posthog

Analyze product data and manage product tooling in PostHog. Use when the user wants product analytics or insights, HogQL/SQL queries, feature flags, experiments and A/B tests, error tracking, session replay, surveys, LLM analytics, dashboards, data warehouse, or PostHog documentation.

Quality

85%

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

70%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, well-structured instruction skill with a clear ordered workflow, explicit destructive-change checkpoint, and useful PostHog-specific gotchas. The main gap is actionability: the HogQL/querying section gives tips but no executable example query or tool-call pattern to anchor the guidance.

Suggestions

Add one or two concrete example HogQL queries (e.g., a minimal 'count events by day' query) in the HogQL & Querying Tips section to make the guidance copy-paste ready.

Show an example tool-call shape or natural-language ask pattern so the runtime-discovered tools have a concrete reference point.

Tighten the Overview's general sentences ("PostHog is an all-in-one product platform") toward routing-relevant detail only.

Dimension	Reasoning	Score
Conciseness	The body is lean and section-organized with tables and bullets; it never explains concepts Claude already knows (no "what is a feature flag") and each section earns its place. It is not a 2 because there is no padded tutorial prose or redundant explanation.	3 / 3
Actionability	Guidance is concrete in workflow terms ("Read first — list/get/query... Write next — create or update flags...") and includes specific PostHog gotchas (person-on-events ingestion-time values, timezone bucketing), but there are no executable examples such as a sample HogQL query or a tool-call shape. It is not a 3 because nothing is copy-paste ready, and not a 1 because the routing and tips are specific rather than abstract.	2 / 3
Workflow Clarity	Steps 0–4 are explicitly ordered ("Follow these steps in order. Do not skip steps."), with a confirm-before-applying checkpoint for destructive changes and a Troubleshooting section for error recovery. It is not a 2 because validation checkpoints and recovery guidance are explicit, not implicit.	3 / 3
Progressive Disclosure	It is a single well-organized SKILL.md with clearly labeled sections (Overview, Prerequisites, Required Workflow, Capability Map, HogQL Tips, Productivity Tips, Troubleshooting) and no nested references; the connected app advertises its own deeper skills/docs at runtime. It is not a 2 because organization is clean and there is no monolithic wall or multi-level indirection.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, third-person description that pairs a concrete capability statement with an explicit, broad "Use when" trigger list scoped tightly to PostHog. It hits all four anchors at the top level with no over-claiming or fluff.

Dimension	Reasoning	Score
Specificity	"Analyze product data and manage product tooling in PostHog" names the domain and the body lists many concrete capabilities (feature flags, experiments and A/B tests, error tracking, session replay, surveys, LLM analytics, dashboards, data warehouse). It is not a 2 because it goes well beyond naming a domain into multiple specific actions.	3 / 3
Completeness	It explicitly answers both what ("Analyze product data and manage product tooling in PostHog") and when ("Use when the user wants...") with an explicit trigger clause, matching the anchor for a 3.	3 / 3
Trigger Term Quality	The "Use when" clause enumerates natural phrasings a user would actually say — "product analytics or insights", "HogQL/SQL queries", "feature flags", "experiments and A/B tests", "error tracking", "session replay", "surveys", "dashboards" — giving broad coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Every trigger is PostHog-specific (HogQL, PostHog feature flags/experiments, PostHog documentation), carving a clear niche unlikely to fire for other skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/posthog/skills/posthog/SKILL.md
Commit: 11c74d6

Reviewed: 17 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.