This description is too terse and lacks the explicit trigger guidance needed for Claude to reliably select it. While it identifies a specific domain (error handling validation), it fails to explain what concrete actions it performs or when it should be used. The cross-language aspect is mentioned but not elaborated with specific language examples or file types.

Suggestions

Add a 'Use when...' clause with trigger terms like 'check error handling', 'exception coverage', 'try-catch blocks', 'error cases'

List specific concrete actions such as 'checks for uncaught exceptions, validates error propagation, identifies missing error cases, reviews try-catch coverage'

Specify which languages are supported or add natural terms like 'Python exceptions', 'JavaScript errors', 'Java try-catch' to improve trigger matching

Dimension	Reasoning	Score
Specificity	Names the domain (error handling) and one action (validate completeness), but lacks concrete details about what validation entails or what specific checks are performed.	2 / 3
Completeness	Only addresses 'what' at a high level (validate error handling) but completely lacks any 'when' guidance or explicit trigger conditions for Claude to know when to select this skill.	1 / 3
Trigger Term Quality	Contains relevant terms like 'error handling' and 'validate' that users might say, but misses common variations like 'exception handling', 'try-catch', 'error checking', or specific language names.	2 / 3
Distinctiveness Conflict Risk	The focus on error handling validation is somewhat specific, but 'across languages' is vague and could overlap with general code review or linting skills.	2 / 3
	Total	7 / 12 Passed

Implementation

100%

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

This is an excellent skill that demonstrates strong technical writing. It efficiently defines scope boundaries, provides executable commands with fallback chains, maintains clear workflow sequencing with explicit validation checkpoints, and appropriately delegates language-specific details to separate files. The JSON output schema is complete and the pass/fail criteria are unambiguous.

Dimension	Reasoning	Score
Conciseness	The skill is lean and efficient, with no unnecessary explanations of concepts Claude already knows. Every section serves a clear purpose and the scope declaration efficiently defines boundaries without padding.	3 / 3
Actionability	Provides fully executable bash commands with fallback chains, concrete file paths for language patterns, and a complete JSON schema for output. The step-by-step process is copy-paste ready.	3 / 3
Workflow Clarity	Clear 5-step sequence with explicit validation logic, fallback behaviors for each step, and well-defined precedence rules. The LSP enrichment step explicitly handles unavailability with graceful degradation.	3 / 3
Progressive Disclosure	Appropriately references external language pattern files (languages/go.md, etc.) for detailed patterns while keeping the main skill focused on the workflow. One-level-deep references are clearly signaled.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Reviewed

2 months ago

Table of Contents

Discovery Implementation Validation