debugger

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/claude-code/skills/debugger/SKILL.md

Quality

Content

62%

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

The content delivers a clear, well-gated debugging workflow with strong feedback loops, but it pays for redundant emphasis on the same anti-guessing message and pseudocode/abstract steps that limit actionability and conciseness.

Suggestions

Collapse the overlapping Overview, Iron Law, Red Flags, and Common Rationalizations sections into a single concise 'avoid symptom-fixing' block to remove repetition.

Replace the pseudocode instrumentation block with concrete, copy-pasteable logging snippets or named tool patterns.

Flesh out abstract steps like 'Gather Evidence' and 'Trace Data Flow' with specific techniques (e.g., breakpoint/logging placement, caller-stack inspection).

Dimension	Reasoning	Score
Conciseness	The body is mostly tight bullets and tables without explaining concepts Claude already knows, but the anti-guessing message is repeated across the Overview, Iron Law, When to Use, Red Flags, and Common Rationalizations sections, which could be consolidated.	2 / 3
Actionability	Concrete procedural steps (read stack traces, git diff, trace data flow) and a diagnostic instrumentation template are provided, but the instrumentation block is pseudocode and several directives like 'Gather Evidence' or 'Trace Data Flow' stay abstract without specific techniques.	2 / 3
Workflow Clarity	The four phases are explicitly sequenced with a 'MUST complete each phase before proceeding' gate, and phases 3 and 4 contain real feedback loops (verify before continuing; stop and question architecture after 3 failed fixes), plus a Quick Reference checklist.	3 / 3
Progressive Disclosure	The skill is a single ~155-line file with clear sections and no nested references, but it exceeds the 'simple skill under 50 lines' threshold, carries no one-level-deep bundle references, and the redundant red-flag/rationalization content suggests organization could be tighter.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 is a well-constructed trigger clause in clean third-person imperative voice, but it over-indexes on 'when' and leaves the skill's actual capabilities implicit, capping most dimensions at the middle level.

Suggestions

Add a brief capability clause stating what the skill does, e.g. 'Systematically investigate root causes via a four-phase debugging process' before the 'Use when' trigger.

Broaden trigger terms to include common user phrasings like 'error', 'crash', 'broken', or 'not working as expected'.

Tighten distinctiveness by tying the trigger to the unique 'find root cause before fixing' behavior rather than generic 'unexpected behavior'.

Dimension	Reasoning	Score
Specificity	The description names the domain ('any bug, test failure, or unexpected behavior') and the action context ('before proposing fixes'), but does not enumerate the concrete debugging capabilities the skill performs, so it stops at naming domain and some actions rather than listing multiple specific actions.	2 / 3
Completeness	The 'Use when...' trigger clause is explicit and strong, but the 'what does this do' half is only implied (systematic root-cause debugging), never stated, so it does not clearly answer both what and when.	2 / 3
Trigger Term Quality	Phrases like 'bug', 'test failure', and 'unexpected behavior' are natural user terms, but common variations such as 'error', 'crash', 'broken', or 'not working' are missing, so coverage is relevant but incomplete.	2 / 3
Distinctiveness Conflict Risk	The 'before proposing fixes' framing gives it a recognizable debugging niche, but the broad 'unexpected behavior' trigger could overlap with adjacent engineering or test-generation skills, so it is somewhat specific yet not fully conflict-free.	2 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: darrenhinde/OpenAgentsControl
Path: plugins/claude-code/skills/debugger/SKILL.md
Commit: 37ca233

Reviewed: 2 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.