CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

observability-rca

Use this skill when performing root cause analysis on incidents detected by Elastic Observability. Activate when the user reports a production issue, outage, degraded performance, or asks to investigate alerts.

67

Quality

84%

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

90%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.

Lean and highly actionable: the body delivers executable ES|QL commands for each investigation phase with no wasted tokens. The gaps are modest — no explicit validation/decision checkpoints between steps, and no reference files for extended query patterns.

DimensionReasoningScore

Conciseness

The body contains only one-line purpose statements and executable ES|QL commands with zero concept explanations or padding — e.g. 'Start with high-level health checks:' followed directly by commands — so every token earns its place.

5 / 5

Actionability

Copy-paste-ready `elastic es query` commands cover the common RCA cases (scope check via cluster health/SLOs, error-rate by service, timeline bucketing, deploy/restart/config changes, cross-service dependency stats, CPU and network metrics), with a symptom-to-cause table for interpretation.

5 / 5

Workflow Clarity

The five steps (assess scope, timeline reconstruction, correlation analysis, common root causes, resolution documentation) are clearly sequenced and the symptom table acts as a decision aid, but there are no explicit decision checkpoints linking each step's output to the next action or feedback loops on unexpected results. Read-only investigation means the destructive-operation validation cap does not apply.

4 / 5

Progressive Disclosure

A single well-organized file with clean sections and nothing inlined that clearly belongs in a separate bundle, but at ~70 lines it exceeds the under-50-line simple-skill exception and offers no one-level-deep references (e.g. an ES|QL query cookbook) for deeper material.

4 / 5

Total

18

/

20

Passed

Description

70%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 solid description with an explicit and natural trigger clause and a clearly staked-out Elastic Observability niche. Its main weakness is that the 'what' stays at the level of a single activity ('root cause analysis') without enumerating the concrete capabilities the skill provides.

Suggestions

Enumerate 2-3 concrete capabilities after the domain, e.g. 'query logs, traces, and metrics, reconstruct incident timelines, and correlate cross-service failures' to lift specificity and completeness.

Add common trigger synonyms such as 'incident', 'downtime', or 'error spike' alongside 'outage' and 'degraded performance' to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

The description names the domain ('root cause analysis on incidents detected by Elastic Observability') and one concrete action, but does not list several specific actions like querying logs, correlating traces, or checking metrics, so it matches the 1-2 concrete actions anchor rather than the several-actions anchor.

3 / 5

Completeness

Both a 'what' ('performing root cause analysis on incidents detected by Elastic Observability') and an explicit 'when' ('Activate when the user reports a production issue, outage, degraded performance, or asks to investigate alerts') are present; the 'what' is somewhat high-level rather than enumerating concrete capabilities, placing it between the 4 and 5 anchors.

4 / 5

Trigger Term Quality

Natural user phrases such as 'production issue, outage, degraded performance, or asks to investigate alerts' give good keyword coverage, though common synonyms like 'incident', 'downtime', or 'error spike' are missing, keeping it below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

'Elastic Observability' pins a clear niche with distinct triggers, but generic root-cause/troubleshooting phrasing creates minor overlap risk with general debugging skills.

4 / 5

Total

15

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

elastic/elastic-ramen

Path

packages/opencode/src/elastic/skills/observability-rca/SKILL.md

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.