investigate-metric

Diagnose why a product metric changed (dropped, spiked, or plateaued) by orchestrating breakdowns, actors, paths, lifecycle, retention, and annotations queries. Use when the user reports an anomaly, asks "why did X change?", or needs root-cause analysis for a trend, funnel, retention, stickiness, or lifecycle metric.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%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.

An exemplary content body: actionable, well-sequenced with validation checkpoints, and cleanly split across verified one-level-deep references. Only minor token-trimming opportunities in the tool listing keep conciseness at 4.

Dimension	Reasoning	Score
Conciseness	Lean and largely free of padding; it assumes Claude knows the domain and skips explaining concepts like funnels or box plots. The enumerated standard-tool list is useful but slightly verbose, keeping it just below the leanest anchor-5 example.	4 / 5
Actionability	Provides copy-paste-ready bash invocations, exact field names (e.g. trendsFilter.display, compareFilter), a complete findings template, and concrete tool routing; fully executable guidance covering common cases.	5 / 5
Workflow Clarity	Clear five-step sequence with explicit validation checkpoints and feedback loops: a stop condition in 2.2 ('report that and stop'), a control-segment cross-check in Step 4 with expand/investigate branching, and skip-when guidance.	5 / 5
Progressive Disclosure	A clear overview that routes each query kind to one-level-deep playbook references via a table; all referenced files (7 playbooks, shared-patterns, common-causes, 2 scripts) exist and are well-signaled with link text and relative paths.	5 / 5
	Total	19 / 20 Passed

Description

92%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: third-person, concrete in its enumerated actions, and explicit about both capability and trigger conditions. The only minor gap is trigger-term exhaustiveness, keeping trigger quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions ('orchestrating breakdowns, actors, paths, lifecycle, retention, and annotations queries') and several metric types, giving comprehensive coverage matching the anchor-5 example.	5 / 5
Completeness	Explicitly answers both 'what' (diagnose a metric change via orchestrated queries) and 'when' ('Use when the user reports an anomaly, asks why did X change, or needs root-cause analysis...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes the highly natural question form 'why did X change?' plus 'anomaly' and 'root-cause analysis', with synonyms across metric types; good coverage though not exhaustive of every natural phrasing a user might say.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (PostHog metric-change diagnosis via specific query kinds) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: PostHog/posthog
Path: products/product_analytics/skills/investigate-metric/SKILL.md
Commit: 5b94e47

Reviewed: 2 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.