Name: signals-scout-customer-analytics
Rating: 64.8 (1 reviews)
Author: PostHog

signals-scout-customer-analytics

Signals scout for PostHog Customer analytics (Accounts). Watches per-account engagement for churn-risk shapes — engagement cliffs, dormancy, champion departure — and the expansion inverse, weighted by commercial ownership, and files each validated risk as a report in the inbox.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./products/signals/skills/signals-scout-customer-analytics/SKILL.md

Quality

Content

88%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 strong, highly actionable scout skill with a well-sequenced, validation-rich workflow; its only real weakness is moderate repetition of the core discriminator and a monolithic structure with no local reference split.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and full of non-obvious PostHog-specific knowledge Claude would not have, but the fleet-held-vs-account-sliding discriminator and sibling-territory boundaries are restated across several sections (intro, 'What you do NOT do', Decide, Disqualifiers) and could be tightened.	4 / 5
Actionability	Fully executable: real ClickHouse SQL queries with concrete thresholds (e.wk < e.prev * 0.5, baseline > 300), exact scratchpad key patterns, named tools with parameters, and specific decision rules cover the common per-account cases.	5 / 5
Workflow Clarity	Clear run sequence (Orient → Profile → Explore → Save memory → Decide → Close out) with explicit validation checkpoints — join-overlap check before trusting numbers, longer-baseline confirmation, fleet-held check, and inbox/dedupe/noise checks before authoring — plus edit-vs-author feedback loops.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and clearly signaled deferral to `authoring-scouts` → `references/report-contract.md` for generic mechanics, but no local reference files exist and the SQL query library and scratchpad taxonomy are inlined in one ~217-line file.	4 / 5
	Total	18 / 20 Passed

Description

70%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, domain-rich, and clearly distinguishable, but it omits an explicit 'when to use this' trigger clause, leaving completeness as the weakest dimension.

Suggestions

Add an explicit 'Use when ...' clause naming the triggering situations (e.g. renewal reviews, CSM/AE asking which accounts are disengaging, per-account churn-risk checks).

Include a couple of natural user-facing synonyms or phrasings a CSM/AE might actually say (e.g. 'account health', 'which of my accounts is slipping') to broaden trigger-term coverage.

Consider adding one more concrete action verb (e.g. 'surfaces', 're-scores') to push specificity from a clear action list toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions and shapes — 'Watches per-account engagement for churn-risk shapes — engagement cliffs, dormancy, champion departure — and the expansion inverse' and 'files each validated risk as a report in the inbox' — but rests on two main verbs rather than a broad action list.	4 / 5
Completeness	The 'what' is clear (watches per-account engagement, files reports), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Good coverage of natural domain terms a CSM/AE would say — 'churn-risk', 'engagement', 'dormancy', 'champion departure', 'expansion', 'accounts' — but lacks synonyms and the occasional generic phrasing a user might lead with.	4 / 5
Distinctiveness Conflict Risk	A clear niche — 'PostHog Customer analytics (Accounts)', 'per-account engagement', 'weighted by commercial ownership' — with distinct triggers and minimal overlap risk against other scouts.	5 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	13 / 16 Passed

Repository: PostHog/posthog
Path: products/signals/skills/signals-scout-customer-analytics/SKILL.md
Commit: 31f2a90

Reviewed: about 21 hours 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.