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

70%

Does it follow best practices?

Impact

83%

1.20x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/0xdarkmatter/claude-mods/claude-code-debug/SKILL.md

Quality

Content

71%Weight 40%Scale 1-5

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

The body is an efficient, actionable troubleshooting reference with a clear diagnostic structure and real validation commands. Its chief defect is that it defers detail to three `./references/*.md` files that are not present in the bundle, leaving dead links where deeper material should be.

Suggestions

Provide the missing `references/common-issues.md`, `references/debug-commands.md`, and `references/troubleshooting-flow.md` files, or remove the references section so navigation is not broken.

Add an explicit "if the check fails, then ..." feedback loop to each Quick Fix subsection (e.g. for the hook fix: if `echo $?` is nonzero, re-run `jq '.'` to validate JSON).

Tighten the loose entries in the Common Issues table (replace "Test server manually with npx" and the `grep -i "use"` heuristic with concrete commands).

Dimension	Reasoning	Score
Conciseness	The body is mostly lean commands with brief inline comments and a compact symptom table, with only minor redundancy such as `claude --debug` appearing in both Quick Diagnostics and Debug Mode Output; it does not over-explain concepts Claude already knows.	4 / 5
Actionability	It provides many copy-paste-ready commands (`claude --debug`, `chmod +x`, `jq '.'`, `just test`) and a concrete hook test invocation, but a few entries are loose heuristics ("Test server manually with npx", `grep -i "use"`) rather than precise steps.	4 / 5
Workflow Clarity	A clear symptom-driven diagnostic flow (Quick Diagnostics → symptom table → per-symptom fixes → Validation) with checkpoints like `echo $?` and `just validate-yaml` is present; minor gaps are the absence of explicit if-fail-then-retry feedback loops in most quick-fix sections.	4 / 5
Progressive Disclosure	Sections are well organized and detail is clearly signaled to one-level-deep references, but the three referenced files (`./references/common-issues.md`, `debug-commands.md`, `troubleshooting-flow.md`) do not exist in the bundle, so the disclosed navigation is broken.	3 / 5
	Total	15 / 20 Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description cleanly states what the skill does and gives an explicit trigger list, with good natural-language trigger coverage and a distinct Claude Code niche. Its main weakness is a terse, single-action "what" that undersells the breadth of issues covered in the body.

Suggestions

Expand the "what" clause to list the concrete sub-actions (e.g. "Debug hooks, skills, agents, MCP, and permissions in Claude Code") so capabilities are comprehensive rather than a single verb.

Add the missing natural trigger terms users say for the body's covered issues, e.g. "MCP connection", "permission denied", "settings".

Consider a "Use when ..." phrasing instead of "Triggers on:" to match the conventional trigger-clause form Claude looks for.

Dimension	Reasoning	Score
Specificity	"Troubleshoot Claude Code extensions and behavior" names the domain and one concrete action (troubleshoot), but does not enumerate the specific sub-actions (hooks, agents, skills) found in the body, so it is not comprehensive enough for a 4.	3 / 5
Completeness	It has both a clear "what" (troubleshoot Claude Code extensions/behavior) and an explicit "when" ("Triggers on:" list), but the "what" is terse and single-action rather than a comprehensive capability list, keeping it just below 5.	4 / 5
Trigger Term Quality	"Triggers on: debug, troubleshoot, not working, skill not loading, hook not running, agent not found" provides good natural-language keyword coverage users would actually say, though a few natural synonyms (e.g. MCP, permission denied) are missing.	4 / 5
Distinctiveness Conflict Risk	Claude-Code-specific triggers like "skill not loading", "hook not running", and "agent not found" carve a clear niche, but generic terms "debug" and "not working" carry minor overlap risk with general debugging skills.	4 / 5
	Total	15 / 20 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
Path: data/skills-md/0xdarkmatter/claude-mods/claude-code-debug/SKILL.md
Commit: 2f57aec

Reviewed: about 23 hours 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.