CtrlK
BlogDocsLog inGet started
Tessl Logo

debugger

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

48

Quality

53%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/debugger/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

48%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 has a clear sequenced debugging workflow but is held back by templated boilerplate, the complete absence of concrete executable guidance, and a broken reference to a non-existent playbook. It reads as a generic template populated with the word 'debugger' rather than debugger-specific expertise.

Suggestions

Add concrete, executable guidance: example debug commands, how to run the failing test, a minimal logging snippet, or a copy-paste hypothesis-testing pattern.

Remove the templated 'Use this skill when / Do not use this skill when' filler and the generic Instructions bullets, or replace them with debugging-specific trigger conditions.

Either create 'resources/implementation-playbook.md' with the promised detailed examples, or drop the reference; a pointer to a missing file misleads Claude.

DimensionReasoningScore

Conciseness

The debugging-specific lists ('When invoked', 'Debugging process', 'For each issue') are lean, but the templated 'Use this skill when / Do not use this skill when' boilerplate ('Working on debugger tasks or workflows') and generic Instructions bullets ('Apply relevant best practices and validate outcomes') are padding, fitting 'Mostly efficient but includes some unnecessary explanation'; not 2 because the core content is not severely verbose.

3 / 5

Actionability

Guidance is high-level hints only ('Capture error message and stack trace', 'Add strategic debug logging') with no code, commands, or specific tools, matching 'Minimal concrete guidance; high-level hints but missing the specific steps to execute'; not 1 because it gives a structured, ordered process rather than purely abstract description.

2 / 5

Workflow Clarity

The numbered 'When invoked' sequence (capture -> identify reproduction -> isolate -> implement minimal fix -> verify) is clearly ordered with a 'Verify solution works' checkpoint, matching 'Clear sequence with most checkpoints present; minor validation gaps'; not 5 because there is no explicit error-recovery feedback loop (what to do when verification fails).

4 / 5

Progressive Disclosure

The body is sectioned into headers, but its only external reference points to 'resources/implementation-playbook.md', which does not exist (no references/scripts/assets dirs), so the pointer is broken, fitting 'references present but not clearly signaled'; not 4 because the dead reference is a real navigation defect, and not 2 because the section structure itself is reasonable.

3 / 5

Total

12

/

20

Passed

Description

57%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 answers both what and when and targets a recognizable niche, but its 'when' clause is generic and it never names concrete debugging actions. Strengthening trigger specificity and listing concrete capabilities would lift it from a mid-range result.

Suggestions

Replace the generic 'when encountering any issues' with concrete trigger phrases users actually say, e.g. 'Use when the user reports a bug, a failing test, a crash, an exception, or unexpected behavior.'

Add 2-3 concrete actions to the 'what' clause, e.g. 'Captures stack traces, isolates root cause, and implements a minimal verified fix.'

Include common synonyms like 'bug', 'crash', and 'exception' to improve trigger-term coverage.

DimensionReasoningScore

Specificity

It names the domain ('Debugging specialist') and the problem types ('errors, test failures, and unexpected behavior') but lists no concrete actions a user would invoke, matching 'Names the domain but actions are minimal or generic'; not a 3 because no executable actions (capture, isolate, fix) are stated.

2 / 5

Completeness

Both what ('Debugging specialist for errors, test failures, and unexpected behavior') and when ('Use proactively when encountering any issues') are explicit, but the 'when' is generic rather than concrete trigger phrases, matching 'Has both what and when; when could be more explicit or specific'; not 5 because no concrete trigger phrases.

4 / 5

Trigger Term Quality

Natural terms like 'errors', 'test failures', 'unexpected behavior', and 'issues' are present, but common debugging synonyms users actually say ('bug', 'crash', 'exception', 'stack trace', 'not working') are missing, fitting 'Some relevant keywords but missing common variations or synonyms'; not a 4 due to those notable gaps.

3 / 5

Distinctiveness Conflict Risk

'Debugging specialist' is a clearly distinct niche with mostly distinct triggers, but the phrase 'when encountering any issues' broadens it and creates minor overlap risk with other support skills, matching 'Mostly distinct; minor overlap risk'; not 3 because debugging is a well-defined, recognizable niche.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.