CtrlK
BlogDocsLog inGet started
Tessl Logo

consuming-endpoints-from-client-code

Wire a PostHog endpoint into a client app or SDK. Covers fetching the OpenAPI spec, generating a typed client with openapi-generator or @hey-api/openapi-ts, sending the right auth header, shaping the variables payload (HogQL code_name vs insight breakdown property), handling rate-limit and materialised-endpoint error responses. Use when the user says "how do I call my endpoint", "generate a client for this", or "what auth header do I use".

72

Quality

88%

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

77%

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

Highly actionable content with a clear validated workflow and concrete examples, but it is a monolithic file that could offload detail to bundle references, and some material is repeated or slightly over-explained. The time-sensitive pricing caveat is appropriately flagged as future.

Suggestions

Move the detailed rate-limit numbers and the full error-handling matrix into a references/ file (e.g. ERROR-REFERENCE.md) and keep SKILL.md to a concise pointer, reducing repetition between the error table and Important notes.

Tighten conciseness by removing duplicated explanations (e.g. the /run trailing-slash and rate-limit paragraphs each appear twice) so each fact is stated once.

Optionally extract the language-specific client-generation command table into a references/CLIENT-GENERATION.md, leaving a one-line pointer, to improve progressive disclosure for a file this long.

DimensionReasoningScore

Conciseness

Content is mostly efficient and accurate, but several passages restate or expand on points Claude already knows — e.g. 'the trailing /run is required' then re-explained, the rate-limit note (~240/min burst, ~2400/hour) repeated across the error table and the Important notes section — so it is not maximally lean.

2 / 3

Actionability

Concrete, executable guidance throughout: a literal endpoint URL, an Authorization header, a JSON payload shape, a four-row client-generator command table with exact commands, and a fully worked example interaction with a real curl-equivalent request.

3 / 3

Workflow Clarity

The numbered Workflow section gives an explicit 7-step sequence with validation built in (confirm name via endpoint-get, check materialisation status, optionally endpoint-run to confirm the payload works), and the example interaction reinforces the feedback loop.

3 / 3

Progressive Disclosure

The body is well-sectioned but is a single ~230-line monolith with no references, scripts, or assets split out; referenceable material (the rate-limit specifics, the full error-handling matrix, the client-generation table) sits inline rather than being offloaded one level deep.

2 / 3

Total

10

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concrete, trigger-rich, and complete, explicitly answering both what the skill does and when to use it with direct user-quote triggers. It is clearly distinct from the endpoint-creation counterpart.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'fetching the OpenAPI spec, generating a typed client with openapi-generator or @hey-api/openapi-ts, sending the right auth header, shaping the variables payload ... handling rate-limit and materialised-endpoint error responses' — matching the highest anchor.

3 / 3

Completeness

Both what (wire a PostHog endpoint into a client app/SDK, with enumerated capabilities) and when ('Use when the user says ...') are explicitly present, satisfying the top anchor.

3 / 3

Trigger Term Quality

Direct quotes of natural phrasings a user would say are given explicitly: "how do I call my endpoint", "generate a client for this", "what auth header do I use" — strong coverage of real trigger language.

3 / 3

Distinctiveness Conflict Risk

The caller-side niche and explicit 'No PostHog code is modified here' framing, plus distinctive triggers tied to client generation and auth headers, make it unlikely to fire for the sibling creating-an-endpoint skill.

3 / 3

Total

12

/

12

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.