claude-code-debug

Troubleshoot Claude Code extensions and behavior. Triggers on: debug, troubleshoot, not working, skill not loading, hook not running, agent not found.

1.20x

Quality

—

Does it follow best practices?

Impact

83%

1.20x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

80%

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

A concise, highly actionable troubleshooting reference with executable commands and a clear diagnostic table. It is held back by absent feedback-loop workflows and by 'Additional Resources' links pointing to reference files that do not exist.

Suggestions

Add an explicit diagnose→fix→verify feedback loop for each fix (e.g., after a hook fix, re-run /hooks and the manual echo test to confirm resolution) to raise workflow clarity.

Create the referenced ./references/common-issues.md, debug-commands.md, and troubleshooting-flow.md files—or remove the dangling 'Additional Resources' links—so the signaled navigation actually resolves.

Dimension	Reasoning	Score
Conciseness	The body is lean—compact symptom tables and executable command blocks with no over-explanation of concepts Claude already knows—so it matches the 'lean and efficient' anchor despite a mildly redundant intro line.	3 / 3
Actionability	It provides concrete, copy-paste-ready commands throughout (claude --debug, chmod +x, jq '.', just test) and a symptom→check table, matching the 'fully executable' anchor.	3 / 3
Workflow Clarity	Per-issue fix sequences exist with some validation (echo $?, just validate-*), but there is no cohesive diagnose→fix→verify feedback loop, so it sits at anchor 2 rather than 3.	2 / 3
Progressive Disclosure	References are well-signaled and one level deep, but the referenced ./references/*.md files do not exist on disk, so the navigation is broken and it cannot reach anchor 3.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 strong, third-person description with explicit trigger guidance and natural keywords that clearly scopes the skill to Claude Code debugging. The only weakness is that the capability statement is a single general action rather than a list of specific concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('Claude Code extensions and behavior') and one main action ('Troubleshoot') plus specific trigger symptoms, but does not list multiple distinct concrete actions, so it falls short of anchor 3.	2 / 3
Completeness	It states what the skill does ('Troubleshoot Claude Code extensions and behavior') and gives explicit 'Triggers on:' guidance equivalent to a 'Use when' clause, satisfying both what and when.	3 / 3
Trigger Term Quality	The 'Triggers on: debug, troubleshoot, not working, skill not loading, hook not running, agent not found' list covers natural phrases a user would actually say, matching anchor 3.	3 / 3
Distinctiveness Conflict Risk	The triggers target Claude Code internals (skill loading, hooks, agents, MCP), forming a clear debugging niche unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: NeverSight/skills_feed
Commit: 26d37ce

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.