file-trademark

file-trademark is a skill for Claude Code, Codex from ThomasMoreAI/legal-skills-open. It costs 120 tokens per session (5,930 once invoked), scanned A, original, Apache-2.0.

A guide to applying for trademark protection through EUIPO for the European Union, USPTO for the United States, or WIPO’s Madrid System for international coverage. It covers the application choices, required information, and later office responses or monitoring.

In plain words
What is it for?
Use it to prepare trademark applications, choose between EU, US, and international routes, claim priority, respond during examination, or draft an open-source trademark policy.
Why use it?
It helps organise the filing process after a trademark conflict check has found no major problems. It reduces uncertainty about which office, goods and services classes, and filing basis to use.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to prepare trademark applications, choose between EU, US, and international routes, claim priority, respond during examination, or draft an open-source trademark policy.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thomasmoreai/legal-skills-open/file-trademark
Install

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.

Any agent
npx skills add ThomasMoreAI/legal-skills-open --skill file-trademark
Clone the repo
git clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-open

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for file-trademark

README.md
[![agentmods](https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/file-trademark/github.svg)](https://agentmods.dev/skills/thomasmoreai/legal-skills-open/file-trademark)
Your own site
<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/file-trademark"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/file-trademark/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.

agentmods 80×15 button for file-trademark

Your own site · 80×15
<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/file-trademark"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/file-trademark.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,930 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00120 $0.05930
Opus 5 $0.00060 $0.02965
Sonnet 5 $0.00024 $0.01186
Haiku 4.5 $0.00012 $0.00593

Measured 9d ago against content hash b6eedae0a986, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

file-trademark 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 9d 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.

cross-jurisdiction/ip/skills/file-trademark/SKILL.md · 355 lines

How it starts

The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.

申请商标

向 EUIPO(欧盟)、USPTO(美国)或 WIPO Madrid Protocol(国际)提交商标申请。本技能涵盖实际申请步骤 —— 从申请前验证到注册后监视和开源商标政策。它假定冲突筛查已通过 screen-trademark 完成。

适用场景

  • 在冲突筛查清晰后准备好提交商标申请
  • 在欧盟、美国或国际申请策略之间选择
  • 申请欧盟商标并为后续美国申请主张优先权
  • 通过 Madrid Protocol 将现有国家商标扩展到国际
  • 在注册后起草开源商标使用政策
  • 在审查期间响应办公室行动或异议程序

输入

  • 必需:要申请的商标(文字、徽标或组合)
  • 必需:商品和服务描述
  • 必需:目标司法管辖区(欧盟、美国、国际或组合)
  • 必需:申请人姓名和地址
  • 可选:Screen-trademark 结果(冲突搜索报告)
  • 可选:徽标文件(若申请图形或组合商标)
  • 可选:优先权主张(在另一司法管辖区的较早申请,6 个月内)
  • 可选:商业使用证明(USPTO 1(a) 基础所需)
  • 可选:开源项目上下文(用于第 10 步的商标政策)

申请费用参考

办公室 基本费用 每类别 备注
EUIPO 850 EUR +50 EUR(第 2 类)、+150 EUR(第 3 类+) SME Fund:75% 退款
USPTO(TEAS Plus) $250 每类 外国申请人需要美国律师
USPTO(TEAS Standard) $350 每类 商品描述更灵活
Madrid Protocol 653 CHF 因国家而异 5 年内依赖基础商标

步骤

第 1 步:申请前检查

在投入申请费用前验证商标已可申请。

  1. 确认 screen-trademark 已运行:
    • 审查冲突搜索报告中的相同或令人混淆的相似商标
    • 验证所有目标司法管辖区都包含在筛查中
    • 检查筛查是最近的(理想为过去 30 天内)
  2. 在官方数据库中运行最终冲突检查:
    • EUIPO TMview:跨所有欧盟成员国注册搜索
    • WIPO Global Brand Database:国际注册
    • USPTO TESS:美国联邦注册(使用结构化搜索:"mark text"[BI]
    • DPMAregister:德国国家注册(若申请欧盟,覆盖最大欧盟市场)
  3. 验证域名和社交媒体句柄可用或已锁定:
    • 域名可用性强化独特性论点(若被挑战)
    • 匹配句柄减少消费者混淆风险
  4. 将搜索结果记录为申请前清晰记录

预期结果: 确认目标司法管辖区中不存在阻塞商标。申请前清晰记录记录尽职调查并支持任何未来异议辩护。

失败处理: 若发现冲突商标,评估严重性:相同商标 + 相同商品 = 不要申请。相似商标 + 相关商品 = 寻求关于混淆可能性的法律咨询。若冲突仅限于单一司法管辖区,考虑仅在清晰司法管辖区申请。

第 2 步:Nice 分类选择

在 Nice 分类系统下识别正确的商品和服务类别。

  1. 咨询 TMclass 工具(tmclass.tmdn.org)进行类别识别:
    • 输入商品/服务描述
    • TMclass 建议大多数办公室接受的协调术语
    • 使用 TMclass 数据库的预先批准术语减少审查延迟
  2. 技术和软件的常见类别:
    • 第 9 类:可下载软件、移动应用、计算机硬件
    • 第 35 类:广告、商业管理、SaaS 平台管理
    • 第 42 类:SaaS、云计算、软件开发服务
    • 第 38 类:电信、在线平台、消息服务
  3. 起草商品和服务描述:
    • 足够具体以定义您的实际使用,但足够广泛以便未来扩展
    • TEAS Plus(USPTO)要求来自 ID Manual 的术语 —— 使用预先批准的术语
    • EUIPO 直接接受 TMclass 协调术语
  4. 平衡成本与覆盖:
    • 每个额外类别增加费用(见上面的费用表)
    • 在您当前使用或打算使用商标的类别中申请
    • 没有使用的过广申请可能被挑战(特别是在美国)

预期结果: 一份最终的 Nice 类别列表,附每个类别的具体、预先批准的商品和服务描述。描述匹配实际业务使用。

Read the full file on GitHub · 355 lines

Changes

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.

  1. 9d ago First seen · 355 lines · 120 tokens per session scan A b6eedae0a986

Subscribe to this mod's changes

file-trademark is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (72 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 120 tokens to every session and 5,930 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 2026-09-03.