1 | 1 | 0% | 2,099 | 2,462 | +17% | 0 | 0 | — |
case-07 | fail→pass | 6,617 | 3,027 | -54% | 1 | 1 | 0% | 1,083 | 2,654 | +145% | 0 | 0 | — |
case-02 | fail→fail | 8,692 | 3,315 | -62% | 1 | 1 | 0% | 1,412 | 2,512 | +78% | 0 | 0 | — |
case-03 | fail→pass | 6,792 | 8,094 | +19% | 1 | 1 | 0% | 1,288 | 3,520 | +173% | 0 | 0 | — |
case-04 | pass→pass | 13,842 | 3,718 | -73% | 1 | 1 | 0% | 940 | 2,790 | +197% | 0 | 0 | — |
case-05 | fail→pass | 14,953 | 2,832 | -81% | 1 | 1 | 0% | 910 | 2,598 | +185% | 0 | 0 | — |
case-06 | fail→pass | 6,138 | 2,155 | -65% | 1 | 1 | 0% | 1,055 | 2,492 | +136% | 0 | 0 | — |
case-08 | fail→pass | 5,973 | 2,322 | -61% | 1 | 1 | 0% | 903 | 2,444 | +171% | 0 | 0 | — |
case-09 | fail→pass | 14,978 | 2,188 | -85% | 1 | 1 | 0% | 2,333 | 2,464 | +6% | 0 | 0 | — |
case-10 | pass→pass | 10,485 | 4,319 | -59% | 1 | 1 | 0% | 1,589 | 2,802 | +76% | 0 | 0 | — |
case-11 | pass→pass | 11,473 | 7,032 | -39% | 1 | 1 | 0% | 1,732 | 3,209 | +85% | 0 | 0 | — |
case-12 | pass→pass | 3,340 | 2,335 | -30% | 1 | 1 | 0% | 477 | 2,479 | +420% | 0 | 0 | — |
case-13 | pass→pass | 8,450 | 5,276 | -38% | 1 | 1 | 0% | 1,564 | 3,055 | +95% | 0 | 0 | — |
case-14 | fail→pass | 12,171 | 1,943 | -84% | 1 | 1 | 0% | 1,748 | 2,409 | +38% | 0 | 0 | — |
case-15 | fail→pass | 10,540 | 3,226 | -69% | 1 | 1 | 0% | 1,584 | 2,653 | +67% | 0 | 0 | — |
case-16 | fail→pass | 8,311 | 2,036 | -76% | 1 | 1 | 0% | 1,228 | 2,448 | +99% | 0 | 0 | — |
case-17 | fail→pass | 12,033 | 3,249 | -73% | 1 | 1 | 0% | 1,879 | 2,646 | +41% | 0 | 0 | — |
case-18 | fail→pass | 13,506 | 2,163 | -84% | 1 | 1 | 0% | 2,175 | 2,494 | +15% | 0 | 0 | — |
case-19 | fail→pass | 11,129 | 1,653 | -85% | 1 | 1 | 0% | 1,840 | 2,313 | +26% | 0 | 0 | — |
case-20 | pass→pass | 11,787 | 10,077 | -15% | 1 | 1 | 0% | 1,773 | 3,615 | +104% | 0 | 0 | — |
case-21 | pass→pass | 4,726 | 2,167 | -54% | 1 | 1 | 0% | 673 | 2,469 | +267% | 0 | 0 | — |
case-22 | fail→fail | 16,322 | 13,007 | -20% | 1 | 1 | 0% | 2,608 | 4,306 | +65% | 0 | 0 | — |
case-23 | fail→fail | 14,545 | 15,517 | +7% | 1 | 1 | 0% | 2,441 | 4,924 | +102% | 0 | 0 | — |
case-24 | fail→fail | 12,635 | 9,253 | -27% | 1 | 1 | 0% | 2,134 | 3,611 | +69% | 0 | 0 | — |
case-25 | fail→fail | 13,606 | 12,391 | -9% | 1 | 1 | 0% | 2,249 | 4,106 | +83% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 25 cases were attempted, and 24 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +48 percentage points is the difference between those two pass rates over the 24 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.