CtrlK
BlogDocsLog inGet started
Tessl Logo

auditing-endpoints

Audit every endpoint in a PostHog project for staleness, failed materialisations, and unused materialised versions. Use when the user asks "what endpoints can I clean up?", "are any of my endpoints broken?", "which materialised versions are still being called?", or wants a one-shot cleanup pass over the Endpoints product. Produces a prioritised report grouped by issue type, with recommended actions but does not modify anything without explicit confirmation.

77

Quality

96%

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

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.

The body is highly actionable and well-structured with a sequenced workflow that bakes in the required confirmation checkpoints for destructive endpoint changes. Its only weakness is mild repetition of the API-key-scope caveat and the worked example restating the audit format.

Suggestions

Consolidate the 'API-key-only scope' caveat into a single Important Notes entry instead of repeating it in 'What counts as an issue', step 3, the example, and Important notes.

Trim the 'Example interaction' so it demonstrates the report once rather than re-explaining the audit structure already covered in step 4.

Consider moving the full report template and example into a reference file if the skill grows, to keep the overview lean.

DimensionReasoningScore

Conciseness

Largely efficient with concrete SQL, tables, and examples, but the API-key-only-usage caveat is repeated across several sections and the worked example restates the audit's structure, so it could be trimmed slightly. Not 5 because of this repetition; not 3 because nothing is padded with concepts Claude already knows.

4 / 5

Actionability

Provides fully executable guidance — exact HogQL queries against system.data_modeling_endpoints and query_log, named tools with their precise purpose, a copy-paste-ready report template, and specific next-step phrasings — covering the common audit cases.

5 / 5

Workflow Clarity

A clearly sequenced five-step workflow with explicit validation/confirmation checkpoints for a destructive/batch operation ('No rows → say so and stop. Don't invent issues', 'confirm with the user before unmaterialising', 'Never act from the audit alone'), satisfying the feedback-loop requirement rather than being capped at 3.

5 / 5

Progressive Disclosure

A single self-contained SKILL.md with well-organized sections (When to use, Available tools, What counts as an issue, Workflow, Example, Important notes) and no nested or buried references; under the simple-skill guidance this clear structure earns the top anchor.

5 / 5

Total

19

/

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.

The description is specific, comprehensive, and trigger-rich, cleanly answering both what the skill does and when to invoke it in third-person voice. It sits at the top anchor on every dimension with no over-claims or fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete, specific actions — auditing endpoints 'for staleness, failed materialisations, and unused materialised versions' and 'Produces a prioritised report grouped by issue type, with recommended actions' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (audits endpoints and produces a prioritised report) and 'when' (an explicit 'Use when the user asks...' clause with concrete trigger phrases), satisfying the top anchor.

5 / 5

Trigger Term Quality

Includes natural user phrasings quoted directly — 'what endpoints can I clean up?', 'are any of my endpoints broken?', 'which materialised versions are still being called?' — covering the ways a user would actually request this.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (PostHog Endpoints cleanup audit) with distinct triggers and a named handoff boundary to 'diagnosing-endpoint-performance', minimizing overlap with other skills; voice is third-person with no first/second-person penalty.

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.