A well-sequenced troubleshooting workflow with clear validation checkpoints and lean step descriptions. Its main weaknesses are duplicated reference sections, comment-style rather than executable examples, and referenced bundle files that are not actually present.

Suggestions

Collapse the duplicate 'Refs' and 'References' sections into a single, clearly signaled reference block.

Provide at least one concrete, executable example (e.g., a real search query string and an actual command the user runs) instead of comment-style pseudocode.

Either ship the referenced files under references/protocols/ or inline the essential detail so the skill is self-contained.

Dimension	Reasoning	Score
Conciseness	The workflow steps are terse and assume Claude's competence, but the duplicated 'Refs' and 'References' sections and verbose Philosophy/Anti-Pattern 'Why:' lines leave padding that could be trimmed, so it is not a clean 3.	2 / 3
Actionability	Named techniques (Wolf Fence, 5 Whys, OODA) and a concrete search-query format give actionable guidance, but the heavy detail is offloaded to references and the Usage Examples are comment-style pseudocode rather than fully executable steps.	2 / 3
Workflow Clarity	A clearly numbered 0→6 sequence with explicit checkpoints ("Exit when root cause confirmed and fix verified", "Only if diagnosis inconclusive") and a validation guard for empty AskUserQuestion answers matches the top anchor.	3 / 3
Progressive Disclosure	The overview-plus-references structure is one level deep and well signaled, but the referenced bundle files (references/protocols/diagnose.md, etc.) do not exist in the bundle and the reference list is duplicated across two sections, keeping it below 3.	2 / 3
	Total	9 / 12 Passed

Description

82%

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 compact, well-structured description with strong trigger-term coverage and an explicit Use-when clause. It is held back from a top score by broad trigger terms that invite overlap and a methodology-level rather than action-level specificity.

Suggestions

Sharpen specificity by naming concrete actions (e.g., "reproduce, isolate via bisect, locate root cause at a file:line") instead of only the methodology.

Narrow trigger terms or add a distinguishing qualifier to reduce overlap with general debugging skills.

Drop the redundant 'Triggers:' list or merge it into the 'Use when' clause to avoid restating the same keywords twice.

Dimension	Reasoning	Score
Specificity	Names the domain and a methodological approach ("Search-first troubleshooting with diagnostic phase") but does not list multiple distinct concrete actions like the top anchor, so it stops at 2 rather than 3.	2 / 3
Completeness	Explicitly answers what ("Search-first troubleshooting with diagnostic phase") and when ("Use when user reports an error, bug, or something not working") with explicit trigger guidance.	3 / 3
Trigger Term Quality	"Triggers: debug, error, broken, not working, failing, crash, exception" gives broad, natural coverage of terms a user would actually say, matching the top anchor.	3 / 3
Distinctiveness Conflict Risk	The error/bug/debug niche is reasonably clear but those trigger terms are broad and could overlap with general coding or debugging skills, so it is not a clean distinct niche.	2 / 3
	Total	10 / 12 Passed

Validation

75%

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 — 12 / 16 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
relative_links	Relative link issues: 3 missing, 2 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 7 missing, 5 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Reviewed

10 days ago

Table of Contents

Discovery Implementation Validation