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 YYH211/Claude-meta-skill --skill software-copyright-writergit clone --depth 1 https://github.com/YYH211/Claude-meta-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/yyh211/claude-meta-skill/software-copyright-writer)<a href="https://agentmods.dev/skills/yyh211/claude-meta-skill/software-copyright-writer"><img src="https://agentmods.dev/badge/skills/yyh211/claude-meta-skill/software-copyright-writer/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/yyh211/claude-meta-skill/software-copyright-writer"><img src="https://agentmods.dev/badge/skills/yyh211/claude-meta-skill/software-copyright-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 431 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- medium MCP Rug Pull · line 420 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00124 | $0.05358 |
| Opus 5 | $0.00062 | $0.02679 |
| Sonnet 5 | $0.00025 | $0.01072 |
| Haiku 4.5 | $0.00012 | $0.00536 |
Grade A, and why
software-copyright-writer 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 12d 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 — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Software Copyright Writer
Overview
使用这个 skill 处理“根据代码仓库和官网材料写软著”的完整流程，而不是只写一篇泛泛的介绍文档。它面向任意软件产品或平台项目，不绑定某个特定产品、技术框架或行业。
先判断仓库里到底能拆出几个像样的软著主题，再补材料、写正文、整理源码原文、抓网页证据、导出 .docx。如果仓库体量根本撑不起用户要的数量，直接指出来，不要硬凑题目。
仓库和 GitHub 只作为内部分析输入。最终软著正文必须使用“软件/系统/平台/产品”的正式说明口径，介绍产品功能、业务流程、运行界面和技术实现，不要写成代码仓库分析报告。
Compliance Boundary
这个 skill 只用于整理真实软件项目的申报材料，不用于伪造软件、伪造截图、伪造权属、虚构功能或包装不存在的源码。
- 不能把设计稿、营销页或登录页冒充实际运行界面
- 不能虚构著作权人、备案页、商标证或版权声明
- 不能为了凑数量强拆高度重复的主题
- 不能把第三方源码、依赖代码或第三方版权信息当作自有源码提交
- 材料不足时必须列缺口和风险，不能直接编造补齐
Output Mode
默认采用“一次性成稿”模式：
- 只有在主题不明确、数量不合理或材料缺失时，才允许停下来提问或给候选方案
- 一旦主题已经确认、材料已经够用，就不要再输出提纲、半成品、分段草稿或中间解释
- 直接一次性输出完整软著正文，目标体量为“每页
30行、约30页、总字数3w-4w，通常约3.5w” - 源码文件同样一次性输出完整结果，不要分批次贴代码
- 如果用户直接要求“给我产 5 份软著”这类批量输出，且信息已经够用，就连续完成全部文档，不逐份中断确认
Workflow
1. 收集输入
先收集这些信息：
- 必填：
代码仓库、官网页面、软著数量 - 选填：
指定模块、已有截图、Logo/商标注册证、域名备案页、著作权人全称、偏粗拆/细拆
缺少关键输入时，先停在材料确认阶段，不要直接开写。
用 references/intake-checklist.md 检查材料完整性和硬性约束。
2. 理解仓库并生成候选主题
先看仓库结构、README、核心目录和页面入口，判断哪些能力可以独立描述为一个软著主题。
主题必须同时满足这些条件中的大部分：
- 有清晰业务目标
- 有独立功能闭环
- 有可配套的实际运行截图
- 有能指向该主题的代码范围
- 能写出和其他主题明显区分的正文
如果用户指定模块：
- 先判断模块体量是否足够支撑多个软著
- 同时给出
粗拆和细拆两套方案 - 说明每套方案的边界、风险和适用数量
如果用户没有指定模块：
- 先识别仓库内可独立申报的候选方向
- 再按用户要求的数量给主题组合建议
- 如果数量明显超出仓库体量，直接回绝不合理拆分
主题拆分规则和确认模板见 references/splitting-rules.md。
3. 确认主题或直接进入成稿
如果主题、数量和模块边界还不清楚，先输出候选主题让用户确认。
如果用户已经明确给出：
- 申报主体
- 软著数量
- 指定模块或明确主题
- 足够支撑写作的仓库和页面材料
那就不要再重复走“候选主题确认”流程，直接进入完整成稿。
确认输出里至少要包含：
- 主题名称
- 拆分粒度：
粗拆或细拆 - 主题边界
- 主要功能点
- 预计截图来源
- 预计
8-12张截图清单，优先10张，说明每张截图对应的功能点 - 预计源码范围
- 与其他主题的差异点
软著名称必须以 系统、平台、软件 或 app软件 结尾。
4. 准备材料和证据
用户确认主题后，再准备每个主题的材料。
必须重点检查这些硬规则：
- 出现
Logo时，必须要求商标注册证 - 文档文字或截图中出现的
版权所有，必须与著作权人全称完全一致 - 界面截图必须是软件实际运行界面，不能是设计稿或效果图
- 出现域名时，必须要求域名备案查询结果页
- 源码需满足前
1500行和后1500行，总计不少于3000行；不足则提供全部源码 - 保留源码注释，不要删除注释信息
- 不能保留第三方版权信息
- 正文必须扩写到足够支撑“每页
30行、约30页、总字数3w-4w，通常约3.5w”的申报体量 - 每篇软著默认规划
8-12张界面截图，优先按10张准备；除非产品界面确实不足，否则不要只放3-5张截图 - 最终正文不得出现
GitHub、仓库、repo、README、开源地址、提交记录、分支、clone等代码托管或代码分析口径，除非它们是软件自身界面中不可避免的功能名称 - 正文不要写“通过分析仓库发现”“本仓库包含”“GitHub 页面显示”等来源性表述；这些只属于内部分析过程，不属于软著产品介绍
What ships with it
12 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 292 B
- references/intake-checklist.md 5.3 KB
- references/source-info-template.md 2.1 KB
- references/splitting-rules.md 3.2 KB
- references/template-extended.md 8.3 KB
- references/template-standard.md 7.0 KB
- scripts/_fetch_web_evidence.mjs 9.1 KB runs code
- scripts/assemble_source_code.py 3.9 KB runs code
- scripts/export_ruanzhu_docx.py 17 KB runs code
- scripts/fetch_web_evidence.py 8.3 KB runs code
- scripts/package.json 95 B
- scripts/requirements.txt 19 B
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.
- 12d ago First seen · 466 lines · 124 tokens per session scan A 23e52fc4974c
software-copyright-writer is a skill published in the GitHub repository YYH211/Claude-meta-skill (277 stars, last pushed 4mo ago), licensed MIT. It adds 124 tokens to every session and 5,358 once invoked, about $0.0006 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
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.
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.