[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718FK6X1B7XYB28NGASVG06":3,"skill-same:01M718FK6X1B7XYB28NGASVG06":67},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":6,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":6,"updatedAt":52,"install":53,"resources":66},"01M718FK6X1B7XYB28NGASVG06","clearance",null,"Trademark clearance first pass — knockout + similar-marks check producing a flag list, not a clearance opinion. Use when a new mark is proposed, when asked whether a mark is available or to run a knockout search, or when assessing likelihood-of-confusion factors before a full professional search. This skill never concludes a mark is clear.","anthropics\u002Fclaude-for-legal","anthropics","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F76263028?v=4","01M697XGDPXJAVQ8391V2BCYTE","Anthropic","01M7189QY7HXHMC9BW4MFHPZ6H",9977,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Fip-legal\u002Fskills\u002Fclearance\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"ask","full","describe","list","clear","run","services","first","mark","check","when","use","new","search","just","professional","knockout","never","trademark","2026-11-10 10:12:30",false,"---\nname: clearance\ndescription: >\n  Trademark clearance first pass — knockout + similar-marks check producing a\n  flag list, not a clearance opinion. Use when a new mark is proposed, when\n  asked whether a mark is available or to run a knockout search, or when\n  assessing likelihood-of-confusion factors before a full professional search.\n  This skill never concludes a mark is clear.\nargument-hint: \"[describe the proposed mark, goods\u002Fservices, and jurisdictions — or just the mark and I'll ask]\"\n---\n\n# \u002Fclearance\n\n**This is a triage, not a clearance opinion.** A trademark clearance opinion\nrequires a full professional search and registered trademark counsel's\njudgment. A \"no obvious conflicts\" result means the triage\ndidn't find anything — it does not mean the mark is clear. Clients have been\nsued over marks that passed a knockout search.\n\n## Instructions\n\n1. Read `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md`. If it\n   contains `[PLACEHOLDER]`, stop and direct to `\u002Fip-legal:cold-start-interview`.\n2. Follow the workflow below.\n3. Run intake (mark, goods\u002Fservices, classes, jurisdictions, visual\u002Fstylization).\n4. Knockout check for intrinsic bars — generic, descriptive, deceptive,\n   geographic, surname, false connection, prohibited matter, functional.\n5. Similar-marks search against what's connected (Solve Intelligence, CourtListener, Descrybe, or whatever MCP is available). If nothing is\n   connected, say so in the output and proceed with the factor analysis only.\n6. Walk the applicable circuit's likelihood-of-confusion factors — du Pont \u002F\n   Polaroid \u002F Sleekcraft \u002F other. Flag each; never conclude.\n7. Write the triage memo to the matter folder (if a matter is active) or the\n   practice outputs folder. Apply the work-product header per role.\n8. End with recommended next steps and the non-lawyer gate if the role is\n   non-lawyer.\n\nThis skill never concludes a mark is clear. If uncertain, flag — the attorney\ndecides.\n\n## Examples\n\n```\n\u002Fip-legal:clearance \"APEXLEAF for an outdoor apparel line, planned launch US + EU\"\n```\n\n```\n\u002Fip-legal:clearance\n```\n\n(And the skill will ask for the mark, goods, classes, and jurisdictions.)\n\n---\n\n## THIS IS A FIRST PASS, NOT A CLEARANCE OPINION\n\n**Say this at the top of every output. Do not drop it. Do not soften it.**\n\n> **This is a first pass, not a clearance opinion.** A trademark clearance opinion\n> requires a full professional search (TESS, state registries, common law sources,\n> international registries, domain and social, trade dress and design marks where\n> relevant) and attorney judgment on likelihood of confusion, which depends on\n> factors a structured triage cannot fully assess. A \"no obvious conflicts\" result\n> from this skill means the triage didn't find anything — it does not mean the\n> mark is clear. Clients have been sued over marks that passed a knockout search.\n> A registered trademark attorney evaluates before anyone adopts, files, or\n> invests in this mark.\n\nThis is the loudest guardrail in the plugin. Under-calling a conflict is a\none-way door — a logo on trucks, a product launched, a TM application filed, all\nwith a problem underneath. Over-calling is a two-way door — the attorney narrows\nthe list in review. Stay on the two-way door side.\n\n---\n\n## Matter context\n\n**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 `\u002Fip-legal:matter-workspace switch \u003Cslug>` or say `practice-level`.\" Load the active matter's `matter.md` for matter-specific context and overrides. Write outputs to the matter folder at `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002F`. Never read another matter's files unless `Cross-matter context` is `on`.\n\n---\n\n## Load the practice profile first\n\nBefore running clearance, read `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md`. Pull:\n\n- **Role** from `## Who's using this` (lawyer vs. non-lawyer changes the work-product header and the non-lawyer gate below).\n- **Registered in** and **enforce where** from `## IP practice profile` and `## Enforcement posture` (default jurisdictions if the user doesn't specify).\n- **Integrations** from `## Available integrations` (CourtListener \u002F Solve Intelligence \u002F Descrybe — each determines what searches are available to run, what the fallback is, and what gets attributed in the output).\n- **Decision posture** from `## Decision posture on subjective legal calls` — this skill never concludes \"not confusingly similar.\"\n\nIf `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md` contains `[PLACEHOLDER]` or `[Your Company Name]`, surface this bounce:\n\n> I notice you haven't configured your practice profile yet — that's how I tailor posture, jurisdictions, and approval chain to your practice.\n>\n> **Two choices:**\n> - Run `\u002Fip-legal:cold-start-interview` (2 minutes) to configure your profile, then I'll run this tailored to YOUR practice.\n> - 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.\n\n### Provisional mode\n\nIf 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:\n\n> \"That was a generic run against default assumptions. Run `\u002Fip-legal:cold-start-interview` to get output calibrated to YOUR practice — your playbook, your jurisdiction, your risk appetite. 2 minutes.\"\n\n---\n\n## Intake\n\nAsk once, in a single batch (don't drag out a quick job):\n\n> A few questions before I run the triage:\n>\n> 1. **Proposed mark.** Exact spelling, any stylization, and whether it's a word mark, logo, or both.\n> 2. **Goods or services.** What's actually being sold or offered under this mark. A sentence or two — I'll map to international classes.\n> 3. **Classes.** If you already know the Nice classes, list them. Otherwise describe the goods\u002Fservices and I'll suggest the likely classes and confirm with you before running the search.\n> 4. **Jurisdictions.** Where do you plan to use, register, or enforce? (US \u002F EU \u002F UK \u002F Madrid \u002F specific countries — I'll default to `Registered in` from your practice profile if you don't say.)\n> 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.\n\nWait for the answer. If the description is vague (\"AI tool,\" \"platform\"), push once:\n\n> Give me the actual thing a customer sees — is it a consumer mobile app, enterprise API, physical product, service? The classes turn on this.\n\n---\n\n## Knockout check\n\nBefore any database search, run the intrinsic problems that kill a mark regardless\nof prior registrations. For each, assess plainly and flag. Do not rationalize away\na clear issue.\n\n| Bar | What it means | Flag when |\n|---|---|---|\n| **Generic** | The term IS the category (e.g., \"Soap\" for soap) | The mark names what the thing is |\n| **Descriptive** | Directly describes a feature, function, quality, or ingredient | A consumer reads the mark and knows what the product does without imagination |\n| **Deceptive \u002F deceptively misdescriptive** | Misrepresents a material feature | The mark suggests a quality the goods don't have and that quality would matter |\n| **Primarily geographically descriptive \u002F deceptive** | Mark is primarily a place name and goods come from (or don't) that place | Mark = place + generic; or place + goods where customers would assume origin |\n| **Primarily merely a surname** | Mark is primarily a surname | Mark reads as someone's last name to the relevant consumer |\n| **False connection** | Mark falsely suggests connection with person, institution, national symbol | Mark invokes a specific identifiable person or institution |\n| **Prohibited matter** | Flags, coats of arms, insignia, specific prohibited categories | Mark contains a prohibited element |\n| **Functional (for design marks \u002F trade dress)** | The feature is essential to use or affects cost\u002Fquality | Design mark — and the feature performs a function |\n\nNote on scandalous\u002Fimmoral marks: after *Iancu v. Brunetti* (2019) and *Matal v.\nTam* (2017), the USPTO no longer refuses registration on those bases. The\nsurviving statutory bar in this zone is false connection under §2(a). Apply that;\ndon't flag under the struck-down bars.\n\n**Output:** for each knockout category, either \"no issue identified\" or a\nspecific flag with a one-line reason. Don't produce a blank table of passes.\n\n---\n\n## Similar marks check\n\nThe purpose here is to **find potentially confusingly similar prior marks**, not\nto decide whether confusion is likely. That is the attorney's call.\n\n### What the user has connected\n\nRead `## Available integrations` from `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md`:\n\n- **If a trademark search connector is available** (Solve Intelligence,\n  Descrybe — or any MCP exposing TM-registry search): run a preliminary search\n  across the relevant classes and jurisdictions. Attribute every result to its\n  source. Note the date of the search and the scope (which registries, which\n  classes, exact-match vs. fuzzy, design search or not).\n- **If a legal research connector is available** (CourtListener for litigation for case law and TTAB decisions): sweep for reported disputes involving\n  the mark or a close variant. Same attribution rule.\n- **If no search connector is available:** say so, explicitly, in the output.\n  Do not infer results from model knowledge and present them as search findings.\n\n### Fallback when no database access exists\n\nWrite out, in the output, this exact statement:\n\n> **No database search was run.** This triage did not hit TESS, Solve\n> Intelligence, Descrybe, CourtListener, state registries, Madrid\u002FWIPO, or any\n> common law \u002F unregistered-mark sources. A knockout or full search across those\n> databases is required before any conclusion about availability. The triage\n> below is limited to intrinsic-bar analysis and structured confusion factors\n> against marks the user has identified or that come up in the conversation.\n\nThen proceed — the intrinsic checks and the factors analysis are still useful,\njust labeled honestly.\n\n### For each similar mark found (or supplied)\n\nCapture:\n\n- **Mark** (exact characters, any stylization)\n- **Source** (TESS registration no., Madrid designation, state registry, case\n  citation, domain, social handle — whichever)\n- **Classes \u002F goods-services description** from the register\n- **Owner**\n- **Status** (registered \u002F pending \u002F abandoned \u002F cancelled — a dead mark is not a\n  bar but can be relevant to fame and to a predecessor's rights)\n- **First-use date if available**\n\n**Do not supplement silently.** If you cite a USPTO registration number, it came\nfrom the search you ran; if you describe a mark the user mentioned, say that.\nNever invent a registration and never \"fill in\" a detail the record doesn't\nsupport. If the search didn't return a first-use date, write \"first-use date not\navailable from search result\" — do not guess.\n\n### Adjacent families sweep (required before concluding)\n\nA clearance that only checks exact and near-exact matches misses the marks a\ncompetitor adopted *because* yours was taken. Before concluding, identify 3–5\nadjacent word families the practitioner should also sweep, and ask the user to\nconfirm or add to the list.\n\nAdjacent families are category-conventional substitutes a reasonable competitor\nwould consider when the direct mark is unavailable. For a mark like\n`NEXUS HOME` in the smart-home hub space, the adjacent families include at\nminimum:\n\n- **Category synonyms** for NEXUS: `HUB`, `NEST`, `CORE`, `LINK`, `CONNECT`,\n  `BRIDGE`, `CENTRAL`, `GATEWAY`.\n- **Assistant-style names** in the same product category: `ALEXA`,\n  `ECHO`, `SIRI`, `GOOGLE HOME`, `CORTANA`, `HOMEY`, `HOMEBASE`.\n- **HOME \u002F HOUSE \u002F SMART variants**: `SMART HOME`, `HOUSEHOLD`, `HOUSE`,\n  `ABODE`, `CASA`, `DOM`.\n- **Phonetic twins** on the root: `NEXIS`, `NEKSUS`, `NEXXUS`, `NECTIS`,\n  `KNOXUS` (depending on how the word sits in the market).\n\nThe skill should output an adjacent-families block in the Similar Marks section\nwith a confirmation prompt:\n\n> **Adjacent families to sweep (please confirm or add):**\n>\n> - [family 1 — e.g., HUB \u002F NEST \u002F LINK \u002F CONNECT]\n> - [family 2 — e.g., ALEXA-style assistant names]\n> - [family 3 — e.g., HOME \u002F HOUSE \u002F SMART variants]\n> - [family 4 — phonetic twins on the root]\n>\n> A clearance that only checks exact and near-exact matches misses the marks a\n> competitor adopted because yours was taken. Confirm this list is complete for\n> the category before I continue.\n\n> **When non-English-speaking jurisdictions are in scope,** the English-only phonetic sweep misses the most common source of cross-border conflicts. Add:\n> - **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.\n> - **Transliteration.** The mark written in the relevant script (Cyrillic, Chinese\u002FJapanese\u002FKorean, Arabic, Hangul, Thai). Phonetic equivalence across scripts is a recognized conflict basis.\n> - **Script variations.** Marks registered in a non-Latin script that sound like your mark when romanized.\n>\n> 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.\"\n\nIf the practitioner has a connected TM search tool, re-run the sweep against\neach confirmed adjacent family (exact + phonetic + translation-of-foreign-equivalent\nwhere relevant) and add the results to the Similar Marks table with the\n`Adjacent family` source noted. If no connector is available, say so, and list\nthe families as the explicit next-step input for a full professional search —\ndo not silently skip the sweep.\n\n---\n\n## Likelihood-of-confusion factors\n\n> **Confusion framework is jurisdiction-specific.** The US and EU assess likelihood of confusion differently. Don't apply the wrong one.\n>\n> - **US (federal circuits):** Multi-factor tests (*du Pont*, *Polaroid*, *Sleekcraft*) — strength of the mark, similarity (sight\u002Fsound\u002Fmeaning), proximity of goods, channels, buyer sophistication, actual confusion, intent.\n> - **EU (Art. 8(1)(b) EUTMR):** Global appreciation — all relevant factors assessed holistically through the eyes of the average consumer. Key differences: greater weight on phonetic similarity; translation equivalents as standard (the mark translated into EU languages); \"likelihood of association\" beyond source confusion; the distinctiveness of the earlier mark carries more weight.\n> - **UK (TMA 1994 §5(2)):** Follows the EU global appreciation approach post-Brexit but diverging case law. Check for UK-specific decisions.\n> - **Other jurisdictions:** If the intake includes a jurisdiction without a framework above, say: \"I don't have [jurisdiction]'s confusion framework. Applying the US test would give you a wrong answer that looks right. Options: (a) I search for the applicable standard, (b) you route to a [jurisdiction] trademark specialist, (c) I note this jurisdiction is out of scope.\" Never silently apply US doctrine.\n\nThe relevant circuit's test determines the factors to walk through. Cite the\ntest that applies:\n\n- **TTAB \u002F Federal Circuit:** *In re E. I. du Pont de Nemours & Co.*, 476 F.2d\n  1357 (C.C.P.A. 1973) (13 factors).\n- **Second Circuit:** *Polaroid Corp. v. Polarad Electronics Corp.*, 287 F.2d 492\n  (2d Cir. 1961) (8 factors).\n- **Ninth Circuit:** *AMF Inc. v. Sleekcraft Boats*, 599 F.2d 341 (9th Cir. 1979)\n  (8 factors).\n- **Other circuits:** walk through the circuit's named multi-factor test (e.g.,\n  *Frisch's Restaurants* in the Sixth Circuit, *Scotch Whisky Association* in the\n  Seventh, *Lapp* in the Third).\n\nPick based on where the user plans to enforce (practice profile), the TTAB if\nthe immediate forum is registration, or the primary commercial forum otherwise.\nNote your pick in the output.\n\nFor each factor, produce a **flag**, not a verdict. Each factor should say what\ncuts each way and where the uncertainty is:\n\n- **Similarity of marks** (appearance, sound, meaning \u002F connotation, commercial\n  impression). Sight-sound-meaning, considered together.\n- **Similarity of goods or services.** Not whether the goods are identical —\n  whether consumers would expect them to come from the same source.\n- **Channels of trade.** Where each side actually sells (or would sell). Same\n  stores? Same distribution? Same trade shows? Online-only?\n- **Sophistication of consumers.** Impulse buy at a gas station vs. considered\n  enterprise purchase changes the standard of care.\n- **Strength of prior mark found.** Fanciful \u002F arbitrary \u002F suggestive \u002F\n  descriptive \u002F generic, and fame evidence if any. A strong prior mark gets\n  wider protection.\n- **Intent.** Evidence of intent to trade on goodwill — a near-copy with similar\n  trade dress in an adjacent class is different from an independent coinage.\n- **Actual confusion.** Any evidence (misdirected inquiries, surveys, reviews,\n  social posts).\n- **Likelihood of expansion** (bridge-the-gap). Whether the senior user is\n  likely to expand into the junior's lane, and vice versa.\n\nPer the decision posture in `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md`:\n\n- **Never conclude \"not confusingly similar.\"**\n- If uncertain, write: \"Similar marks found — confusion assessment required\n  before adoption.\" Or: \"Factors cut both ways; attorney judgment required.\"\n- Clear space for \"no similar marks found in the databases searched\" is fine\n  *only* if a real search was run; see the no-search fallback above otherwise.\n\n---\n\n## Recommended next steps\n\nEvery clearance output ends with concrete next steps, bucketed by what the\ntriage found:\n\n- **If knockout issues found:** reframe the mark, or accept the descriptiveness\n  bar and plan for secondary-meaning over time; route for attorney review before\n  adopting.\n- **If similar marks found in the databases searched:** attorney review is\n  required before adopting, filing, or marketing. Often the next step is a full\n  professional search to find everything the triage missed.\n- **If no similar marks found but no database search ran:** a full search is\n  required before adoption. Name the databases that need to be hit.\n- **If similar marks found and the senior mark is weak, old, in a different\n  class, or abandoned:** flag for attorney review — the triage will not make\n  this call.\n- **Always:** a full clearance opinion from registered trademark counsel, scaled\n  to the investment the mark will carry. A mark you'll put on a product line and\n  a Super Bowl ad carries more weight than a mark for a one-off pop-up.\n\n---\n\n## Output format\n\nPrepend the work-product header from `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md` `## Outputs`.\n\n```markdown\n[WORK-PRODUCT HEADER]\n\n# Trademark Clearance — First Pass (NOT AN OPINION)\n\n**This is a first pass, not a clearance opinion.** A clearance opinion requires\na full professional search and attorney judgment. A \"no obvious conflicts\"\nresult here means the triage didn't find anything — it does not mean the mark\nis clear. A registered trademark attorney evaluates before anyone adopts, files,\nor invests in this mark.\n\n**Triage result:** [GREEN \u002F YELLOW \u002F RED — one sentence why]\n\n## Proposed mark\n\n- **Mark:** [exact text, stylization noted]\n- **Mark type:** [word \u002F design \u002F composite]\n- **Goods \u002F services:** [description]\n- **Classes:** [Nice class numbers with one-line descriptions]\n- **Jurisdictions:** [US \u002F EU \u002F UK \u002F Madrid \u002F specific countries]\n- **Confusion test applied:** [du Pont \u002F Polaroid \u002F Sleekcraft \u002F other — with the\n  reason it's the right one]\n\n## Knockout issues\n\n| Bar | Flag | Note |\n|---|---|---|\n| Generic \u002F descriptive \u002F deceptive \u002F geographic \u002F surname \u002F false connection \u002F prohibited \u002F functional | [none \u002F flagged] | [one line if flagged] |\n\n## Similar marks check\n\n**Sources searched:** [registries and databases hit, with dates — or \"no database\nsearch run; see scope note below.\"]\n**Scope:** [classes, jurisdictions, exact-vs-fuzzy, design search or not]\n\n**Adjacent families swept (confirmed with user):**\n- [family 1 — e.g., HUB \u002F NEST \u002F LINK \u002F CONNECT \u002F BRIDGE \u002F GATEWAY]\n- [family 2 — e.g., ALEXA-style assistant names]\n- [family 3 — e.g., HOME \u002F HOUSE \u002F SMART variants]\n- [family 4 — phonetic twins on the root]\n\n*A clearance that only checks exact and near-exact matches misses the marks a\ncompetitor adopted because yours was taken. If any family was not swept (no\nconnector, time not available), it is listed explicitly as a next-step input\nto the full professional search — not silently skipped.*\n\n| Mark | Source | Classes \u002F G&S | Owner | Status | First use | Note |\n|---|---|---|---|---|---|---|\n| [exact] | [registration no. \u002F citation \u002F URL] | [class list] | [owner from record] | [reg\u002Fpending\u002Fabandoned\u002Fcancelled] | [date or \"not available\"] | [why it matters — exact match \u002F adjacent family] |\n\n*If no search was run:* **No database search was run.** This triage did not hit\nTESS, Solve Intelligence, Descrybe, CourtListener, state registries,\nMadrid\u002FWIPO, or any common law \u002F unregistered-mark sources. A knockout or full\nsearch across those databases is required before any conclusion about availability.\n\n## Confusion factors — flags for attorney review\n\nFor each of the factors under the test applied, a one-line flag noting what cuts\neach way.\n\n| Factor | Flag | Direction |\n|---|---|---|\n| Similarity of marks (sight \u002F sound \u002F meaning \u002F commercial impression) | [note] | [weighs toward \u002F against conflict \u002F mixed] |\n| Similarity of goods or services | [note] | [direction] |\n| Channels of trade | [note] | [direction] |\n| Consumer sophistication | [note] | [direction] |\n| Strength of prior mark | [note] | [direction] |\n| Intent | [note] | [direction] |\n| Actual confusion | [note or \"no evidence surfaced\"] | [direction] |\n| Likelihood of expansion \u002F bridge-the-gap | [note] | [direction] |\n\n**Conclusion on confusion:** *This skill does not conclude.* Either:\n- \"Similar marks found; attorney confusion assessment required before adoption.\"\n- \"No similar marks found in the databases searched; full clearance required\n  before adoption.\"\n- \"Factors cut both ways; attorney judgment required.\"\n\n## Recommended next steps\n\n- [specific next step 1 — e.g., \"Full professional search across USPTO, state\n  registries, common law sources, EUIPO, and UK IPO before adoption\"]\n- [specific next step 2 — e.g., \"Design-around review of the `APEXLEAF` mark\n  in Class 25 if the intent is to proceed\"]\n- [specific next step 3 — e.g., \"Reframe the mark — current form is descriptive\n  and will require secondary meaning\"]\n- [routing per `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md` —\n  trademark OC or in-house IP counsel named in the practice profile]\n\n## Citation verification\n\nEvery case, registration number, statute, and database result in this memo must\nbe verified against the authoritative source before relying on it. Registration\nnumbers, class designations, and first-use dates are the most common sites of\nerror. Do not cite a result you cannot open.\n```\n\n---\n\n## Non-lawyer gate\n\nBefore issuing the output, read `## Who's using this`. If the Role is Non-lawyer:\n\n> This output is a research triage, not legal advice. Adopting, filing, or\n> investing in this mark based on this triage alone has legal consequences —\n> including being sued for infringement over a mark that \"passed\" this check.\n> A registered trademark attorney needs to evaluate before you move.\n>\n> Here's a brief to bring to an attorney — it'll cut the time the conversation\n> takes:\n>\n> [Generate a 1-page summary: the proposed mark, the goods\u002Fservices and classes,\n> the knockout issues (if any), the similar marks surfaced (if any), what was\n> and wasn't searched, and the three questions to ask the attorney.]\n>\n> If you need to find a licensed attorney, solicitor, barrister, or other authorised legal professional in your jurisdiction: your professional regulator's referral service is the fastest starting point (state bar in the US, SRA\u002FBar Standards Board in England & Wales, Law Society in Scotland\u002FNI\u002FIreland\u002FCanada\u002FAustralia, or your jurisdiction's equivalent). The INTA (International Trademark Association)\n> maintains a member directory of registered trademark practitioners.\n\nDeliver the full triage memo alongside the brief. Do not withhold the analysis.\n\n---\n\n## Output location\n\nIf matter workspaces are enabled and a matter is active, write the output to\n`~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002Foutputs\u002Fclearance-\u003Cmark-slug>-YYYY-MM-DD.md`.\nOtherwise write to\n`~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002Foutputs\u002Fclearance-\u003Cmark-slug>-YYYY-MM-DD.md`\nand surface the path to the user.\n\nAppend a one-line entry to the matter's `history.md` if a matter is active.\n\n---\n\n## Close with the next-steps decision tree\n\nEnd with the next-steps decision tree per CLAUDE.md `## Outputs`. Customize the options to what this skill just produced — the five default branches (draft the X, escalate, get more facts, watch and wait, something else) are a starting point, not a lock-in. The tree is the output; the lawyer picks.\n\n## What this skill does not do\n\n- **Conclude a mark is clear.** Ever. The loudest guardrail in the plugin.\n- **Substitute for TESS search, state-registry search, common-law search,\n  international search, watch-service check, or design-mark search.**\n- **File a trademark application.** Filing is an attorney task; this skill\n  informs the decision to file.\n- **Evaluate trade dress, trademark dilution, or famous-mark claims** beyond a\n  preliminary flag. Dilution under the TDRA requires a fame analysis this\n  skill does not attempt.\n- **Address foreign local-law bars** (e.g., phonetic similarity standards in\n  Japan, translation-of-foreign-equivalents in the EU) beyond flagging that\n  foreign analysis is required when a foreign jurisdiction is in scope.\n- **Quote outputs to customers, counterparties, or the press.** This is\n  internal research. Privileged if the header at the top applies.\n\n---\n\n## Tone\n\nCrisp, concrete, honest about scope. The lawyer reading this output should know\nin ten seconds what the triage found, what it didn't, and what has to happen\nbefore anyone adopts the mark. No hedging prose. The guardrail at the top and\nthe \"this skill does not conclude\" line on confusion do the scope work.\n","# \u002Fclearance\n\n**This is a triage, not a clearance opinion.** A trademark clearance opinion\nrequires a full professional search and registered trademark counsel's\njudgment. A \"no obvious conflicts\" result means the triage\ndidn't find anything — it does not mean the mark is clear. Clients have been\nsued over marks that passed a knockout search.\n\n## Instructions\n\n1. Read `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md`. If it\n   contains `[PLACEHOLDER]`, stop and direct to `\u002Fip-legal:cold-start-interview`.\n2. Follow the workflow below.\n3. Run intake (mark, goods\u002Fservices, classes, jurisdictions, visual\u002Fstylization).\n4. Knockout check for intrinsic bars — generic, descriptive, deceptive,\n   geographic, surname, false connection, prohibited matter, functional.\n5. Similar-marks search against what's connected (Solve Intelligence, CourtListener, Descrybe, or whatever MCP is available). If nothing is\n   connected, say so in the output and proceed with the factor analysis only.\n6. Walk the applicable circuit's likelihood-of-confusion factors — du Pont \u002F\n   Polaroid \u002F Sleekcraft \u002F other. Flag each; never conclude.\n7. Write the triage memo to the matter folder (if a matter is active) or the\n   practice outputs folder. Apply the work-product header per role.\n8. End with recommended next steps and the non-lawyer gate if the role is\n   non-lawyer.\n\nThis skill never concludes a mark is clear. If uncertain, flag — the attorney\ndecides.\n\n## Examples\n\n```\n\u002Fip-legal:clearance \"APEXLEAF for an outdoor apparel line, planned launch US + EU\"\n```\n\n```\n\u002Fip-legal:clearance\n```\n\n(And the skill will ask for the mark, goods, classes, and jurisdictions.)\n\n---\n\n## THIS IS A FIRST PASS, NOT A CLEARANCE OPINION\n\n**Say this at the top of every output. Do not drop it. Do not soften it.**\n\n> **This is a first pass, not a clearance opinion.** A trademark clearance opinion\n> requires a full professional search (TESS, state registries, common law sources,\n> international registries, domain and social, trade dress and design marks where\n> relevant) and attorney judgment on likelihood of confusion, which depends on\n> factors a structured triage cannot fully assess. A \"no obvious conflicts\" result\n> from this skill means the triage didn't find anything — it does not mean the\n> mark is clear. Clients have been sued over marks that passed a knockout search.\n> A registered trademark attorney evaluates before anyone adopts, files, or\n> invests in this mark.\n\nThis is the loudest guardrail in the plugin. Under-calling a conflict is a\none-way door — a logo on trucks, a product launched, a TM application filed, all\nwith a problem underneath. Over-calling is a two-way door — the attorney narrows\nthe list in review. Stay on the two-way door side.\n\n---\n\n## Matter context\n\n**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 `\u002Fip-legal:matter-workspace switch \u003Cslug>` or say `practice-level`.\" Load the active matter's `matter.md` for matter-specific context and overrides. Write outputs to the matter folder at `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002F`. Never read another matter's files unless `Cross-matter context` is `on`.\n\n---\n\n## Load the practice profile first\n\nBefore running clearance, read `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md`. Pull:\n\n- **Role** from `## Who's using this` (lawyer vs. non-lawyer changes the work-product header and the non-lawyer gate below).\n- **Registered in** and **enforce where** from `## IP practice profile` and `## Enforcement posture` (default jurisdictions if the user doesn't specify).\n- **Integrations** from `## Available integrations` (CourtListener \u002F Solve Intelligence \u002F Descrybe — each determines what searches are available to run, what the fallback is, and what gets attributed in the output).\n- **Decision posture** from `## Decision posture on subjective legal calls` — this skill never concludes \"not confusingly similar.\"\n\nIf `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md` contains `[PLACEHOLDER]` or `[Your Company Name]`, surface this bounce:\n\n> I notice you haven't configured your practice profile yet — that's how I tailor posture, jurisdictions, and approval chain to your practice.\n>\n> **Two choices:**\n> - Run `\u002Fip-legal:cold-start-interview` (2 minutes) to configure your profile, then I'll run this tailored to YOUR practice.\n> - 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.\n\n### Provisional mode\n\nIf 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:\n\n> \"That was a generic run against default assumptions. Run `\u002Fip-legal:cold-start-interview` to get output calibrated to YOUR practice — your playbook, your jurisdiction, your risk appetite. 2 minutes.\"\n\n---\n\n## Intake\n\nAsk once, in a single batch (don't drag out a quick job):\n\n> A few questions before I run the triage:\n>\n> 1. **Proposed mark.** Exact spelling, any stylization, and whether it's a word mark, logo, or both.\n> 2. **Goods or services.** What's actually being sold or offered under this mark. A sentence or two — I'll map to international classes.\n> 3. **Classes.** If you already know the Nice classes, list them. Otherwise describe the goods\u002Fservices and I'll suggest the likely classes and confirm with you before running the search.\n> 4. **Jurisdictions.** Where do you plan to use, register, or enforce? (US \u002F EU \u002F UK \u002F Madrid \u002F specific countries — I'll default to `Registered in` from your practice profile if you don't say.)\n> 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.\n\nWait for the answer. If the description is vague (\"AI tool,\" \"platform\"), push once:\n\n> Give me the actual thing a customer sees — is it a consumer mobile app, enterprise API, physical product, service? The classes turn on this.\n\n---\n\n## Knockout check\n\nBefore any database search, run the intrinsic problems that kill a mark regardless\nof prior registrations. For each, assess plainly and flag. Do not rationalize away\na clear issue.\n\n| Bar | What it means | Flag when |\n|---|---|---|\n| **Generic** | The term IS the category (e.g., \"Soap\" for soap) | The mark names what the thing is |\n| **Descriptive** | Directly describes a feature, function, quality, or ingredient | A consumer reads the mark and knows what the product does without imagination |\n| **Deceptive \u002F deceptively misdescriptive** | Misrepresents a material feature | The mark suggests a quality the goods don't have and that quality would matter |\n| **Primarily geographically descriptive \u002F deceptive** | Mark is primarily a place name and goods come from (or don't) that place | Mark = place + generic; or place + goods where customers would assume origin |\n| **Primarily merely a surname** | Mark is primarily a surname | Mark reads as someone's last name to the relevant consumer |\n| **False connection** | Mark falsely suggests connection with person, institution, national symbol | Mark invokes a specific identifiable person or institution |\n| **Prohibited matter** | Flags, coats of arms, insignia, specific prohibited categories | Mark contains a prohibited element |\n| **Functional (for design marks \u002F trade dress)** | The feature is essential to use or affects cost\u002Fquality | Design mark — and the feature performs a function |\n\nNote on scandalous\u002Fimmoral marks: after *Iancu v. Brunetti* (2019) and *Matal v.\nTam* (2017), the USPTO no longer refuses registration on those bases. The\nsurviving statutory bar in this zone is false connection under §2(a). Apply that;\ndon't flag under the struck-down bars.\n\n**Output:** for each knockout category, either \"no issue identified\" or a\nspecific flag with a one-line reason. Don't produce a blank table of passes.\n\n---\n\n## Similar marks check\n\nThe purpose here is to **find potentially confusingly similar prior marks**, not\nto decide whether confusion is likely. That is the attorney's call.\n\n### What the user has connected\n\nRead `## Available integrations` from `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md`:\n\n- **If a trademark search connector is available** (Solve Intelligence,\n  Descrybe — or any MCP exposing TM-registry search): run a preliminary search\n  across the relevant classes and jurisdictions. Attribute every result to its\n  source. Note the date of the search and the scope (which registries, which\n  classes, exact-match vs. fuzzy, design search or not).\n- **If a legal research connector is available** (CourtListener for litigation for case law and TTAB decisions): sweep for reported disputes involving\n  the mark or a close variant. Same attribution rule.\n- **If no search connector is available:** say so, explicitly, in the output.\n  Do not infer results from model knowledge and present them as search findings.\n\n### Fallback when no database access exists\n\nWrite out, in the output, this exact statement:\n\n> **No database search was run.** This triage did not hit TESS, Solve\n> Intelligence, Descrybe, CourtListener, state registries, Madrid\u002FWIPO, or any\n> common law \u002F unregistered-mark sources. A knockout or full search across those\n> databases is required before any conclusion about availability. The triage\n> below is limited to intrinsic-bar analysis and structured confusion factors\n> against marks the user has identified or that come up in the conversation.\n\nThen proceed — the intrinsic checks and the factors analysis are still useful,\njust labeled honestly.\n\n### For each similar mark found (or supplied)\n\nCapture:\n\n- **Mark** (exact characters, any stylization)\n- **Source** (TESS registration no., Madrid designation, state registry, case\n  citation, domain, social handle — whichever)\n- **Classes \u002F goods-services description** from the register\n- **Owner**\n- **Status** (registered \u002F pending \u002F abandoned \u002F cancelled — a dead mark is not a\n  bar but can be relevant to fame and to a predecessor's rights)\n- **First-use date if available**\n\n**Do not supplement silently.** If you cite a USPTO registration number, it came\nfrom the search you ran; if you describe a mark the user mentioned, say that.\nNever invent a registration and never \"fill in\" a detail the record doesn't\nsupport. If the search didn't return a first-use date, write \"first-use date not\navailable from search result\" — do not guess.\n\n### Adjacent families sweep (required before concluding)\n\nA clearance that only checks exact and near-exact matches misses the marks a\ncompetitor adopted *because* yours was taken. Before concluding, identify 3–5\nadjacent word families the practitioner should also sweep, and ask the user to\nconfirm or add to the list.\n\nAdjacent families are category-conventional substitutes a reasonable competitor\nwould consider when the direct mark is unavailable. For a mark like\n`NEXUS HOME` in the smart-home hub space, the adjacent families include at\nminimum:\n\n- **Category synonyms** for NEXUS: `HUB`, `NEST`, `CORE`, `LINK`, `CONNECT`,\n  `BRIDGE`, `CENTRAL`, `GATEWAY`.\n- **Assistant-style names** in the same product category: `ALEXA`,\n  `ECHO`, `SIRI`, `GOOGLE HOME`, `CORTANA`, `HOMEY`, `HOMEBASE`.\n- **HOME \u002F HOUSE \u002F SMART variants**: `SMART HOME`, `HOUSEHOLD`, `HOUSE`,\n  `ABODE`, `CASA`, `DOM`.\n- **Phonetic twins** on the root: `NEXIS`, `NEKSUS`, `NEXXUS`, `NECTIS`,\n  `KNOXUS` (depending on how the word sits in the market).\n\nThe skill should output an adjacent-families block in the Similar Marks section\nwith a confirmation prompt:\n\n> **Adjacent families to sweep (please confirm or add):**\n>\n> - [family 1 — e.g., HUB \u002F NEST \u002F LINK \u002F CONNECT]\n> - [family 2 — e.g., ALEXA-style assistant names]\n> - [family 3 — e.g., HOME \u002F HOUSE \u002F SMART variants]\n> - [family 4 — phonetic twins on the root]\n>\n> A clearance that only checks exact and near-exact matches misses the marks a\n> competitor adopted because yours was taken. Confirm this list is complete for\n> the category before I continue.\n\n> **When non-English-speaking jurisdictions are in scope,** the English-only phonetic sweep misses the most common source of cross-border conflicts. Add:\n> - **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.\n> - **Transliteration.** The mark written in the relevant script (Cyrillic, Chinese\u002FJapanese\u002FKorean, Arabic, Hangul, Thai). Phonetic equivalence across scripts is a recognized conflict basis.\n> - **Script variations.** Marks registered in a non-Latin script that sound like your mark when romanized.\n>\n> 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.\"\n\nIf the practitioner has a connected TM search tool, re-run the sweep against\neach confirmed adjacent family (exact + phonetic + translation-of-foreign-equivalent\nwhere relevant) and add the results to the Similar Marks table with the\n`Adjacent family` source noted. If no connector is available, say so, and list\nthe families as the explicit next-step input for a full professional search —\ndo not silently skip the sweep.\n\n---\n\n## Likelihood-of-confusion factors\n\n> **Confusion framework is jurisdiction-specific.** The US and EU assess likelihood of confusion differently. Don't apply the wrong one.\n>\n> - **US (federal circuits):** Multi-factor tests (*du Pont*, *Polaroid*, *Sleekcraft*) — strength of the mark, similarity (sight\u002Fsound\u002Fmeaning), proximity of goods, channels, buyer sophistication, actual confusion, intent.\n> - **EU (Art. 8(1)(b) EUTMR):** Global appreciation — all relevant factors assessed holistically through the eyes of the average consumer. Key differences: greater weight on phonetic similarity; translation equivalents as standard (the mark translated into EU languages); \"likelihood of association\" beyond source confusion; the distinctiveness of the earlier mark carries more weight.\n> - **UK (TMA 1994 §5(2)):** Follows the EU global appreciation approach post-Brexit but diverging case law. Check for UK-specific decisions.\n> - **Other jurisdictions:** If the intake includes a jurisdiction without a framework above, say: \"I don't have [jurisdiction]'s confusion framework. Applying the US test would give you a wrong answer that looks right. Options: (a) I search for the applicable standard, (b) you route to a [jurisdiction] trademark specialist, (c) I note this jurisdiction is out of scope.\" Never silently apply US doctrine.\n\nThe relevant circuit's test determines the factors to walk through. Cite the\ntest that applies:\n\n- **TTAB \u002F Federal Circuit:** *In re E. I. du Pont de Nemours & Co.*, 476 F.2d\n  1357 (C.C.P.A. 1973) (13 factors).\n- **Second Circuit:** *Polaroid Corp. v. Polarad Electronics Corp.*, 287 F.2d 492\n  (2d Cir. 1961) (8 factors).\n- **Ninth Circuit:** *AMF Inc. v. Sleekcraft Boats*, 599 F.2d 341 (9th Cir. 1979)\n  (8 factors).\n- **Other circuits:** walk through the circuit's named multi-factor test (e.g.,\n  *Frisch's Restaurants* in the Sixth Circuit, *Scotch Whisky Association* in the\n  Seventh, *Lapp* in the Third).\n\nPick based on where the user plans to enforce (practice profile), the TTAB if\nthe immediate forum is registration, or the primary commercial forum otherwise.\nNote your pick in the output.\n\nFor each factor, produce a **flag**, not a verdict. Each factor should say what\ncuts each way and where the uncertainty is:\n\n- **Similarity of marks** (appearance, sound, meaning \u002F connotation, commercial\n  impression). Sight-sound-meaning, considered together.\n- **Similarity of goods or services.** Not whether the goods are identical —\n  whether consumers would expect them to come from the same source.\n- **Channels of trade.** Where each side actually sells (or would sell). Same\n  stores? Same distribution? Same trade shows? Online-only?\n- **Sophistication of consumers.** Impulse buy at a gas station vs. considered\n  enterprise purchase changes the standard of care.\n- **Strength of prior mark found.** Fanciful \u002F arbitrary \u002F suggestive \u002F\n  descriptive \u002F generic, and fame evidence if any. A strong prior mark gets\n  wider protection.\n- **Intent.** Evidence of intent to trade on goodwill — a near-copy with similar\n  trade dress in an adjacent class is different from an independent coinage.\n- **Actual confusion.** Any evidence (misdirected inquiries, surveys, reviews,\n  social posts).\n- **Likelihood of expansion** (bridge-the-gap). Whether the senior user is\n  likely to expand into the junior's lane, and vice versa.\n\nPer the decision posture in `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md`:\n\n- **Never conclude \"not confusingly similar.\"**\n- If uncertain, write: \"Similar marks found — confusion assessment required\n  before adoption.\" Or: \"Factors cut both ways; attorney judgment required.\"\n- Clear space for \"no similar marks found in the databases searched\" is fine\n  *only* if a real search was run; see the no-search fallback above otherwise.\n\n---\n\n## Recommended next steps\n\nEvery clearance output ends with concrete next steps, bucketed by what the\ntriage found:\n\n- **If knockout issues found:** reframe the mark, or accept the descriptiveness\n  bar and plan for secondary-meaning over time; route for attorney review before\n  adopting.\n- **If similar marks found in the databases searched:** attorney review is\n  required before adopting, filing, or marketing. Often the next step is a full\n  professional search to find everything the triage missed.\n- **If no similar marks found but no database search ran:** a full search is\n  required before adoption. Name the databases that need to be hit.\n- **If similar marks found and the senior mark is weak, old, in a different\n  class, or abandoned:** flag for attorney review — the triage will not make\n  this call.\n- **Always:** a full clearance opinion from registered trademark counsel, scaled\n  to the investment the mark will carry. A mark you'll put on a product line and\n  a Super Bowl ad carries more weight than a mark for a one-off pop-up.\n\n---\n\n## Output format\n\nPrepend the work-product header from `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md` `## Outputs`.\n\n```markdown\n[WORK-PRODUCT HEADER]\n\n# Trademark Clearance — First Pass (NOT AN OPINION)\n\n**This is a first pass, not a clearance opinion.** A clearance opinion requires\na full professional search and attorney judgment. A \"no obvious conflicts\"\nresult here means the triage didn't find anything — it does not mean the mark\nis clear. A registered trademark attorney evaluates before anyone adopts, files,\nor invests in this mark.\n\n**Triage result:** [GREEN \u002F YELLOW \u002F RED — one sentence why]\n\n## Proposed mark\n\n- **Mark:** [exact text, stylization noted]\n- **Mark type:** [word \u002F design \u002F composite]\n- **Goods \u002F services:** [description]\n- **Classes:** [Nice class numbers with one-line descriptions]\n- **Jurisdictions:** [US \u002F EU \u002F UK \u002F Madrid \u002F specific countries]\n- **Confusion test applied:** [du Pont \u002F Polaroid \u002F Sleekcraft \u002F other — with the\n  reason it's the right one]\n\n## Knockout issues\n\n| Bar | Flag | Note |\n|---|---|---|\n| Generic \u002F descriptive \u002F deceptive \u002F geographic \u002F surname \u002F false connection \u002F prohibited \u002F functional | [none \u002F flagged] | [one line if flagged] |\n\n## Similar marks check\n\n**Sources searched:** [registries and databases hit, with dates — or \"no database\nsearch run; see scope note below.\"]\n**Scope:** [classes, jurisdictions, exact-vs-fuzzy, design search or not]\n\n**Adjacent families swept (confirmed with user):**\n- [family 1 — e.g., HUB \u002F NEST \u002F LINK \u002F CONNECT \u002F BRIDGE \u002F GATEWAY]\n- [family 2 — e.g., ALEXA-style assistant names]\n- [family 3 — e.g., HOME \u002F HOUSE \u002F SMART variants]\n- [family 4 — phonetic twins on the root]\n\n*A clearance that only checks exact and near-exact matches misses the marks a\ncompetitor adopted because yours was taken. If any family was not swept (no\nconnector, time not available), it is listed explicitly as a next-step input\nto the full professional search — not silently skipped.*\n\n| Mark | Source | Classes \u002F G&S | Owner | Status | First use | Note |\n|---|---|---|---|---|---|---|\n| [exact] | [registration no. \u002F citation \u002F URL] | [class list] | [owner from record] | [reg\u002Fpending\u002Fabandoned\u002Fcancelled] | [date or \"not available\"] | [why it matters — exact match \u002F adjacent family] |\n\n*If no search was run:* **No database search was run.** This triage did not hit\nTESS, Solve Intelligence, Descrybe, CourtListener, state registries,\nMadrid\u002FWIPO, or any common law \u002F unregistered-mark sources. A knockout or full\nsearch across those databases is required before any conclusion about availability.\n\n## Confusion factors — flags for attorney review\n\nFor each of the factors under the test applied, a one-line flag noting what cuts\neach way.\n\n| Factor | Flag | Direction |\n|---|---|---|\n| Similarity of marks (sight \u002F sound \u002F meaning \u002F commercial impression) | [note] | [weighs toward \u002F against conflict \u002F mixed] |\n| Similarity of goods or services | [note] | [direction] |\n| Channels of trade | [note] | [direction] |\n| Consumer sophistication | [note] | [direction] |\n| Strength of prior mark | [note] | [direction] |\n| Intent | [note] | [direction] |\n| Actual confusion | [note or \"no evidence surfaced\"] | [direction] |\n| Likelihood of expansion \u002F bridge-the-gap | [note] | [direction] |\n\n**Conclusion on confusion:** *This skill does not conclude.* Either:\n- \"Similar marks found; attorney confusion assessment required before adoption.\"\n- \"No similar marks found in the databases searched; full clearance required\n  before adoption.\"\n- \"Factors cut both ways; attorney judgment required.\"\n\n## Recommended next steps\n\n- [specific next step 1 — e.g., \"Full professional search across USPTO, state\n  registries, common law sources, EUIPO, and UK IPO before adoption\"]\n- [specific next step 2 — e.g., \"Design-around review of the `APEXLEAF` mark\n  in Class 25 if the intent is to proceed\"]\n- [specific next step 3 — e.g., \"Reframe the mark — current form is descriptive\n  and will require secondary meaning\"]\n- [routing per `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md` —\n  trademark OC or in-house IP counsel named in the practice profile]\n\n## Citation verification\n\nEvery case, registration number, statute, and database result in this memo must\nbe verified against the authoritative source before relying on it. Registration\nnumbers, class designations, and first-use dates are the most common sites of\nerror. Do not cite a result you cannot open.\n```\n\n---\n\n## Non-lawyer gate\n\nBefore issuing the output, read `## Who's using this`. If the Role is Non-lawyer:\n\n> This output is a research triage, not legal advice. Adopting, filing, or\n> investing in this mark based on this triage alone has legal consequences —\n> including being sued for infringement over a mark that \"passed\" this check.\n> A registered trademark attorney needs to evaluate before you move.\n>\n> Here's a brief to bring to an attorney — it'll cut the time the conversation\n> takes:\n>\n> [Generate a 1-page summary: the proposed mark, the goods\u002Fservices and classes,\n> the knockout issues (if any), the similar marks surfaced (if any), what was\n> and wasn't searched, and the three questions to ask the attorney.]\n>\n> If you need to find a licensed attorney, solicitor, barrister, or other authorised legal professional in your jurisdiction: your professional regulator's referral service is the fastest starting point (state bar in the US, SRA\u002FBar Standards Board in England & Wales, Law Society in Scotland\u002FNI\u002FIreland\u002FCanada\u002FAustralia, or your jurisdiction's equivalent). The INTA (International Trademark Association)\n> maintains a member directory of registered trademark practitioners.\n\nDeliver the full triage memo alongside the brief. Do not withhold the analysis.\n\n---\n\n## Output location\n\nIf matter workspaces are enabled and a matter is active, write the output to\n`~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002Foutputs\u002Fclearance-\u003Cmark-slug>-YYYY-MM-DD.md`.\nOtherwise write to\n`~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002Foutputs\u002Fclearance-\u003Cmark-slug>-YYYY-MM-DD.md`\nand surface the path to the user.\n\nAppend a one-line entry to the matter's `history.md` if a matter is active.\n\n---\n\n## Close with the next-steps decision tree\n\nEnd with the next-steps decision tree per CLAUDE.md `## Outputs`. Customize the options to what this skill just produced — the five default branches (draft the X, escalate, get more facts, watch and wait, something else) are a starting point, not a lock-in. The tree is the output; the lawyer picks.\n\n## What this skill does not do\n\n- **Conclude a mark is clear.** Ever. The loudest guardrail in the plugin.\n- **Substitute for TESS search, state-registry search, common-law search,\n  international search, watch-service check, or design-mark search.**\n- **File a trademark application.** Filing is an attorney task; this skill\n  informs the decision to file.\n- **Evaluate trade dress, trademark dilution, or famous-mark claims** beyond a\n  preliminary flag. Dilution under the TDRA requires a fame analysis this\n  skill does not attempt.\n- **Address foreign local-law bars** (e.g., phonetic similarity standards in\n  Japan, translation-of-foreign-equivalents in the EU) beyond flagging that\n  foreign analysis is required when a foreign jurisdiction is in scope.\n- **Quote outputs to customers, counterparties, or the press.** This is\n  internal research. Privileged if the header at the top applies.\n\n---\n\n## Tone\n\nCrisp, concrete, honest about scope. The lawyer reading this output should know\nin ten seconds what the triage found, what it didn't, and what has to happen\nbefore anyone adopts the mark. No hedging prose. The guardrail at the top and\nthe \"this skill does not conclude\" line on confusion do the scope work.\n",{"name":5,"description":43,"argument-hint":44},"Trademark clearance first pass — knockout + similar-marks check producing a flag list, not a clearance opinion. Use when a new mark is proposed, when asked whether a mark is available or to run a knockout search, or when assessing likelihood-of-confusion factors before a full professional search. This skill never concludes a mark is clear.\n","[describe the proposed mark, goods\u002Fservices, and jurisdictions — or just the mark and I'll ask]","main","4a6c651889c97cc9140580363c73e0eb17379c2b","ip-legal\u002Fskills\u002Fclearance",1959,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal","https:\u002F\u002Fgithub.com\u002Fanthropics","https:\u002F\u002Fanthropic.com","2026-11-08 22:42:37",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add anthropics\u002Fclaude-for-legal --skill clearance",{"tool":59,"command":60},"bunx","bunx skills add anthropics\u002Fclaude-for-legal --skill clearance",{"tool":62,"command":63},"pnpm","pnpm dlx skills add anthropics\u002Fclaude-for-legal --skill clearance","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Fip-legal\u002Fskills\u002Fclearance\u002FSKILL.md",true,[],[68,96,116,135,156,169],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":79,"publishedAt":38},"01M718SG9G2R92ECCD0HYK2R5E","reg-feed-watcher","Check regulatory feeds now and report what's new since the last check, filtered by your materiality threshold. Use when the user says \"check the feeds\", \"what's new\", \"regulatory update\", when running from the scheduled agent, or when manually pasting a regulatory development for classification and diff.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Fregulatory-legal\u002Fskills\u002Freg-feed-watcher\u002FSKILL.md",[74],{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[80,81,82,83,84,85,86,87,88,89,31,90,30,91,29,28,92,93,94,95],"reg","watcher","reg feed watcher","running","feeds","filtered","diff","development","for","classification","now","scheduled","last","update","report","regulatory",{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":38},"01M718SCRTBN55DMTVSPG67A7N","policy-redraft","Produce a proposed marked-up policy redraft that closes a gap found by \u002Fregulatory-legal:gaps or \u002Fregulatory-legal:policy-diff. A first draft for internal review — not for direct application to approved policy documents. Use when the user says \"redraft the policy\", \"draft the policy fix\", \"mark up the policy\", or when gap-surfacer hands off a gap for drafting.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Fregulatory-legal\u002Fskills\u002Fpolicy-redraft\u002FSKILL.md",[],[103,104,86,88,105,106,107,30,108,29,109,110,111,112,113,114,27,26,95,115],"policy","policy redraft","up","fix","produce","documents","drafting","gaps","review","draft","id","gap","direct",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":38},"01M718S8RV0C4NMVKG078CBFXP","policy-diff","Diff a specific regulatory change against the indexed policy library. Use when a reg has changed and you need to know which policies it touches and what the gap is, when the user says \"diff this reg against our policies\", \"which policy does this affect\", or \"gap analysis\", or when reg-feed-watcher hands off a material item.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Fregulatory-legal\u002Fskills\u002Fpolicy-diff\u002FSKILL.md",[],[86,103,123,124,29,125,126,80,127,81,128,129,130,131,30,132,114,133,134,95],"policy diff","which","you","analysis","text","change","paste","library","material","gap analysis","what the","name",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":38},"01M718S6521Y0FT4T24VCFKVG5","matter-workspace","Manage matter workspaces — create, list, switch, close, or detach the active matter (practice-level). Use when working across multiple clients or matters and you need to keep one engagement's context separate from another, or when a substantive skill needs to know which matter it's working in.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Fregulatory-legal\u002Fskills\u002Fmatter-workspace\u002FSKILL.md",[],[142,143,124,144,145,146,31,30,29,125,147,148,149,150,151,152,153,22,154,155],"workspace","matter workspace","switch","manage","workspaces","keep","across","create","engagement","close","active","clients","it","context",{"skillNo":157,"name":110,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":38},"01M718S3FPEJNQGCMQ1AR8M4HE","Open gaps tracker — what's flagged and not yet closed. Use when the user asks \"what gaps are open\", \"gap tracker\", \"remediation status\", or wants to close (--close GAP-ID) or risk-accept (--accept GAP-ID) a tracked gap.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Fregulatory-legal\u002Fskills\u002Fgaps\u002FSKILL.md",[],[110,113,114,162,151,163,164,165,166,30,167,29,168],"risk","tracker","remediation","status","open","accept","user",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":180,"publishedAt":38},"01M718S06WSZ9Y24JKYM0VVPPE","gap-surfacer","Reference: shared gap- and comment-tracker framework backing \u002Fregulatory-legal:gaps and \u002Fregulatory-legal:comments. Tracks open policy gaps with remediation status, ingests gaps from policy-diff, surfaces what's open and aging, routes to owners, and notifies gap owners via Slack with per-send confirmation. Loaded by the gaps and comments skills before doing substantive work.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Fregulatory-legal\u002Fskills\u002Fgap-surfacer\u002FSKILL.md",[175],{"categoryNo":176,"categoryName":177,"taxonomyType":178,"taxonomyTypeDesc":179},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[114,181,182,183,86,103,184,166,185,186,187,188,110,189,190,191,192,163,164,193],"gap surfacer","shared","tracks","send","confirmation","aging","false","comments","with","work","slack","via","surfaces"]