CtrlK
BlogDocsLog inGet started
Tessl Logo

customs-trade-compliance

Codified expertise for customs documentation, tariff classification, duty optimisation, restricted party screening, and regulatory compliance across multiple jurisdictions.

54

Quality

61%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/customs-trade-compliance/SKILL.md

The canonical home for this skill is customs-trade-compliance in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

60%Weight 40%Scale 1-5

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

The body is a dense, well-structured compliance manual with concrete regulatory guidance and clear decision workflows, but it is noticeably verbose for a SKILL.md and inlines encyclopedic detail that would be better split into the existing reference files.

Suggestions

Move the full GRI breakdown, penalty-tier framework, escalation table, and performance-indicator table into reference files, keeping SKILL.md a lean overview that links to them.

Trim general-knowledge explanations Claude already has (e.g., what the Harmonized System is, what a Bill of Lading is) and retain only the specific regulatory citations, deadlines, thresholds, and formulas.

Add explicit validation gates to the classification and valuation workflows (e.g., 'Verify binding-ruling alignment before filing') to close the remaining workflow-checkpoint gaps.

DimensionReasoningScore

Conciseness

The ~235-line body inlines large encyclopedic sections (full GRI breakdown, penalty-tier framework, escalation table, performance-indicator table) and explains concepts Claude already knows (what the Harmonized System is, what a Bill of Lading is), making it noticeably verbose even though much of the regulatory detail is accurate.

2 / 5

Actionability

It provides concrete, specific guidance — numbered decision procedures (7-step classification, 6-step FTA qualification, 6-method valuation with 'Fails when' conditions), exact regulatory citations (19 CFR §141.86, 19 USC §1592, 19 CFR §162.74), penalty multipliers, filing deadlines, and an 85% screening threshold — which is highly actionable for an instruction skill, with only minor gaps where steps reference external databases (CROSS, BTI).

4 / 5

Workflow Clarity

Multi-step processes (classification, FTA qualification, valuation selection, screening assessment) are clearly numbered with documentation-as-validation checkpoints ('Document the rationale', 'Check for binding rulings') and explicit fail conditions, but a few workflows lack an explicit 'verify before proceeding' gate, leaving it just below the full-feedback-loop anchor of 5.

4 / 5

Progressive Disclosure

All three bundle files (decision-frameworks.md, edge-cases.md, communication-templates.md) exist and are clearly signaled with one-level-deep links, but the SKILL.md itself is a full manual rather than a lean overview — substantial detail (escalation tables, performance indicators, full GRI list) is inlined that could live in references, leaving minor organization gaps.

4 / 5

Total

14

/

20

Passed

Description

62%Weight 40%Scale 1-5

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

The description names a clear, distinctive niche and several specific capabilities, but it lacks an explicit 'Use when' trigger clause and omits the most common natural trigger terms (HS codes, Incoterms, import/export), capping completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' trigger clause — e.g., 'Use when classifying goods under HS/HTS codes, choosing Incoterms, preparing import/export documentation, or screening restricted parties' — so Claude knows when to invoke the skill.

Include the most common user trigger terms ('HS codes', 'Incoterms', 'import/export', 'FTA') alongside the current capability list to raise trigger-term coverage.

Reframe 'Codified expertise for...' as concrete actions ('Classifies goods under HS/HTS codes, determines Incoterms, optimises duty...') to convert noun-phrase knowledge areas into executable-action specificity.

DimensionReasoningScore

Specificity

Lists several specific capability domains — 'customs documentation, tariff classification, duty optimisation, restricted party screening, and regulatory compliance' — giving broad coverage, but the 'Codified expertise for' framing presents knowledge areas as noun phrases rather than concrete executable actions, leaving it just below the comprehensive-verbs anchor of 5.

4 / 5

Completeness

The 'what' is clear and detailed, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

It includes some natural, specific terms ('customs documentation', 'tariff classification', 'duty', 'restricted party screening') but omits the most common user trigger phrases — 'HS/HTS codes', 'Incoterms', 'import/export', 'FTA' — so it sits at 'missing common variations or synonyms' rather than full coverage.

3 / 5

Distinctiveness Conflict Risk

It occupies a clear, specialized niche (customs and trade compliance across jurisdictions) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.