CtrlK
BlogDocsLog inGet started
Tessl Logo

infringement-triage

Infringement triage across trademark, copyright, patent, and trade secret — a flag list with the factors cutting each way, not a finding. Use when assessing whether someone is infringing your IP or whether you might be infringing theirs, when a knockoff or copycat surfaces, or when deciding whether a matter is worth pursuing and how.

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 concrete doctrine. Its main weakness is verbosity from guardrail repetition and a monolithic structure that could push per-right detail into separate reference files.

Suggestions

Consolidate the 'triage, not a finding' guardrail into one canonical block and reference it from other sections instead of repeating the full text in four places.

Move per-right doctrine (e.g., the full trademark confusion factors, copyright fair-use analysis) into separate reference files in a references/ bundle, keeping SKILL.md as an overview with one-level-deep pointers.

Trim rhetorical emphasis prose ('The loudest guardrail in the plugin. Do not drop it. Do not soften it.') to instruction-only phrasing that preserves the rule without the flourish.

DimensionReasoningScore

Conciseness

Most content earns its place (statutes, case cites, per-right factor lists), but the 'triage, not a finding' guardrail is repeated in four places and rhetorical prose ('The loudest guardrail in the plugin. Do not drop it. Do not soften it.') adds padding; could be tightened.

2 / 3

Actionability

Highly concrete guidance: per-right factor checklists, specific statutes and named cases, prefix-based branching (D/RE/PP), and a complete output-format template — fully actionable instruction-only content.

3 / 3

Workflow Clarity

A numbered 8-step workflow with explicit gating ('Wait for the answer before walking factors'), a PLACEHOLDER config bounce, provisional-mode branch, and a citation-verification checkpoint provide clear sequencing with validation feedback loops.

3 / 3

Progressive Disclosure

Cross-skill routing (fto-triage, cease-desist, takedown, claim-chart) is one-level-deep and clearly signaled, but the file is monolithic with substantial per-right doctrine inline that could be split into reference files; no bundle files exist to offload detail.

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 strong, well-targeted description: concrete on what it produces, explicit on when to use it, and naturally phrased. Third-person voice is maintained throughout.

DimensionReasoningScore

Specificity

Names the full domain scope ('trademark, copyright, patent, and trade secret') and a concrete deliverable ('a flag list with the factors cutting each way, not a finding'), matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what (flag-list triage across four rights, not a finding) and when via a clear 'Use when...' clause with multiple trigger scenarios.

3 / 3

Trigger Term Quality

Uses natural user phrasing ('knockoff or copycat surfaces', 'infringing your IP', 'worth pursuing and how'), giving good coverage of terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (infringement triage) with distinct triggers; unlikely to fire for adjacent legal skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (629 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
anthropics/claude-for-legal
Reviewed

Table of Contents

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.