CtrlK
BlogDocsLog inGet started
Tessl Logo

diagnosing-endpoint-performance

Diagnose why a PostHog endpoint is slow or expensive and propose a concrete fix — bump the cache TTL, enable materialisation, restructure variables, or rewrite the query. Use when the user says "this endpoint is slow", "my endpoint times out", "we're hitting the cost cap on this one", or asks "should I materialise this?". Focuses on a single named endpoint, not a project-wide audit.

72

Quality

87%

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

75%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, actionable diagnostic skill that loads Claude with genuine PostHog-specific knowledge (materialisation eligibility, the JOIN+variable trap, TTL enum) and provides a clear sequenced workflow with validation. Slight gains available from trimming the example interaction and splitting the detailed rewrite bullets into a reference file.

Suggestions

Trim the "Example interaction" block or move it to a reference file — its reasoning largely restates the decision tree above it, which would lift conciseness toward the score-5 anchor.

Split the Step 3 rewrite bullets (cohort breakdown, JOIN+variables, missing variables, HogQL `*`) into a dedicated reference file linked from the body, improving progressive_disclosure for this ~200-line skill.

Intersperse validation checkpoints through the numbered Workflow (e.g. after steps 2–4) rather than only at the final "confirm before applying" step, which would move workflow_clarity to the score-5 anchor.

DimensionReasoningScore

Conciseness

The body is dense with product-specific knowledge (materialisation semantics, the JOIN+variable trap, the TTL enum) that Claude would not already know, so most tokens earn their place; minor restating in "Important notes" and a somewhat long example interaction keep it just below the lean score-5 anchor.

4 / 5

Actionability

Names specific tools, gives exact TTL enum values, and provides a copy-paste SQL query against `query_log`; the rewrite guidance is necessarily prose rather than code, leaving minor gaps versus the fully-executable score-5 anchor.

4 / 5

Workflow Clarity

A numbered 6-step workflow plus a sequenced Step 1–4 decision tree, with explicit validation ("confirm before applying", "get sign-off") and a validate→compare→apply→confirm feedback loop for the AI rewrite; the destructive-operation cap does not bind because validation is present, but per-step checkpoints are concentrated at the end of the numbered workflow rather than interspersed.

4 / 5

Progressive Disclosure

Self-contained with clear section headers (When to use, Available tools, Decision tree, Workflow, Example, Important notes) and no bundle files; at ~200 lines some detail such as the Step 3 rewrite bullets could be split into a reference file, keeping it just below the score-5 anchor.

4 / 5

Total

16

/

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.

An exemplary description: concrete named fixes, verbatim user trigger phrases, and explicit what/when coverage, all scoped to a single named endpoint to avoid overlap with the project-wide audit skill. No improvements needed.

DimensionReasoningScore

Specificity

"propose a concrete fix — bump the cache TTL, enable materialisation, restructure variables, or rewrite the query" lists four concrete named actions with comprehensive coverage of the diagnostic domain, matching the score-5 anchor rather than the minor-gaps score-4 anchor.

5 / 5

Completeness

Explicitly answers both what ("Diagnose why a PostHog endpoint is slow or expensive and propose a concrete fix") and when ("Use when the user says...") with concrete trigger phrases, matching the score-5 anchor.

5 / 5

Trigger Term Quality

Quotes natural verbatim user phrases ("this endpoint is slow", "my endpoint times out", "we're hitting the cost cap on this one", "should I materialise this?") — comprehensive coverage of the terms a user would actually say.

5 / 5

Distinctiveness Conflict Risk

"Focuses on a single named endpoint, not a project-wide audit" carves a clear niche and explicitly distinguishes it from `auditing-endpoints`, giving 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.