Name: bug-hunter
Rating: 52.8 (1 reviews)
Author: administrakt0r

bug-hunter

Systematically finds and fixes bugs using proven debugging techniques. Traces from symptoms to root cause, implements fixes, and prevents regression.

Quality

59%

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/AI-Agents-Safe-Coding-Skills-claude/skills/bug-hunter/SKILL.md

The canonical home for this skill is bug-hunter in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

56%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 skill offers a strong, actionable 8-step debugging workflow with real executable examples, but is weighed down by verbose re-explanation of basic programming concepts and a lack of any file-level progressive disclosure. Trimming beginner material and splitting the catalog into a reference file would notably improve it.

Suggestions

Cut or condense the Common Bug Patterns and Debugging Techniques sections, which re-teach off-by-one errors, type coercion, and rubber-ducking that Claude already knows.

Move the bug-pattern catalog and tool-config snippets (DevTools, Node, VS Code) into a references file and link to it from a leaner SKILL.md overview.

Make the feedback loop explicit in the workflow, e.g. after 'Test the Fix', add 'If the bug still reproduces, return to step 3 and revise your hypothesis.'

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: sections like Common Bug Patterns, Rubber Duck Debugging, and 'When You're Stuck' re-explain basics Claude already knows (off-by-one, type coercion, race conditions, 'walk away for 10 minutes'), adding several padded sections beyond what the skill uniquely contributes.	2 / 5
Actionability	Concrete, mostly executable guidance throughout (git bisect commands, `node --inspect`, .vscode/launch.json, jest tests, console.log checkpoints) with only minor gaps where examples are illustrative patterns rather than copy-paste-ready for a specific case.	4 / 5
Workflow Clarity	A clearly numbered 8-step process with explicit validation steps (step 7 'Test the Fix', step 8 'Prevent Regression'); not a 5 because the error-recovery feedback loop (if the fix fails, revisit root cause) is only implicit rather than spelled out.	4 / 5
Progressive Disclosure	Section headers are well-organized, but at ~370 inlined lines with no bundle files and no references to separate detail files, content that could be split out (bug-pattern catalog, tool configs) lives entirely in SKILL.md; the under-50-line exception does not apply.	3 / 5
	Total	13 / 20 Passed

Description

62%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 states a clear, multi-action 'what' with natural trigger keywords, but omits any explicit 'Use when...' trigger clause, which caps completeness and limits distinctiveness. Adding concrete trigger phrases would lift the two weakest dimensions.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user reports a bug, error, or unexpected behavior, or asks to debug or fix something that isn't working.'

Include natural synonyms like 'error', 'broken', and 'not working' alongside 'bugs' and 'debugging' to broaden trigger coverage.

Sharpen distinctiveness by naming the methodology niche (e.g. evidence-based root-cause tracing) to reduce overlap with generic debugging skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('finds and fixes bugs', 'Traces from symptoms to root cause', 'implements fixes', 'prevents regression') covering the debugging lifecycle, though 'proven debugging techniques' is mild fluff and the opening verb is slightly generic; not a 5 because coverage has minor gaps.	4 / 5
Completeness	The 'what' is clear (trace, fix, prevent regression) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	'bugs', 'debugging', 'fixes', and 'regression' are natural terms users would say, but common variations like 'error', 'broken', or 'not working' are missing, so it falls just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	'Bug hunting/debugging' is a recognizable niche but broad enough to overlap with related debugging skills (the body itself cross-references @systematic-debugging), so it is only somewhat distinct.	3 / 5
	Total	14 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/bug-hunter/SKILL.md
Commit: 57c135b

Reviewed: 1 day 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.