debugger

Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.

Quality

38%

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 ./skills/debugger/SKILL.md

Quality

Content

35%Scale 1-5

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

This skill is a generic, high-level debugging guide that provides abstract advice rather than actionable, concrete instructions. It suffers from vague language, redundant sections, and a lack of executable examples or specific tool usage. The workflow structure is reasonable but lacks validation checkpoints and feedback loops essential for debugging tasks.

Suggestions

Replace abstract instructions with concrete, executable examples showing specific debugging techniques (e.g., how to add debug logging, how to use a debugger, specific commands for inspecting state).

Remove boilerplate sections ('Use this skill when/Do not use this skill when') and the generic 'Instructions' bullets that add no debugging-specific value.

Add validation checkpoints and feedback loops to the workflow, such as 'If hypothesis is disproven, return to step 3 with new evidence' and explicit verification commands.

Either provide the referenced 'resources/implementation-playbook.md' bundle file or inline the most critical debugging patterns and examples directly in the skill.

Dimension	Reasoning	Score
Conciseness	The content is noticeably verbose with several unnecessary sections. The 'Use this skill when' and 'Do not use this skill when' sections are generic boilerplate that add no value. Phrases like 'You are an expert debugger specializing in root cause analysis' explain Claude's role unnecessarily. Multiple bullet lists repeat similar ideas (e.g., 'Apply relevant best practices and validate outcomes' is vague padding).	2 / 5
Actionability	The guidance is entirely high-level and abstract with no concrete code, commands, or specific examples. Instructions like 'Capture error message and stack trace' and 'Add strategic debug logging' are vague directions without showing how to actually do these things. No executable code, no specific tool usage, no concrete examples of debugging patterns.	2 / 5
Workflow Clarity	There is a numbered sequence (capture error → identify reproduction → isolate failure → implement fix → verify), which provides a reasonable high-level workflow. However, there are no validation checkpoints, no feedback loops for when hypotheses are wrong, and no explicit verification steps beyond 'Verify solution works.' The workflow is present but lacks the specificity and checkpoints needed for robust debugging.	3 / 5
Progressive Disclosure	There is a reference to 'resources/implementation-playbook.md' for detailed examples, which is a reasonable attempt at progressive disclosure. However, no bundle files exist to support this reference, the reference is vaguely signaled ('If detailed examples are required'), and the content itself could benefit from better structural organization rather than having multiple overlapping bullet lists inline.	3 / 5
	Total	10 / 20 Passed

Description

41%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 is too vague and broad to effectively differentiate this skill from others. While it identifies the general domain of debugging and includes a 'Use when' clause, the trigger phrase 'any issues' is overly generic and the description lacks concrete actions that would help Claude understand what this skill specifically does. The keyword coverage misses many natural terms users would employ when seeking debugging help.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Analyzes stack traces, diagnoses root causes, inspects error logs, and suggests fixes for code defects.'

Replace the overly broad 'any issues' trigger with specific scenarios, e.g., 'Use when the user encounters error messages, exceptions, stack traces, failing tests, crashes, or says something is broken or not working.'

Add natural synonyms and variations users would say, such as 'bug', 'crash', 'exception', 'not working', 'broken', 'fix', 'traceback', to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (debugging) and lists broad categories (errors, test failures, unexpected behavior) but provides no concrete actions like 'analyze stack traces', 'set breakpoints', or 'inspect variables'. The actions are entirely absent.	2 / 5
Completeness	The 'what' is vaguely stated as 'debugging specialist for errors, test failures, and unexpected behavior' but lacks concrete actions. There is a 'when' clause ('Use proactively when encountering any issues') but it is extremely broad and non-specific, essentially saying 'use for any issue', which barely qualifies as explicit trigger guidance.	3 / 5
Trigger Term Quality	Includes some relevant keywords like 'errors', 'test failures', 'unexpected behavior', and 'debugging', but misses many natural user phrases such as 'bug', 'crash', 'exception', 'stack trace', 'not working', 'broken', or 'fix'.	3 / 5
Distinctiveness Conflict Risk	'Any issues' is extremely broad and would overlap with many other skills that handle errors, testing, code review, or troubleshooting. The description lacks specificity about what kind of debugging or what technologies, making conflict risk high.	2 / 5
	Total	10 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/debugger/SKILL.md
Commit: 57c135b

Reviewed: 3 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.