SoftwareCopyright-Skill is a coding-agent skill that reads a local software project and generates Chinese software copyright application documents, including application details, an operating manual, and source-code materials. Developers use it to prepare, review, and export these materials locally without using an outside document-preparation service. The catalogue entry contains the skill that performs this workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Fokkyp/SoftwareCopyright-Skill --skill software-copyright-materialsgit clone --depth 1 https://github.com/Fokkyp/SoftwareCopyright-SkillWrote 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/fokkyp/softwarecopyright-skill/software-copyright-materials)<a href="https://agentmods.dev/skills/fokkyp/softwarecopyright-skill/software-copyright-materials"><img src="https://agentmods.dev/badge/skills/fokkyp/softwarecopyright-skill/software-copyright-materials/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fokkyp/softwarecopyright-skill/software-copyright-materials"><img src="https://agentmods.dev/badge/skills/fokkyp/softwarecopyright-skill/software-copyright-materials.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00098 | $0.08492 |
| Opus 5.5 | $0.00039 | $0.03397 |
| Sonnet 5.5 | $0.00020 | $0.01698 |
| Haiku 4.5 | $0.00010 | $0.00849 |
Grade A, and why
software-copyright-materials 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 5d 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 — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.
软著申请资料生成
这个 skill 生成可审阅、可追溯的软著申请资料。核心原则:
- 固定输出目录:当前工作目录下的
软件著作权申请资料/。不要默认写到/tmp、/private/tmp或其他临时目录。 - 只有测试 skill 自身时才允许显式指定临时目录;面向用户生成材料时必须写入当前目录。
- 先生成 Markdown 草稿,用户确认后再生成正式 Word/TXT。
- 正式 Word/TXT 只能写入
软件著作权申请资料/正式资料/,不要散落在输出目录根部。 - 正式 Word/TXT 的文字一律使用默认黑色字体,不生成蓝色超链接、主题色标题或其他彩色文字;Markdown 链接写入 Word 时必须转成普通文本。
- 正式资料中的软件名称必须与
草稿/申请表信息.md的“软件全称”字段一致;正式生成时以已确认的申请表软件全称为准。 - 正式代码 Word 页眉中的版本号必须与
草稿/申请表信息.md的“版本号”字段一致;正式生成时以已确认的申请表版本号为准。 - 代码材料必须来自真实项目源码,禁止 AI 编造代码。
- 写申请表和操作手册前,必须先形成模型研判后的
草稿/业务理解.md/json,理解软件业务、行业、目标用户、核心价值和操作流程。 - 脚本只能收集项目证据、校验字段和生成文件;行业判断、功能抽取、代码抽取选择、操作手册结构必须由模型阅读项目后决定,不得依赖脚本关键字表或固定范本。
- 优先抽取前端代码:入口、路由、页面、核心组件、接口封装、状态管理、工具函数。
- 生成代码材料前,必须先生成代码文件候选清单;模型理解项目后填写抽取文件和选择理由,再让用户确认或修改。
- 代码优先抽取模型和用户确认的、最能体现软件真实功能和运行逻辑的源码;不足 60 页时,从其他相关源码文件补充到 60 页;候选源码仍不足 60 页时,才生成全部代码文档。
- 源码发现不得依赖编程语言扩展名白名单。脚本默认扫描可读文本文件,并排除明确的文档、配置、媒体、压缩包、二进制、生成物和超大文件;未知扩展名源码同样进入候选清单,再由模型和用户确认是否抽取。
- 业务证据收集必须发现项目中的文本设计资料以及 DOCX、PDF、ODT、DOC、WPS 等文档;能自动提取正文时写入证据,无法提取时也必须登记路径并提示模型进一步阅读,不能因格式不在文本扩展名列表中而静默遗漏。
- 操作手册成稿应像真实软件随附的操作说明,而不是研发说明、功能清单或 AI 生成的汇总文。
- 操作手册草稿必须按传统软著操作手册骨架组织:相关文档、说明、功能特点、系统要求、按真实页面/流程逐章操作、常见问题解答、术语表。一级章节标题使用中文大写序号,例如
一、相关文档,不得使用(1)、相关文档。相关文档必须用表格指向总体设计、详细设计、测试案例等配套文档。正文尽量使用连续段落,不使用项目符号列表或1. 2. 3.编号列表。 - 每个核心页面都要用普通用户视角说明页面用途、进入位置、用户可见内容、用户动作、输入限制或异常提示、结果反馈和截图预留。不得把章节写成“进入方式:/页面内容:/操作步骤:/操作规则:/操作结果与反馈:”这种字段模板;这些信息要自然合并到段落里。避免代码、框架、接口、状态管理、异步任务等技术化表达;撰写过程中由 agent 自行循环检查、扩写和修正,完整草稿完成后只向用户发起一次整体确认。
- 操作手册必须去除明显“AI 味”:避免空泛赞美、营销口号、万能句式、每章同一结构、头中尾固定结构、过度对称的排比、没有项目细节的正确废话、频繁使用“旨在、赋能、一站式、智能化、高效便捷、显著提升、强大能力、丰富功能”等套话。每段都应能回答“这个项目里这个功能具体做什么、用户看见什么、操作后有什么结果”。
- 操作手册生成必须同步输出
草稿/操作手册自检记录.md和草稿/操作手册自检记录.json,记录初稿、按项目流程扩写、去制式表达等自检轮次;如果前 3 轮仍发现问题,必须继续补写修正,直到问题清零或记录无法自动修复的原因后再停止。 - 截图方式只允许用户选择:Playwright CLI 自动截图或用户自行截图。用户选择自动截图后,先检查固定验证版本的
playwright-cli是否可用;如果用户说现在不截图、先跳过截图或截图失败,操作手册仍必须保留清晰可见的截图预留位置,正式 Word 中也要能看到。 - 申请表信息中的硬件/系统环境必须让用户确认或填写,不能硬编码。
- Word 生成统一使用 OfficeCLI 后端;Python 只负责业务分析、代码抽取、门禁和命令编排,不直接解包、重打包或写入 DOCX 包。OfficeCLI 完成正文写入后,必须通过
/theme+raw-set把主题字体统一为宋体(SimSun)和 Times New Roman,并重新读取主题确认 Calibri、Calibri Light、等线等默认主题字体已消失。 - OfficeCLI 固定验证版本为
1.0.151,运行时必须设置OFFICECLI_SKIP_UPDATE=1,不得静默升级、静默安装或回退到 python-docx/Pandoc/.NET 工具包。 - OfficeCLI 的安装、批处理、分页与校验细节见
references/officecli_backend.md。
What ships with it
25 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.
- agents/openai.yaml 235 B
- references/application_fields.md 5.2 KB
- references/business_understanding_rules.md 3.0 KB
- references/code_selection_rules.md 1.9 KB
- references/copyright_material_rules.md 1.6 KB
- references/manual_structure.md 5.9 KB
- references/officecli_backend.md 4.7 KB
- references/playwright_cli_screenshots.md 5.8 KB
- scripts/analyze_project.py 13 KB runs code
- scripts/build_docx_from_md.py 31 KB runs code
- scripts/capture_screenshots.py 2.7 KB runs code
- scripts/check_environment.py 6.5 KB runs code
- scripts/check_playwright_cli.py 5.9 KB runs code
- scripts/common.py 15 KB runs code
- scripts/confirm_stage.py 13 KB runs code
- scripts/extract_code_material.py 15 KB runs code
- scripts/generate_application_info.py 33 KB runs code
- scripts/generate_business_context.py 23 KB runs code
- scripts/generate_manual_draft.py 35 KB runs code
- scripts/officecli_backend.py 9.2 KB runs code
- scripts/propose_code_selection.py 8.0 KB runs code
- tests/test_code_layout.py 1.4 KB runs code
- tests/test_officecli_builder.py 10 KB runs code
- tests/test_source_discovery.py 3.8 KB runs code
- tests/test_workflow_integrity.py 6.6 KB runs code
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.
- 5d ago Changed df1616ee219b
- 1mo ago Changed · -18 lines · +1 tokens per session 1d17ca8d7d47
- 1mo ago First seen · 503 lines · 97 tokens per session scan A 51dde004da8b
software-copyright-materials is a skill published in the GitHub repository Fokkyp/SoftwareCopyright-Skill (6,036 stars, last pushed 6d ago), licensed MIT. It adds 98 tokens to every session and 8,492 once invoked, about $0.0004 per session on Opus 5.5. 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
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.
meta-pdf-reformat-pipeline
Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.
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.
court-sms
A workflow that reads court text messages or delivery links, extracts case details, downloads court documents, and files them in the matching case folder.
recht-report-pdf-momarcode1
Generates professional PDF reports with risk scores, cost estimates, and recommendations using ReportLab. Austrian law branding.