CtrlK
BlogDocsLog inGet started
Tessl Logo

error-diagnostics-smart-debug

Use when working with error diagnostics smart debug

44

Quality

46%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/error-diagnostics-smart-debug/SKILL.md
SKILL.md
Quality
Evals
Security

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 content lays out a well-sequenced debugging workflow with a validation checkpoint, but leans on mock/pseudocode examples and restates widely-known tooling and bug categories. Structure is sound though everything is inline with no progressive disclosure to deeper materials.

Suggestions

Replace mock functions in the example with real, executable calls or clearly label the example as illustrative pseudocode with justification.

Trim the tool-name catalogs and common-bug-category lists to the few that matter, trusting Claude's existing knowledge of observability tools.

Add an explicit error-recovery feedback loop in the validation step (e.g. 'if canary error rate rises, revert and return to hypothesis generation').

DimensionReasoningScore

Conciseness

The body is mostly efficient structured workflow guidance, but lists of tool names (Sentry/Rollbar/Bugsnag, DataDog/New Relic) and common bug categories (race conditions, stale cache) restate knowledge Claude already has and could be tightened.

3 / 5

Actionability

There is some concrete guidance such as 'Use Task tool (subagent_type="debugger")' and OpenTelemetry span.setAttribute calls, but the example relies on non-executable mock APIs (aiAnalyze, getSentryIssue) and many steps are high-level directions rather than runnable commands.

3 / 5

Workflow Clarity

The ten numbered steps are clearly sequenced from triage through prevention and step 9 includes explicit validation with a success-criteria checklist, though error-recovery feedback loops back to earlier steps are only implicit.

4 / 5

Progressive Disclosure

The skill is a single inline file with clear section headers and no external references, which is acceptable, but at ~190 lines some material (tool catalogs, strategy detail) could be split into reference files for better discovery.

3 / 5

Total

13

/

20

Passed

Description

36%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 is a bare trigger clause that names a domain but fails to state what the skill actually does, leaving Claude without capability information. Trigger terms are reasonable but thin and lack synonyms.

Suggestions

Add a 'what' clause listing concrete actions, e.g. 'Analyzes error diagnostics, triages stack traces, and ranks root-cause hypotheses for debugging tasks.'

Expand trigger terms with natural synonyms users say, such as 'troubleshoot', 'stack trace', 'root cause analysis', or 'fix a bug'.

Replace the awkward 'smart debug' phrasing with standard terminology to improve naturalness and distinctiveness.

DimensionReasoningScore

Specificity

The phrase 'Use when working with error diagnostics smart debug' names the domain but provides no concrete action verbs describing what the skill does, sitting just above the entirely-vague anchor.

2 / 5

Completeness

Only a 'when' clause ('Use when working with error diagnostics smart debug') is present with no 'what' describing capabilities, matching the 'only when present without what' anchor.

2 / 5

Trigger Term Quality

'error diagnostics' and 'debug' are natural terms a user might say, but common synonyms like 'troubleshoot', 'stack trace', or 'root cause' are missing and 'smart debug' is awkward phrasing.

3 / 5

Distinctiveness Conflict Risk

The debugging/error-diagnostics domain is somewhat specific but broad enough to overlap with general coding or troubleshooting skills, so conflict risk remains moderate.

3 / 5

Total

10

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rmyndharis/antigravity-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.