>
76
76%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its domain (freight/logistics exception handling), lists specific capabilities, and includes an explicit 'Use when...' clause with natural trigger terms. The description is concise yet comprehensive, covering both the scope of expertise and the situations that should activate it. The only minor note is the credential claim ('15+ years operational experience') which is somewhat fluffy but doesn't detract significantly from the functional clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: handling freight exceptions, shipment delays, damages, losses, carrier disputes, escalation protocols, claims procedures, and judgment frameworks. | 3 / 3 |
Completeness | Clearly answers both 'what' (handling freight exceptions, delays, damages, losses, disputes with escalation protocols and claims procedures) and 'when' with an explicit 'Use when...' clause listing four trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'shipping exceptions', 'freight claims', 'delivery issues', 'carrier disputes', 'shipment delays', 'damages', 'losses'. These cover common variations of how logistics professionals would describe these problems. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a very clear niche in freight/logistics exception handling. The domain-specific terminology (freight exceptions, carrier disputes, claims procedures) makes it highly unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill contains deep domain expertise with well-structured decision frameworks, escalation protocols, and edge cases that would genuinely help Claude handle freight exceptions. However, it is far too verbose — much of the content explains industry fundamentals that Claude already knows, and the entire document could be condensed to perhaps 40% of its current length without losing actionable value. The lack of progressive disclosure means the full ~2500-word document loads into context every time, wasting tokens on reference material that could be in linked files.
Suggestions
Reduce content by 50-60% by removing explanations of basic logistics concepts (what LTL is, what a BOL is, what TMS/WMS are) and trimming the exception taxonomy to just the resolution-relevant details Claude wouldn't already know.
Split carrier-specific behaviors, claims process details, edge cases, and communication templates into separate linked reference files (e.g., CARRIERS.md, CLAIMS.md, EDGE-CASES.md) to keep the main skill as a concise overview with navigation.
Add concrete tool-usage examples — e.g., specific carrier portal URLs/APIs, exact claim form field mappings, or template files that Claude can populate, rather than abstract descriptions of what templates should contain.
Move seasonal patterns and fraud red flags to a separate reference file since they are contextual knowledge rather than actionable workflow steps.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This is extremely verbose at ~2500+ words. It explains concepts Claude already knows (what LTL/FTL/parcel means, what TMS/WMS are, basic definitions of exception types). Much of the content reads like a training manual for a human logistics analyst rather than concise instructions for Claude. The role description, seasonal patterns, and fraud sections could be dramatically condensed. | 1 / 3 |
Actionability | The skill provides concrete decision frameworks (dollar thresholds, escalation timelines, severity classifications) and useful templates, which are actionable. However, there is no executable code, no specific API calls, no tool usage instructions, and the templates are skeletal outlines rather than copy-paste ready artifacts. The guidance is specific but remains at the procedural/judgment level rather than executable. | 2 / 3 |
Workflow Clarity | The multi-step workflows are clearly sequenced with explicit validation checkpoints. The escalation protocol table provides specific triggers, actions, and timelines. The severity classification framework has clear axes with defined thresholds. The 'How It Works' section provides a clear 5-step sequence, and the escalation chain has defined time-based progression. The eat-the-cost framework includes clear decision boundaries. | 3 / 3 |
Progressive Disclosure | The content is structured with clear headers and sections, but it's essentially a monolithic document with everything inline. The 'Additional Resources' section at the end vaguely references external materials but doesn't link to specific files. Content like carrier-specific behaviors, claims process details, and edge cases could be split into separate reference files with clear navigation from the main skill. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
Reviewed
Table of Contents