CtrlK
BlogDocsLog inGet started
Tessl Logo

debugging

To investigate errors, test failures, and unexpected behavior — root cause before fix.

60

Quality

71%

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 ./instructions/r2/core/skills/debugging/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 body is a concise, well-structured debugging methodology with strong workflow sequencing, explicit validation, and feedback loops. It is instruction-only but actionable, with only minor redundancy and a couple of unexplained references.

DimensionReasoningScore

Conciseness

The body is lean — short XML-tagged sections, numbered lists, no padding about what debugging is — with only minor redundancy (best_practices/pitfalls restate phase-1 steps); not a 5 because the checklist and pitfalls overlap content already covered.

4 / 5

Actionability

Concrete instructions like 'git diff, new dependencies, config changes', 'add diagnostic logging at each boundary', and 'create a failing test that reproduces the bug' give mostly executable guidance; not a 5 because 'OODA' is referenced without explanation and no concrete hypothesis example beyond the template.

4 / 5

Workflow Clarity

Four sequential phases with 'Execute phases sequentially', explicit validation ('Verify: test passes, no regressions, issue resolved'), feedback loops ('If it fails, form a new hypothesis', 'If 3+ fixes have failed: stop'), and a validation_checklist match the clear-sequence-with-validation-and-feedback anchor.

5 / 5

Progressive Disclosure

Content is well-organized into clearly signaled sections (role, when_to_use, four phases, checklist, best_practices, pitfalls) with no nested references and no bulky inlined material that belongs elsewhere; not a 5 because the simple-skill 5 exception targets sub-50-line skills and this runs ~97 lines as a single monolithic file.

4 / 5

Total

17

/

20

Passed

Description

61%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 gives a clear purpose and natural trigger terms but omits an explicit 'Use when...' clause, capping completeness. It is concise and reasonably distinct, with good but not comprehensive keyword coverage.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when encountering errors, test failures, or unexpected behavior that needs root-cause analysis.'

Broaden trigger terms with common synonyms such as 'bugs', 'crashes', 'stack traces', or 'exceptions'.

List one or two more concrete actions (e.g. 'reproduce, isolate, and fix') to lift specificity above the domain-only level.

DimensionReasoningScore

Specificity

Quotes 'investigate errors, test failures, and unexpected behavior — root cause before fix' name the domain plus one concrete action framing (investigate/root cause), matching the 'names domain and 1-2 concrete actions' anchor; not a 4 because no list of multiple specific actions.

3 / 5

Completeness

The description clearly states what ('investigate errors... root cause before fix') but has no explicit 'Use when...' trigger clause, so per the missing-trigger cap completeness cannot exceed 3; not a 4 because 'when' is absent rather than weakly explicit.

3 / 5

Trigger Term Quality

Phrases 'errors', 'test failures', 'unexpected behavior' are natural terms users say, giving good coverage; not a 5 because synonyms like 'bugs', 'crashes', 'stack trace', or 'exceptions' are missing.

4 / 5

Distinctiveness Conflict Risk

'debugging' with 'root cause before fix' carves a mostly distinct niche with only minor overlap against general coding skills; not a 5 because 'errors, test failures, unexpected behavior' is still broad enough to graze related engineering skills.

4 / 5

Total

14

/

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
griddynamics/rosetta
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.