Name: creating-an-endpoint
Rating: 70.39999999999999 (1 reviews)
Author: PostHog

creating-an-endpoint

Create a PostHog endpoint with the right shape on the first try — covers query kind choice, name conventions, what to expose as variables (HogQL code_name vs insight breakdown), data_freshness_seconds, and whether to materialise on day one. Use when the user says "create an endpoint", "expose this query as an API", "turn this insight into an endpoint", or asks for help structuring a new endpoint. Steers away from common mistakes: materialising a query with cohort breakdowns or compare mode, inline-only variables on a materialised endpoint, unbounded date ranges, ambiguous names.

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

78%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.

A well-structured, domain-specific skill body with concrete field values and tool names, a clear sequenced workflow with verification, and clean progressive disclosure via one reference file. Main weakness is mild verbosity in the example-interaction and notes sections.

Suggestions

Tighten the example interaction block — the multi-line transcript padding can be compressed without losing the decision-negotiation signal.

Add one complete, copy-paste-ready endpoint-create payload example (with query, variables, and data_freshness_seconds filled in) to push actionability from mostly-executable to fully-executable.

Add an explicit validate→fix→retry loop for the eligibility check (e.g., 'if endpoints-materialization-preview rejects, adjust the query and re-run preview') to strengthen the workflow's feedback structure.

Dimension	Reasoning	Score
Conciseness	Dense with PostHog-specific knowledge and largely free of generic filler, though the example interaction and the important-notes section run long and could be trimmed. Not a 5 due to these padded passages; not a 3 because there is no basic-concept over-explanation.	4 / 5
Actionability	Provides concrete, executable specifics — exact data_freshness_seconds enum values, the run URL pattern, the variable payload shape, and named tools (endpoint-create, endpoint-run, endpoints-materialization-preview). Not a 5 because the endpoint-create payload is illustrative rather than a complete copy-paste example.	4 / 5
Workflow Clarity	Offers an ordered 6-decision section plus a 9-step Workflow with an explicit verification checkpoint (step 8 sample-payload run) and an eligibility pre-check via endpoints-materialization-preview. Not a 5 because the error-recovery feedback loop is lighter than a validate→fix→retry cycle.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview that splits materialisation detail into a single, well-signaled one-level-deep reference (references/materializing.md), cited in two places; the referenced file exists and is well-organized, giving easy navigation.	5 / 5
	Total	17 / 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, specific description that names the domain and concrete creation decisions while providing explicit, natural-language trigger phrases. It also usefully steers away from common mistakes, sharpening the when-to-use signal.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete creation-time decisions — 'query kind choice', 'name conventions', 'what to expose as variables', 'data_freshness_seconds', 'whether to materialise' — giving comprehensive coverage of the endpoint-creation decision space.	5 / 5
Completeness	Explicitly answers both what ('Create a PostHog endpoint with the right shape... covers [decisions]') and when ('Use when the user says...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Quotes natural user phrases ('create an endpoint', 'expose this query as an API', 'turn this insight into an endpoint') but a few common phrasings are absent, falling just short of comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (PostHog endpoint creation) with triggers specific to that action, presenting minimal overlap risk with adjacent insight or diagnostic skills.	5 / 5
	Total	19 / 20 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: PostHog/posthog
Path: products/endpoints/skills/creating-an-endpoint/SKILL.md
Commit: 6fca5f8

Reviewed: 3 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.