>
68
68%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 (carrier and freight management), lists multiple concrete capabilities, and includes an explicit 'Use when' clause with relevant trigger terms. The description is well-structured, uses third person voice appropriately, and occupies a distinct niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: managing carrier portfolios, negotiating freight rates, tracking carrier performance, allocating freight, maintaining strategic carrier relationships, scorecarding frameworks, RFP processes, market intelligence, and compliance vetting. | 3 / 3 |
Completeness | Clearly answers both 'what' (managing carrier portfolios, negotiating rates, tracking performance, etc.) and 'when' with an explicit 'Use when managing carriers, negotiating rates, evaluating carrier performance, or building freight strategies' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'carriers', 'freight rates', 'carrier performance', 'negotiating rates', 'RFP', 'scorecarding', 'freight strategies', 'compliance vetting'. These cover a good range of terms a transportation manager would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific niche in carrier/freight management with distinct domain-specific triggers like 'carrier portfolios', 'freight rates', 'RFP processes', and 'compliance vetting' that are unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads like a comprehensive transportation management handbook rather than a concise, actionable skill file for Claude. While the domain expertise is genuine and the thresholds/benchmarks are valuable, the content is far too verbose, lacks executable artifacts (templates, scripts, tool commands), and dumps everything into a single file without progressive disclosure. The strongest elements are the escalation protocols table and the decision frameworks, but even these could be more concise.
Suggestions
Reduce content by 60-70%: Remove explanatory text Claude already knows (what FSC is, how freight markets work, what LTL means) and keep only the specific thresholds, decision criteria, and non-obvious expert heuristics.
Split into multiple files: Create separate reference files for scorecarding (SCORECARD.md), RFP process (RFP_PROCESS.md), compliance vetting (COMPLIANCE.md), and rate negotiation (NEGOTIATION.md), with SKILL.md serving as a concise overview with links.
Add executable templates: Include a copy-paste ready scorecard template (CSV/markdown table), an RFP evaluation matrix template, and a carrier onboarding checklist that can be directly used rather than described.
Add explicit validation checkpoints to workflows: For the carrier onboarding and RFP processes, insert 'STOP and verify' steps (e.g., 'Do not proceed to rate negotiation until FMCSA compliance check passes all criteria above').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This is extremely verbose at ~3000+ words. While the domain knowledge is accurate, it extensively explains concepts and industry fundamentals that Claude already knows (what fuel surcharges are, what LTL means, how freight markets work). The rate negotiation section, portfolio strategy, and market intelligence sections read like a textbook rather than actionable instructions. Much of this could be condensed to decision tables and key thresholds. | 1 / 3 |
Actionability | The skill provides specific thresholds (OTD ≥95%, tender acceptance ≥90%, claims ratio <0.5%), concrete dollar ranges for accessorials, and clear decision frameworks with criteria. However, there is no executable code, no API calls, no specific tool commands, and no copy-paste ready templates for scorecards, RFP documents, or carrier evaluation forms. The guidance is detailed but remains descriptive rather than directly executable. | 2 / 3 |
Workflow Clarity | The RFP process and carrier selection decision tree provide reasonable step sequences, and the escalation protocols table is well-structured with timelines. However, validation checkpoints are largely missing — there's no explicit 'verify before proceeding' pattern in the onboarding workflow, no feedback loops for corrective action processes, and the carrier exit criteria lack a documented corrective action workflow sequence. | 2 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to external files. All content — rate negotiation fundamentals, scorecarding details, RFP processes, market intelligence, compliance vetting, decision frameworks, edge cases, communication patterns, and escalation protocols — is inlined in a single massive document. This would benefit enormously from splitting into separate reference files (e.g., SCORECARDING.md, RFP_PROCESS.md, COMPLIANCE.md, RATE_NEGOTIATION.md) with the SKILL.md serving as a concise overview. | 1 / 3 |
Total | 6 / 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