Name: exploring-autocapture-events
Rating: 74.4 (1 reviews)
Author: PostHog

exploring-autocapture-events

Guides exploration of $autocapture events captured by posthog-js to understand user interactions, find CSS selectors (especially data-attr attributes), evaluate selector uniqueness, query matching clicks ad-hoc, and create actions. Use when the user asks about autocapture data, wants to find what users are clicking, needs to build actions from click events, asks about elements_chain, wants to build a trend or funnel filtered by clicks or other autocapture interactions, asks which properties autocapture sends, or asks how to filter $autocapture events. Only applies to projects using posthog-js autocapture.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

85%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-sequenced with strong validation feedback loops, and it is mostly token-efficient. The main weakness is progressive disclosure: two referenced files are missing from the bundle, leaving dead links where detailed material was meant to live.

Suggestions

Create the referenced bundle files (./references/elements-chain-format.md and ./references/example-queries.md) so the inline links resolve, or inline the small amount of content they would hold and remove the links.

Tighten the workflow-step prose (e.g., the explanatory sentences in Steps 2, 3, and 6) to lift conciseness toward a 5.

Consider moving the full funnel-join SQL and the complete FunnelsQuery JSON into the example-queries reference to keep SKILL.md as a tighter overview.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes domain competence (materialized-column tables, direct SQL/JSON), but a few workflow paragraphs add explanatory prose that could be trimmed; this sits between the score-3 'mostly efficient' and score-5 'lean' anchors, closer to 4.	4 / 5
Actionability	Provides copy-paste-ready, executable HogQL (count, trends, funnel joins) and complete JSON for FunnelsQuery steps and action creation, covering the common cases, matching the score-5 anchor.	5 / 5
Workflow Clarity	An 8-step sequence with explicit validation checkpoints (count query in Step 1, uniqueness check in Step 4, re-run after refinement in Step 5, matchesAction verification in Step 8) and a feedback loop, matching the score-5 anchor; operations are read/create rather than destructive-batch so no cap applies.	5 / 5
Progressive Disclosure	Sections are well organized and references are signaled, but the two cited bundles (./references/elements-chain-format.md and ./references/example-queries.md) do not exist in the bundle, so navigation dead-ends; with broken references and a fair amount of inline example content, this falls to the score-3 anchor.	3 / 5
	Total	17 / 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 a strong, third-person statement that concretely enumerates capabilities, supplies a rich set of natural trigger phrases, and explicitly bounds scope to posthog-js autocapture. It clearly answers both what the skill does and when to use it. The only minor weakness is verbosity, but the description rubric does not penalize length and every clause earns its place.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'understand user interactions, find CSS selectors (especially data-attr attributes), evaluate selector uniqueness, query matching clicks ad-hoc, and create actions' — giving comprehensive coverage, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both what ('Guides exploration of $autocapture events...') and when ('Use when the user asks about autocapture data, wants to find what users are clicking...') with concrete trigger phrases, exactly matching the score-5 anchor.	5 / 5
Trigger Term Quality	Covers natural phrasings a user would actually say — 'autocapture data', 'what users are clicking', 'build actions from click events', 'trend or funnel filtered by clicks', 'properties autocapture sends' — including synonyms, matching the comprehensive score-5 anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche scoped to 'posthog-js autocapture' with an explicit boundary ('Only applies to projects using posthog-js autocapture'), minimizing conflict with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: PostHog/posthog
Path: products/product_analytics/skills/exploring-autocapture-events/SKILL.md
Commit: 130f3a1

Reviewed: 9 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.