Paper to Chinese Patent Drafter
Yuan1z0825/nature-skills
Drafts Chinese invention patent applications and technical disclosures from research papers or inventor materials, tying each claim feature to source evidence.
When the user faces brand impersonation, fake websites, phishing sites, or trademark infringement.
Install Brand Protection
$ npx skills add kostja94/marketing-skills --skill brand-protection -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kostja94/marketing-skills brand-protection --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/kostja94/marketing-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/strategies/brand/brand-protection .claude/skills/brand-protection && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "brand-protection" agent skill from https://github.com/kostja94/marketing-skills/tree/main/skills/strategies/brand/brand-protection into .claude/skills/brand-protection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brand-protection", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/kostja94/marketing-skills/tree/main/skills/strategies/brand/brand-protectionType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add kostja94/marketing-skills --skill brand-protection -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kostja94/marketing-skills brand-protection --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kostja94/marketing-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/strategies/brand/brand-protection .agents/skills/brand-protection && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "brand-protection" agent skill from https://github.com/kostja94/marketing-skills/tree/main/skills/strategies/brand/brand-protection into .agents/skills/brand-protection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brand-protection", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kostja94/marketing-skills --skill brand-protection -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kostja94/marketing-skills brand-protection --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kostja94/marketing-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/strategies/brand/brand-protection .cursor/skills/brand-protection && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "brand-protection" agent skill from https://github.com/kostja94/marketing-skills/tree/main/skills/strategies/brand/brand-protection into .cursor/skills/brand-protection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brand-protection", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/kostja94/marketing-skills.git --path skills/strategies/brand/brand-protection--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add kostja94/marketing-skills --skill brand-protection -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kostja94/marketing-skills brand-protection --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kostja94/marketing-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/strategies/brand/brand-protection .gemini/skills/brand-protection && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "brand-protection" agent skill from https://github.com/kostja94/marketing-skills/tree/main/skills/strategies/brand/brand-protection into .gemini/skills/brand-protection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brand-protection", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install kostja94/marketing-skills brand-protectionInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add kostja94/marketing-skills --skill brand-protection -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/kostja94/marketing-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/strategies/brand/brand-protection .github/skills/brand-protection && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "brand-protection" agent skill from https://github.com/kostja94/marketing-skills/tree/main/skills/strategies/brand/brand-protection into .github/skills/brand-protection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brand-protection", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kostja94/marketing-skills --skill brand-protection -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install kostja94/marketing-skills brand-protection --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kostja94/marketing-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/strategies/brand/brand-protection .opencode/skills/brand-protection && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "brand-protection" agent skill from https://github.com/kostja94/marketing-skills/tree/main/skills/strategies/brand/brand-protection into .opencode/skills/brand-protection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "brand-protection", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
brand-protection- GitHub stars
- 1k
- Token cost
- ~2.4k tokens
- SKILL.md length
- 980 words
- Files
- 1
- Skills in repo
- 102
- Repo updated
- First seen
- Licence
- MIT
At a glance
When the user faces brand impersonation, fake websites, phishing sites, or trademark infringement.
- Works in 4 steps: Impersonation type: Fake website,… → Evidence available: Screenshots, URLs,… → Legal assets: Registered trademark,… → …
- Faces brand impersonation
- SKILL.md covers Initial Assessment, Evidence Collection Checklist, Reporting Channels (Priority… and Reporting Best Practices, plus 9 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Brand Protection is an agent skill from kostja94/marketing-skills. When the user faces brand impersonation, fake websites, phishing sites, or trademark infringement. Also use when the user mentions "fake site," "impersonation," "phishing site," "trademark infringement," "domain squatting," or "brand abuse." For monitoring, use brand-monitoring.
Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Legal & Compliance, covering Intellectual property. The repository describes itself as: Agent Skills for Marketing — SEO, Social, Influencer & More. 160+ open-source skills for SEO, content, 40+ page types, paid ads, channels, and strategies. Add project context… The licence is MIT.
When your agent uses it
- Faces brand impersonation
- Trademark infringement
- The user mentions fake site
- Domain squatting
Example prompts
- “fake site,”
- “impersonation,”
- “phishing site,”
- “/brand-protection”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Impersonation type: Fake website, phishing, trademark misuse, domain squatting
- Evidence available: Screenshots, URLs, WHOIS, hosting info
- Legal assets: Registered trademark, copyright ownership
- Impact: Traffic interception (fake site ranks for brand queries)? Payment fraud (users pay on fake site, then contact official support)?
What it can do on your machine
Read from SKILL.md and the folder at commit 8dd89c5. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
lookup.icann.orgsafebrowsing.google.comservices.google.combing.comicann.orgabuse.cloudflare.comlegalclarity.orgbrandshield.comcloudflare.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Brand Protection loads about 2.4k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 980 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from kostja94/marketing-skills at commit 8dd89c5, republished under its MIT licence (© kostja94). 980 words, ~2,376 tokens.
Download SKILL.mdSave it as
.claude/skills/brand-protection/SKILL.md (or your agent's skills folder).- name
- brand-protection
- description
- When the user faces brand impersonation, fake websites, phishing sites, or trademark infringement. Also use when the user mentions "fake site," "impersonation," "phishing site," "trademark infringement," "domain squatting," or "brand abuse." For monitoring, use brand-monitoring.
- metadata.version
- 1.0.1
Strategy: Brand Protection
Guides discovery, reporting, and prevention of brand impersonation—fake websites, phishing sites, trademark infringement, and domain squatting. See domain-selection for defensive domain registration; trust-badges for official site verification signals; about-page for identity declaration.
When invoking: On first use, if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.
Initial Assessment
Project context: Read root contextus.md when present and load only the modules relevant to this task. Without Contextus, use available project material or user-provided facts and ask for missing information; do not create a parallel context system.
Identify:
- Impersonation type: Fake website, phishing, trademark misuse, domain squatting
- Evidence available: Screenshots, URLs, WHOIS, hosting info
- Legal assets: Registered trademark, copyright ownership
- Impact: Traffic interception (fake site ranks for brand queries)? Payment fraud (users pay on fake site, then contact official support)?
Evidence Collection Checklist
| Item | Action |
|---|---|
| Full URLs | Document all key pages of the fake site |
| Screenshots | Homepage, product pages, logo, layout; include date/time |
| Comparison | Side-by-side: official vs fake (layout, logo, copy similarity) |
| WHOIS | Use ICANN Lookup for registrar, creation date, registrant |
| Hosting | IP lookup to identify hosting provider |
Reporting Channels (Priority Order)
| Channel | Entry | Use Case |
|---|---|---|
| Domain registrar | Abuse / Report Misuse on registrar site | Brand impersonation, trademark, fraud |
| Hosting provider | Same; submit abuse form | Hosting infringing content |
| Google Safe Browsing | Report Phishing | Phishing / impersonation risk |
| Google Trademark | Trademark Complaint or trademark@google.com | Trademark infringement in search; requires registered trademark |
| Bing Content Removal | Content Moderation Platform | Copyright/trademark; content removal from Bing |
| Payment processors | PayPal Resolution Center, Stripe support | If fake site accepts payments; report fraud |
| Social platforms | X, Facebook, Instagram abuse forms | If fake site is promoted or linked there |
| Google Ads / Microsoft Ads | Platform trademark complaint forms | If impersonator runs brand ads |
| DMCA | To hosting provider | Copyright infringement; images, copy, design copied |
| ICANN | DNS Abuse complaint | If registrar does not respond within reasonable time |
Report content: Include full URL, clear description of fraudulent activity, and all evidence (screenshots, logs).
Reporting Best Practices
Registrar vs hosting: Use ICANN Lookup for registrar. For hosting, use IP lookup (HostingCheckerOnline, HostingDetector, ipinfo.io) to find origin server—registrar may be Cloudflare while origin host is elsewhere; report to both.
Cloudflare as registrar: Use abuse.cloudflare.com or abuse form; select "Phishing & Malware" for impersonation. Email complaints are generally not processed; use the online form. Provide specific URLs of infringing pages.
Hosting detection: Sites behind Cloudflare CDN hide origin IP. Use reverse IP lookup or hosting detection tools to identify underlying host; submit abuse to that provider as well.
Parallel reporting: Submit to registrar, host, and Google Safe Browsing simultaneously; do not wait for one before others. Google trademark review takes 1–8 weeks.
Legal Options
| Option | When | Notes |
|---|---|---|
| Cease and desist | Trademark infringement | Lawyer-drafted; often first step |
| DMCA takedown | Copyrighted material copied | Images, copy, design; hosting providers typically comply |
| Consumer protection | Scam / fraud | FTC ReportFraud.ftc.gov (US) |
| Law enforcement | Financial loss, identity theft | IC3 (FBI) for cybercrime |
Prevention Measures
Defensive Registration
- Register brand+ai, brand+app, brand+official, etc. See domain-selection for defensive registration.
- Redirect variants to main domain; do not deploy separate sites.
Official Site Verification
Place "Official website: [domain]" prominently:
- Homepage (above fold or hero)
- Sign-in / Sign-up pages
- Pricing / Payment pages: "Only pay at [official-domain]. Do not enter payment on other domains."
- Footer: "© [Brand]. Official site: [domain]"
- FAQ: "How do I verify I'm on the official site?" → "The only official URL is [domain]. Any other domain is not affiliated."
Use trust-badges for verification signals. See about-page for identity declaration.
Show full SKILL.md (381 more words)Show less
Customer Support (Payment Fraud)
When users report "can't use after payment" but no record exists—likely paid on fake site:
- Verify source: Ask which URL they used (request screenshot or URL).
- Response template: Explain that the only official site is [official-domain]; if they paid elsewhere, that site is not affiliated. Recommend: (a) dispute charge with payment provider, (b) use only [official-domain] going forward.
- Roll out template to support team; ensure consistent messaging.
User Education
- Social media pinned post / announcement: "Only use [official-domain]"
- Email signatures, support replies: link to official domain only
Traffic Recovery (When Impersonation Intercepts Search)
| Tactic | Purpose |
|---|---|
| Brand search ads | Run Google Ads and Microsoft Ads on brand terms; ensure official site appears first for brand queries |
| SEO | Strengthen official site for branded queries; Organization schema, clear H1, meta tags. See schema-markup, title-tag |
| Social | Pinned post: "Only use [official-domain]. Beware of impersonation." |
Monitoring (Ongoing)
- Periodic search: brand name + common variants (e.g., brand+ai, brand+app)
- See brand-monitoring for monitoring setup, tool selection, and cadence
Timeline (Typical)
| Phase | Focus |
|---|---|
| Immediate (Days 1–3) | Support template; site declaration; evidence collection |
| Short-term (Week 1–2) | Abuse reports; Google Safe Browsing; DMCA if applicable |
| Traffic (Week 2+) | Brand ads; SEO; social announcement |
| Ongoing | Monitoring; defensive registration if feasible |
Implementation Checklist
Short-term (1–2 weeks): Evidence collection; abuse reports to registrar and host; Google Safe Browsing report; DMCA if applicable; add "Official website" on site.
Medium-term: Add impersonation guidance to domain-selection; official verification to trust-badges, about-page.
Long-term: Periodic search (brand + variants); brand monitoring (BrandShield, Doppel); defensive registration of variants.
Output Format
- Evidence package (checklist, evidence list)
- Report templates (registrar, hosting, Google)
- Timeline (immediate vs medium vs long-term actions)
- Prevention (defensive registration, site verification, user education)
References
- How to Report and Take Down a Fake Website - LegalClarity
- Website Spoofing: Detection and Take Down - BrandShield
- ICANN DNS Abuse Complaints Guide
- Google Safe Browsing - Report Phishing
- Cloudflare Abuse Reporting — use online form; select Phishing & Malware
- Google Trademark Complaint
- Bing Content Removal
Related Skills
- domain-selection: Defensive domain registration; brand variants
- rebranding-strategy: When rebranding, sync brand protection checks
- brand-monitoring: Proactive monitoring setup; tool selection; this skill = reactive takedown
- branding: Brand asset protection; consistency
- trust-badges: Official site verification signals
- about-page: Official identity and domain declaration
- homepage-generator: "Official website" placement
- google-ads, paid-ads-strategy: Brand search ads for traffic recovery
- schema-markup, title-tag: SEO for branded queries
© kostja94, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/strategies/brand/brand-protection of kostja94/marketing-skills.
Open the folder on GitHubat commit 8dd89c5
Compare with similar skills
Brand Protection next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Brand Protection this skillkostja94/marketing-skills | 1k | — | ~2.4k | Automated safety check: Pass | MIT | |
| Paper to Chinese Patent DrafterYuan1z0825/nature-skills | 47k | 1 repos | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Paper To Cn Patentsnipp-zha/Paper-to-patent-Skill | 107 | 1 repos | ~959 | Automated safety check: Pass | None | |
| Patent Examinegfodor/legal-skills | 393 | — | ~4.8k | Automated safety check: Pass | GPL-3.0 | |
| Patent Auditgfodor/legal-skills | 393 | — | ~2.9k | Automated safety check: Pass | GPL-3.0 | |
| Replica BrandJakeschincariol/replica-skill | 1.4k | — | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
Paper To Cn Patent
snipp-zha/Paper-to-patent-Skill
Convert scientific papers, theses, technical reports, source code, figures, or research manuscripts into evidence-grounded Chinese invention patent drafts.
Patent Examine
gfodor/legal-skills
Iteratively examine and revise a draft U.S. An agent skill from gfodor/legal-skills.
Patent Audit
gfodor/legal-skills
Audit a draft U.S. An agent skill from gfodor/legal-skills.
Replica Brand
Jakeschincariol/replica-skill
Names and rebrands an app clone so it is the user's own: name candidates with the trademark, domain, store and handle checks to run, a new palette checked for contrast, a logo brief, a voice guide…
Patent Workaround
gfodor/legal-skills
Adversarially pressure-test a draft or pending U.S. An agent skill from gfodor/legal-skills.
More from kostja94/marketing-skills
All 102 skills in this repoGrokipedia Recommendations
kostja94/marketing-skills
When the user wants to add recommendations, links, or content to Grokipedia.
AI Traffic Tracking
kostja94/marketing-skills
When the user wants to track AI search traffic in GA4 or GSC.
Analytics Tracking
kostja94/marketing-skills
When the user wants to set up, audit, or optimize analytics tracking (GA4, events, conversions).
Brand Visual Generator
kostja94/marketing-skills
When the user wants to define, audit, or apply visual identity (typography, colors, spacing, design tokens, frontend aesthetics).
Canonical Tag
kostja94/marketing-skills
When the user wants to configure canonical URLs, fix duplicate content, or consolidate URL signals.
Content Strategy
kostja94/marketing-skills
When the user wants to plan content for SEO, create content calendar, or build topic clusters.
Related
Categories
Questions about Brand Protection
What does Brand Protection do?
When the user faces brand impersonation, fake websites, phishing sites, or trademark infringement. Brand Protection is an agent skill from kostja94/marketing-skills. When the user faces brand impersonation, fake websites, phishing sites, or trademark infringement.
When should I use Brand Protection?
Brand Protection fits situations like: faces brand impersonation; trademark infringement; the user mentions fake site; domain squatting.
How do I install Brand Protection in Claude Code?
Run `npx skills add kostja94/marketing-skills --skill brand-protection -a claude-code`. Or copy the skill folder (skills/strategies/brand/brand-protection in kostja94/marketing-skills) into .claude/skills/brand-protection in your project. Claude Code loads it when a task matches its description.
How do I install Brand Protection in Codex?
Run `npx skills add kostja94/marketing-skills --skill brand-protection -a codex`. Or copy the skill folder (skills/strategies/brand/brand-protection in kostja94/marketing-skills) into .agents/skills/brand-protection in your project. Codex loads it when a task matches its description.
Can I use Brand Protection in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kostja94/marketing-skills --skill brand-protection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/brand-protection, .gemini/skills/brand-protection, .github/skills/brand-protection and .opencode/skills/brand-protection in your project.
What does Brand Protection need to run?
SKILL.md names no scripts, command-line tools or credentials: Brand Protection is instructions for the agent only.
Does Brand Protection access the network?
SKILL.md names 9 domains. As links in the text: lookup.icann.org, safebrowsing.google.com, services.google.com, bing.com, icann.org, abuse.cloudflare.com, legalclarity.org, brandshield.com and cloudflare.com. This is read from the text; nothing was executed.
Is Brand Protection safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Brand Protection use?
Brand Protection is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Brand Protection use?
About 2.4k tokens (SKILL.md is roughly 9.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Brand Protection?
Skills that share tags, products or a category with Brand Protection: Paper to Chinese Patent Drafter (Yuan1z0825/nature-skills, 47k stars), Paper To Cn Patent (snipp-zha/Paper-to-patent-Skill, 107 stars), Patent Examine (gfodor/legal-skills, 393 stars) and Patent Audit (gfodor/legal-skills, 393 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Brand Protection?
kostja94 (a GitHub user) maintains it in kostja94/marketing-skills, which has 1,025 GitHub stars. The repository holds 102 skills in this directory. The repository was last updated on October 6, 2026.
Source: kostja94/marketing-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.