CtrlK
BlogDocsLog inGet started
Tessl Logo

bug-hunter

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

43

Quality

44%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/bug-hunter/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

38%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 reads more like a general debugging tutorial than a targeted skill for Claude. It extensively covers concepts Claude already knows (common bug patterns, basic debugging techniques, general advice) without adding unique, project-specific, or non-obvious value. The workflow is logically sequenced but lacks explicit validation checkpoints and feedback loops, and the content would benefit significantly from being trimmed and restructured.

Suggestions

Remove or drastically reduce the 'Common Bug Patterns' and 'Debugging Techniques' sections—Claude already knows these. Focus on the specific workflow and decision-making process unique to this skill.

Add explicit validation checkpoints with feedback loops, e.g., 'Run the test suite after applying the fix. If tests fail, return to step 5 and re-examine the root cause hypothesis.'

Split the monolithic content: move debugging tools, common patterns, and the documentation template into separate referenced files to improve progressive disclosure.

Make the skill more actionable by specifying concrete tool commands Claude should use (e.g., grep for error patterns, specific test runner commands) rather than generic advice like 'check logs' and 'add logging.'

DimensionReasoningScore

Conciseness

Extensively explains concepts Claude already knows well—common bug patterns (null/undefined, race conditions, off-by-one, type coercion), basic debugging techniques (rubber duck, print debugging), and general advice like 'take a break.' The document is ~250 lines of mostly tutorial-level content that adds little Claude doesn't already possess.

2 / 5

Actionability

Provides concrete code examples for common patterns and some executable snippets, but much of the content is generic guidance rather than specific, executable instructions. The examples are illustrative rather than copy-paste ready for a real debugging workflow—they're teaching examples, not operational procedures.

3 / 5

Workflow Clarity

The 8-step debugging process is clearly sequenced and logical, but validation checkpoints are weak. Step 7 ('Test the Fix') is a checklist without explicit verification commands or feedback loops. There's no 'if the fix doesn't work, go back to step X' explicit loop, and no validation tooling is specified for confirming fixes beyond manual re-testing.

3 / 5

Progressive Disclosure

The entire skill is a monolithic document with no bundle files. At ~250 lines, the common bug patterns, debugging tools, and documentation template sections could easily be split into separate reference files. The 'Related Skills' section references other skills but the main content is all inlined with no structural separation.

2 / 5

Total

10

/

20

Passed

Description

50%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 communicates the general purpose of the skill (systematic debugging) but remains at a high level of abstraction without concrete techniques or tools. It lacks a 'Use when...' clause, which is critical for skill selection, and misses many natural trigger terms users would employ when encountering bugs. The description reads more like a tagline than actionable selection guidance.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases like 'error', 'crash', 'not working', 'broken', 'exception', 'failing test', or 'unexpected behavior'.

Replace generic phrases like 'proven debugging techniques' with concrete actions such as 'analyzes stack traces, isolates failing components, adds diagnostic logging, reproduces issues'.

Include synonyms and variations users might say, such as 'troubleshoot', 'diagnose', 'issue', 'defect', or 'problem' to improve trigger term coverage.

DimensionReasoningScore

Specificity

Names the domain (debugging) and mentions a few actions ('finds and fixes bugs', 'traces from symptoms to root cause', 'implements fixes', 'prevents regression'), but these are fairly generic debugging concepts rather than concrete, specific actions like 'sets breakpoints', 'analyzes stack traces', or 'uses binary search on commits'.

3 / 5

Completeness

Has a clear 'what' (finds and fixes bugs, traces root cause, prevents regression) but completely lacks a 'when' clause. There is no explicit 'Use when...' guidance, which per the rubric should cap completeness at 3.

3 / 5

Trigger Term Quality

Includes some relevant terms like 'bugs', 'debugging', 'root cause', 'fixes', and 'regression', but misses many natural user phrases like 'error', 'crash', 'not working', 'broken', 'exception', 'stack trace', 'failing test', or 'issue'.

3 / 5

Distinctiveness Conflict Risk

Debugging is a somewhat specific domain, but the description is broad enough to overlap with general coding assistance skills, code review skills, or testing skills. Without specifying the type of debugging (e.g., runtime errors, logic bugs, performance issues) or languages/frameworks, overlap risk is moderate.

3 / 5

Total

12

/

20

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.