clearance

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.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, actionable legal triage skill with strong workflow sequencing and validation gates. Its weaknesses are repetition of the same scope guardrail across multiple sections and a monolithic structure that, given its length, would benefit from splitting stable reference material into bundled files.

Suggestions

State the 'first pass, not a clearance opinion' guardrail once at the top and reference it; remove the verbatim restatements in the dedicated section, output template, and 'What this skill does not do' to recover token budget.

Extract the stable reference material — the per-jurisdiction confusion-framework table (du Pont / Polaroid / Sleekcraft / EU / UK) and the full output-format template — into reference files (e.g. references/confusion-frameworks.md, references/output-template.md) and link them one level deep from SKILL.md.

Move the adjacent-families catalog and cross-language sweep guidance into a reference file, keeping only the decision rule and the confirmation prompt inline.

Dimension	Reasoning	Score
Conciseness	The guidance is domain-specific and largely non-redundant in substance, but the same guardrail ('This is a first pass, not a clearance opinion' / 'never concludes a mark is clear') is restated verbatim four times (opening, the dedicated blockquote section, the output template, and 'What this skill does not do'), which is padding a competent reader does not need.	2 / 3
Actionability	For an instruction-only skill it is highly concrete: a knockout table with per-bar flag criteria, a batched intake prompt, named confusion tests with citations, a full output template, and explicit output paths — copy-paste ready guidance rather than abstraction.	3 / 3
Workflow Clarity	The 8-step instruction sequence is explicit and carries real validation checkpoints: the no-search fallback statement, the user-confirmation gate before concluding the adjacent-families sweep, and the citation-verification section, with clear feedback on what to do when each fails.	3 / 3
Progressive Disclosure	At ~487 lines this is a monolithic wall of text with no bundle/reference files; well-organized into sections, but content that clearly belongs in reference files (the per-jurisdiction confusion frameworks, the full output template, the adjacent-families catalog) is inlined rather than split out and signaled one level deep.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A tight, third-person description that states the action, the trigger conditions, and an explicit scope guardrail ('never concludes a mark is clear'). It satisfies the what/when/specificity/distinctiveness criteria without padding.

Dimension	Reasoning	Score
Specificity	The description names multiple concrete actions — 'knockout + similar-marks check producing a flag list' — within a clearly bounded domain (trademark clearance first pass), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It explicitly answers both what ('Trademark clearance first pass — knockout + similar-marks check producing a flag list, not a clearance opinion') and when via an explicit 'Use when...' clause, matching the top anchor.	3 / 3
Trigger Term Quality	It surfaces natural phrasings a user would actually say — 'a new mark is proposed', 'whether a mark is available', 'run a knockout search', 'likelihood-of-confusion factors' — giving good coverage rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	The trademark-clearance niche is distinct and the triggers ('knockout search', 'mark is available', 'likelihood-of-confusion') are unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: anthropics/claude-for-legal
Path: ip-legal/skills/clearance/SKILL.md
Commit: 4a6c651

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.