CtrlK
BlogDocsLog inGet started
Tessl Logo

sentry-javascript-bugs

Review Sentry React and TypeScript changes for bug patterns drawn from real production issues. Use when reviewing a frontend diff or PR, checking Warden findings, auditing the current branch, reviewing production-error patterns, or looking for common regressions in `static/`.

71

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

Well-structured, actionable review skill with clean progressive disclosure and a clear gated workflow. The main improvement is tightening the opening statistics framing and adding a couple more executable examples where red flags are currently descriptive.

Suggestions

Trim or relocate the '428 real production issues (201 resolved, 130 ignored, 97 unresolved)...' statistics sentence; the exact counts are contextual padding that does not change how Claude runs a check.

For checks where red flags are currently prose (e.g. Check 4, Check 6), add one short executable safe-pattern snippet so every check has copy-paste-ready guidance.

Make the per-finding validation loop explicit in Step 3 (e.g. 're-trace the triggering input before promoting MEDIUM to HIGH') to mirror the confidence table as a true checkpoint.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, avoiding basic-concept explanations; the opening statistics sentence ('428 real production issues... 524,000 error events across 93,000+ users') is minor trimmable context that slightly pads the overview.

4 / 5

Actionability

Each check pairs concrete red flags with executable safe-pattern snippets (e.g. `obj?.property?.nested`, `if (!hasPlottableValues(data)) return <EmptyState />`), giving mostly copy-paste-ready guidance with minor gaps where red flags are descriptive rather than code-backed.

4 / 5

Workflow Clarity

A clear Step 1 -> Step 2 -> Step 3 sequence is present with a confidence-gating checklist (HIGH/MEDIUM/LOW) and an explicit 'do not invent issues / report zero findings' feedback rule, but there is no true validate-fix-retry loop as the process is review-only rather than destructive.

4 / 5

Progressive Disclosure

A well-signaled reference table maps each code category to a real one-level-deep file in references/ (all 7 files verified to exist), keeping the overview concise while routing detail to split files with easy navigation.

5 / 5

Total

17

/

20

Passed

Description

95%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.

A strong, specific description that clearly answers what the skill does and when to use it, with rich natural trigger terms and minimal conflict risk. Minor room to sharpen the enumerated actions beyond the review contexts.

DimensionReasoningScore

Specificity

Names the domain (Sentry React/TypeScript frontend) and lists several concrete review actions ('reviewing a frontend diff or PR, checking Warden findings, auditing the current branch'), with only minor gaps in enumerating the underlying bug-checking actions.

4 / 5

Completeness

Clearly states the 'what' ('Review Sentry React and TypeScript changes for bug patterns') and an explicit 'Use when...' clause enumerating concrete trigger scenarios, satisfying both requirements.

5 / 5

Trigger Term Quality

Comprehensive natural terms users would actually say -- 'frontend diff', 'PR', 'Warden findings', 'auditing the current branch', 'production-error patterns', 'regressions', plus the `static/` path -- covering synonyms and concrete triggers.

5 / 5

Distinctiveness Conflict Risk

Targets a clear Sentry-specific niche with distinct triggers (Warden findings, `static/`, production-error patterns), minimizing overlap with generic code-review skills.

5 / 5

Total

19

/

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
getsentry/sentry
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.