CtrlK
BlogDocsLog inGet started
Tessl Logo

investigating-metric-anomalies

Investigates server/infrastructure metric anomalies in PostHog Metrics — from "this metric is rising/dropping/spiking" or a fired alert to a probable cause with evidence. Use when asked why a metric looks wrong (ingestion lag rising, error rate spiking, latency degrading, queue depth growing, throughput dropping), when an alert fires on an OTel/Prometheus metric, or for any incident triage that starts from a metric symptom. Composes characterize-metric-anomaly, query-metrics, and metric-names-list with logs (query-logs) and traces (APM span tools) for cross-signal root-cause correlation.

80

Quality

100%

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

100%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.

Excellent content: a tight, well-structured investigative loop with concrete tool calls, validation checkpoints, a worked example, and pitfall guidance — all token-efficient and free of over-explanation. The only minor risk is that all four dimensions sit at the top anchor, leaving little headroom to distinguish truly exceptional content.

DimensionReasoningScore

Conciseness

Lean and efficient: assumes Claude's competence (never explains what a metric, log, or trace is) and every line adds non-obvious domain knowledge (counter resets, scrape lag, gaps vs zero). No padding.

5 / 5

Actionability

Concrete, executable orchestration guidance with specific tool names and parameters (anomalyFrom, filters, clauses+formula) plus a fully worked example walking real steps — actionable without being code.

5 / 5

Workflow Clarity

A clearly sequenced 5-step loop with explicit validation/decision checkpoints (flat direction → widen window; clean logs → widen to neighbors; vanished label → pivot to logs) and feedback loops for error recovery.

5 / 5

Progressive Disclosure

No bundle files exist; the under-50-line body is well-organized into clear sections (loop, worked example, pitfalls), satisfying the simple-skill exception for progressive disclosure.

5 / 5

Total

20

/

20

Passed

Description

100%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 description: specific, trigger-rich, complete, and clearly niched. It names the concrete tools it composes, gives natural symptom phrasing users would say, and explicitly states when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and named tools (characterize-metric-anomaly, query-metrics, metric-names-list, query-logs, APM span tools) composed for cross-signal correlation, giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both what (go from a metric symptom to a probable cause with evidence) and when ('Use when asked why a metric looks wrong... when an alert fires... or for any incident triage that starts from a metric symptom') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Rich natural trigger phrasing users would actually say — 'metric is rising/dropping/spiking', 'ingestion lag rising, error rate spiking, latency degrading, queue depth growing, throughput dropping', 'alert fires on an OTel/Prometheus metric' — with synonyms and concrete symptom variants.

5 / 5

Distinctiveness Conflict Risk

Clear niche (PostHog Metrics anomaly triage) with specific tool composition and metric-symptom triggers, making it distinct from adjacent log or trace skills with minimal conflict risk.

5 / 5

Total

20

/

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
PostHog/posthog
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.