dt-obs-frontends
Real User Monitoring (RUM), Web Vitals, user sessions, mobile crashes, page performance, user interactions, and frontend errors. Query web and mobile frontend telemetry.
60
70%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/dt-obs-frontends/SKILL.mdQuality
Discovery
54%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 has strong trigger terms and a distinctive niche in frontend observability/RUM, making it easy to distinguish from other skills. However, it lacks an explicit 'Use when...' clause and could be more specific about the concrete actions it performs beyond just 'Query'. Adding explicit trigger guidance and more action verbs would significantly improve it.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Real User Monitoring, Web Vitals scores, frontend performance issues, mobile app crashes, or user session analysis.'
List more specific concrete actions beyond 'Query', e.g., 'Analyze Core Web Vitals (LCP, FID, CLS), investigate user session replays, diagnose mobile crash reports, track page load performance, and query frontend error logs.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (RUM, Web Vitals, frontend telemetry) and lists several relevant concepts (user sessions, mobile crashes, page performance, user interactions, frontend errors), but the only concrete action stated is 'Query' — it doesn't list multiple specific actions like 'analyze crash reports, track Core Web Vitals metrics, diagnose slow page loads.' | 2 / 3 |
Completeness | The description answers 'what' (query frontend telemetry) but has no explicit 'Use when...' clause or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' itself is also somewhat thin (just 'Query'), so this falls to 1. | 1 / 3 |
Trigger Term Quality | Includes strong natural keywords users would actually say: 'Real User Monitoring', 'RUM', 'Web Vitals', 'user sessions', 'mobile crashes', 'page performance', 'frontend errors', 'user interactions'. These cover a good range of terms a user would naturally use when asking about frontend observability. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche around frontend/RUM telemetry with specific terms like 'Real User Monitoring', 'Web Vitals', 'mobile crashes', and 'frontend errors' that are unlikely to conflict with backend monitoring, APM, or general analytics skills. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, comprehensive frontend observability skill with excellent actionability through numerous executable DQL queries and clear workflow guidance. Its main weakness is verbosity — the troubleshooting section, 'When to Use This Skill' list, and some explanatory passages could be significantly trimmed without losing value. The progressive disclosure structure is well-designed with clear references to supporting files.
Suggestions
Trim the Troubleshooting section significantly — the decision tree, 'Red Flags', and 'Common Investigation Steps' largely describe general diagnostic reasoning Claude already knows. Keep only domain-specific gotchas (zombie sessions, session creation delay, time window behavior).
Remove or drastically shorten the 'When to Use This Skill' section — the skill description and overview already make the scope clear, and listing what NOT to use it for is unnecessary padding.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~400+ lines) with significant verbosity in sections like Troubleshooting (decision trees, red flags, common investigation steps) and the detailed session data documentation. While much content is genuinely useful reference material (field names, naming conventions, gotchas), the troubleshooting section over-explains diagnostic reasoning that Claude already knows, and the 'When to Use This Skill' section restates what's obvious from context. The zombie sessions and session creation delay explanations are valuable domain knowledge but could be more concise. | 2 / 3 |
Actionability | The skill excels at actionability with numerous executable DQL queries covering web vitals, long tasks, cache effectiveness, compression waste, DNS analysis, and more. The Slow Page Load Playbook provides concrete, copy-paste-ready queries with clear heuristics for interpretation. Field names, metric names, and filter values are all specific and directly usable. | 3 / 3 |
Workflow Clarity | The Slow Page Load Playbook provides a clear diagnostic workflow with heuristics (high TTFB → slow backend, high LCP with normal TTFB → render bottleneck) followed by specific queries for each scenario. The troubleshooting section includes a well-structured decision tree for handling zero results and anomalous data. The session correlation workflow explicitly warns about time window gotchas and zombie sessions with validation queries. | 3 / 3 |
Progressive Disclosure | The skill clearly organizes content with a Quick Reference section for immediate use, Core Workflows pointing to specific reference files (WebVitals.md, user-sessions.md, error-tracking.md, mobile-monitoring.md, performance-analysis.md), and an explicit Progressive Disclosure section defining what's always available vs. loaded by workflow vs. on-demand. References are one level deep and well-signaled. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (610 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- Dynatrace/dynatrace-for-ai
- Commit
4991356
- 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.