error-diagnostics-smart-debug

Use when working with error diagnostics smart debug

Quality

42%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

62%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a strong, well-sequenced debugging workflow with explicit validation checkpoints and a useful worked example. Its main weaknesses are generic boilerplate padding at the top and a pseudocode example that isn't executable, plus a monolithic single-file structure that underuses progressive disclosure.

Suggestions

Remove the generic "Use this skill when / Do not use use this skill when / Instructions" boilerplate lines that restate the obvious; keep only debugging-specific guidance.

Make the example executable or label it explicitly as illustrative pseudocode, and prefer real API calls (e.g. actual Sentry/Datadog SDK snippets) over invented functions like aiAnalyze().

Move the long tool catalogs (Step 2) and the worked example into a separate reference file (e.g. references/debug-example.md) to keep SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	The core workflow and example are reasonably tight, but the generic "Use this skill when / Do not use this skill when / Instructions" boilerplate (e.g. "Clarify goals, constraints, and required inputs", "Apply relevant best practices") is filler that adds nothing debugging-specific and could be trimmed.	2 / 3
Actionability	It gives concrete guidance (named tools like Sentry/DataDog/Jaeger, a structured hypothesis format with falsification criteria, and a worked example), but the example code calls non-existent functions (aiAnalyze, getSentryIssue, getDataDogTraces) that are illustrative pseudocode rather than executable, matching the score-2 pseudocode anchor.	2 / 3
Workflow Clarity	The 10-step workflow is clearly sequenced with explicit validation in Step 9 (run tests, performance baseline comparison, canary monitoring) plus success criteria and a rollback strategy, and the example shows a feedback loop of deploy-monitor-confirm-fix-validate.	3 / 3
Progressive Disclosure	The body is well-sectioned with headers but is a ~190-line monolithic file with no external references; for content this long, the detailed tool catalogs and worked example are inline material that could be split into separate reference files.	2 / 3
	Total	9 / 12 Passed

Description

22%Weight 40%Scale 1-3

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 trigger-only fragment: it tells Claude when to activate but not what the skill does or how, leaning on a buzzwordy domain label. It fails to answer the "what does this do" half of completeness and lists no concrete capabilities.

Suggestions

Add explicit capabilities, e.g. "Diagnoses errors, analyzes stack traces, generates ranked root-cause hypotheses, and suggests fixes using observability data."

Replace "smart debug" with natural trigger terms users actually say, such as "debug this error", "diagnose this bug", or "find the root cause of this failure".

Combine what and when into one clause: "Diagnoses production errors via observability data and trace analysis. Use when the user asks to debug, root-cause, or diagnose a failing service."

Dimension	Reasoning	Score
Specificity	The description only states a domain trigger ("Use when working with error diagnostics smart debug") with no concrete actions named, mirroring the vague "Helps with documents" anchor rather than the score-2 anchor that names actions like "Processes PDF files and extracts content".	1 / 3
Completeness	It supplies a "when" trigger ("Use when...") but completely lacks a "what" statement of capabilities; anchor 1 explicitly covers missing what OR when, and no actions are described.	1 / 3
Trigger Term Quality	It contains relevant keywords ("error", "diagnostics", "debug") a user might say, but the compound "error diagnostics smart debug" reads as a product/feature name with buzzwordy "smart debug" rather than natural phrasing, and it omits common variations like "figure out why this is failing" or "root cause this bug".	2 / 3
Distinctiveness Conflict Risk	The debugging/diagnostics niche is somewhat specific, but the generic phrasing could still overlap with general code-fixing or testing skills, fitting the score-2 "somewhat specific but could still overlap" anchor.	2 / 3
	Total	6 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rmyndharis/antigravity-skills
Path: skills/error-diagnostics-smart-debug/SKILL.md
Commit: e63f7dd

Reviewed: 13 days 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.