Clearance

/clearance

This is a triage, not a clearance opinion. A trademark clearance opinion requires a full professional search and registered trademark counsel's judgment. A "no obvious conflicts" result means the triage didn't find anything — it does not mean the mark is clear. Clients have been sued over marks that passed a knockout search.

Instructions

1. Read ~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md. If it contains [PLACEHOLDER], stop and direct to /ip-legal:cold-start-interview.
2. Follow the workflow below.
3. Run intake (mark, goods/services, classes, jurisdictions, visual/stylization).
4. Knockout check for intrinsic bars — generic, descriptive, deceptive, geographic, surname, false connection, prohibited matter, functional.
5. Similar-marks search against what's connected (Solve Intelligence, CourtListener, Descrybe, or whatever MCP is available). If nothing is connected, say so in the output and proceed with the factor analysis only.
6. Walk the applicable circuit's likelihood-of-confusion factors — du Pont / Polaroid / Sleekcraft / other. Flag each; never conclude.
7. Write the triage memo to the matter folder (if a matter is active) or the practice outputs folder. Apply the work-product header per role.
8. End with recommended next steps and the non-lawyer gate if the role is non-lawyer.

This skill never concludes a mark is clear. If uncertain, flag — the attorney decides.

Examples

/ip-legal:clearance "APEXLEAF for an outdoor apparel line, planned launch US + EU"

/ip-legal:clearance

(And the skill will ask for the mark, goods, classes, and jurisdictions.)

THIS IS A FIRST PASS, NOT A CLEARANCE OPINION

Say this at the top of every output. Do not drop it. Do not soften it.

This is a first pass, not a clearance opinion. A trademark clearance opinion requires a full professional search (TESS, state registries, common law sources, international registries, domain and social, trade dress and design marks where relevant) and attorney judgment on likelihood of confusion, which depends on factors a structured triage cannot fully assess. A "no obvious conflicts" result from this skill means the triage didn't find anything — it does not mean the mark is clear. Clients have been sued over marks that passed a knockout search. A registered trademark attorney evaluates before anyone adopts, files, or invests in this mark.

This is the loudest guardrail in the plugin. Under-calling a conflict is a one-way door — a logo on trucks, a product launched, a TM application filed, all with a problem underneath. Over-calling is a two-way door — the attorney narrows the list in review. Stay on the two-way door side.

Matter context

Matter context. Check ## Matter workspaces in the practice-level CLAUDE.md. If Enabled is ✗ (the default for in-house users), skip the rest of this paragraph — skills use practice-level context and the matter machinery is invisible. If enabled and there is no active matter, ask: "Which matter is this for? Run /ip-legal:matter-workspace switch <slug> or say practice-level." Load the active matter's matter.md for matter-specific context and overrides. Write outputs to the matter folder at ~/.claude/plugins/config/claude-for-legal/ip-legal/matters/<matter-slug>/. Never read another matter's files unless Cross-matter context is on.

Load the practice profile first

Before running clearance, read ~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md. Pull:

• Role from ## Who's using this (lawyer vs. non-lawyer changes the work-product header and the non-lawyer gate below).
• Registered in and enforce where from ## IP practice profile and ## Enforcement posture (default jurisdictions if the user doesn't specify).
• Integrations from ## Available integrations (CourtListener / Solve Intelligence / Descrybe — each determines what searches are available to run, what the fallback is, and what gets attributed in the output).
• Decision posture from ## Decision posture on subjective legal calls — this skill never concludes "not confusingly similar."

If ~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md contains [PLACEHOLDER] or [Your Company Name], surface this bounce:

I notice you haven't configured your practice profile yet — that's how I tailor posture, jurisdictions, and approval chain to your practice.

Two choices:

• Run /ip-legal:cold-start-interview (2 minutes) to configure your profile, then I'll run this tailored to YOUR practice.
• Say "provisional" and I'll run this against generic defaults — US jurisdiction, middle risk appetite, lawyer role, no playbook — and tag every output [PROVISIONAL — configure your profile for tailored output] so you can see what I do before committing.

Provisional mode

If the user says "provisional," run the clearance normally using these generic defaults: middle risk appetite, lawyer role, US jurisdiction (USPTO + common-law), no playbook (do the full analysis rather than matching against a position list). Tag the reviewer note and every finding block with [PROVISIONAL]. At the end of the output, append:

"That was a generic run against default assumptions. Run /ip-legal:cold-start-interview to get output calibrated to YOUR practice — your playbook, your jurisdiction, your risk appetite. 2 minutes."

Intake

Ask once, in a single batch (don't drag out a quick job):

A few questions before I run the triage:

1. Proposed mark. Exact spelling, any stylization, and whether it's a word mark, logo, or both.
2. Goods or services. What's actually being sold or offered under this mark. A sentence or two — I'll map to international classes.
3. Classes. If you already know the Nice classes, list them. Otherwise describe the goods/services and I'll suggest the likely classes and confirm with you before running the search.
4. Jurisdictions. Where do you plan to use, register, or enforce? (US / EU / UK / Madrid / specific countries — I'll default to Registered in from your practice profile if you don't say.)
5. How it will appear in use. Any taglines, adjacent product names, trade dress, or design elements that would show up with it in market.

Wait for the answer. If the description is vague ("AI tool," "platform"), push once:

Give me the actual thing a customer sees — is it a consumer mobile app, enterprise API, physical product, service? The classes turn on this.

Knockout check

Before any database search, run the intrinsic problems that kill a mark regardless of prior registrations. For each, assess plainly and flag. Do not rationalize away a clear issue.

Note on scandalous/immoral marks: after Iancu v. Brunetti (2019) and Matal v. Tam (2017), the USPTO no longer refuses registration on those bases. The surviving statutory bar in this zone is false connection under §2(a). Apply that; don't flag under the struck-down bars.

Output: for each knockout category, either "no issue identified" or a specific flag with a one-line reason. Don't produce a blank table of passes.

Similar marks check

The purpose here is to find potentially confusingly similar prior marks, not to decide whether confusion is likely. That is the attorney's call.

What the user has connected

Read ## Available integrations from ~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md:

• If a trademark search connector is available (Solve Intelligence, Descrybe — or any MCP exposing TM-registry search): run a preliminary search across the relevant classes and jurisdictions. Attribute every result to its source. Note the date of the search and the scope (which registries, which classes, exact-match vs. fuzzy, design search or not).
• If a legal research connector is available (CourtListener for litigation for case law and TTAB decisions): sweep for reported disputes involving the mark or a close variant. Same attribution rule.
• If no search connector is available: say so, explicitly, in the output. Do not infer results from model knowledge and present them as search findings.

Fallback when no database access exists

Write out, in the output, this exact statement:

No database search was run. This triage did not hit TESS, Solve Intelligence, Descrybe, CourtListener, state registries, Madrid/WIPO, or any common law / unregistered-mark sources. A knockout or full search across those databases is required before any conclusion about availability. The triage below is limited to intrinsic-bar analysis and structured confusion factors against marks the user has identified or that come up in the conversation.

Then proceed — the intrinsic checks and the factors analysis are still useful, just labeled honestly.

For each similar mark found (or supplied)

Capture:

• Mark (exact characters, any stylization)
• Source (TESS registration no., Madrid designation, state registry, case citation, domain, social handle — whichever)
• Classes / goods-services description from the register
• Owner
• Status (registered / pending / abandoned / cancelled — a dead mark is not a bar but can be relevant to fame and to a predecessor's rights)
• First-use date if available

Do not supplement silently. If you cite a USPTO registration number, it came from the search you ran; if you describe a mark the user mentioned, say that. Never invent a registration and never "fill in" a detail the record doesn't support. If the search didn't return a first-use date, write "first-use date not available from search result" — do not guess.

Adjacent families sweep (required before concluding)

A clearance that only checks exact and near-exact matches misses the marks a competitor adopted because yours was taken. Before concluding, identify 3–5 adjacent word families the practitioner should also sweep, and ask the user to confirm or add to the list.

Adjacent families are category-conventional substitutes a reasonable competitor would consider when the direct mark is unavailable. For a mark like NEXUS HOME in the smart-home hub space, the adjacent families include at minimum:

• Category synonyms for NEXUS: HUB, NEST, CORE, LINK, CONNECT, BRIDGE, CENTRAL, GATEWAY.
• Assistant-style names in the same product category: ALEXA, ECHO, SIRI, GOOGLE HOME, CORTANA, HOMEY, HOMEBASE.
• HOME / HOUSE / SMART variants: SMART HOME, HOUSEHOLD, HOUSE, ABODE, CASA, DOM.
• Phonetic twins on the root: NEXIS, NEKSUS, NEXXUS, NECTIS, KNOXUS (depending on how the word sits in the market).

The skill should output an adjacent-families block in the Similar Marks section with a confirmation prompt:

Adjacent families to sweep (please confirm or add):

• [family 1 — e.g., HUB / NEST / LINK / CONNECT]
• [family 2 — e.g., ALEXA-style assistant names]
• [family 3 — e.g., HOME / HOUSE / SMART variants]
• [family 4 — phonetic twins on the root]

A clearance that only checks exact and near-exact matches misses the marks a competitor adopted because yours was taken. Confirm this list is complete for the category before I continue.

When non-English-speaking jurisdictions are in scope, the English-only phonetic sweep misses the most common source of cross-border conflicts. Add:

• Translation equivalents. The mark translated into the relevant languages. The EU's foreign-equivalents doctrine treats a translation as the same mark for confusion purposes.
• Transliteration. The mark written in the relevant script (Cyrillic, Chinese/Japanese/Korean, Arabic, Hangul, Thai). Phonetic equivalence across scripts is a recognized conflict basis.
• Script variations. Marks registered in a non-Latin script that sound like your mark when romanized.

If you can't perform cross-language analysis, say so: "Cross-language phonetic and translation-equivalent analysis not performed — this is the most common source of cross-border conflicts. A clearance search in [jurisdiction] should include it."

If the practitioner has a connected TM search tool, re-run the sweep against each confirmed adjacent family (exact + phonetic + translation-of-foreign-equivalent where relevant) and add the results to the Similar Marks table with the Adjacent family source noted. If no connector is available, say so, and list the families as the explicit next-step input for a full professional search — do not silently skip the sweep.