Name: signals-scout-customer-analytics
Rating: 59.2 (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.

Quality

70%

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

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.

The content is highly actionable with executable SQL and a precise memory schema, and it practices good progressive disclosure by deferring generic mechanics to an external reference. The main weakness is repetition of the core discriminator concept, which inflates the token budget without adding new information.

Suggestions

Consolidate the "one staked account sliding while the fleet holds" discriminator into a single authoritative statement; later sections can reference it instead of restating it.

Consider splitting the scratchpad key taxonomy and the SQL query library into a local references/ file to shorten the SKILL.md overview.

Make the validation checkpoints (join check, fleet-held check, inbox dedupe) explicit numbered steps within the Decide flow so they read as enforced feedback loops rather than prose.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (no basic concept explanation) and is domain-dense, but the core discriminator ("one staked account sliding while the fleet holds") is restated across the intro, profile table, Decide, and Disqualifiers sections, so it could be tightened.	3 / 5
Actionability	Provides multiple complete, executable SQL queries (group-type discovery, engagement cliff, dormancy onset), exact tool names, and a precise scratchpad key taxonomy — copy-paste ready and covering the common cases.	5 / 5
Workflow Clarity	A clear run cycle (Orient → Profile → Explore → Save memory → Decide → Close out) with real validation checkpoints (join verification, baseline confirmation, inbox dedupe, fleet-held quantification) and a Disqualifier checklist; a few checkpoints are implicit rather than enforced as feedback loops.	4 / 5
Progressive Disclosure	Cleanly defers generic report mechanics to a clearly-signaled one-level-deep external reference (authoring-scouts → references/report-contract.md via skill-file-get) and keeps only customer-analytics framing inline; the inlined SQL/scratchpad schema is reasonable but the ~200-line body could split some detail into a local reference.	4 / 5
	Total	16 / 20 Passed

Description

66%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 and well-scoped to a clear niche, naming concrete churn-risk shapes and natural trigger terms. Its main weakness is the absence of an explicit "Use when..." trigger clause, which caps completeness.

Suggestions

Add an explicit "Use when..." clause naming the triggering situations (e.g., renewal reviews, account-health checks, spotting disengaging or expanding accounts).

Include common synonyms users actually say — retention, renewal, upsell, account health — alongside churn-risk and expansion.

Briefly note the per-account (not aggregate, not revenue) framing in the description to sharpen distinctiveness from sibling scouts.

Dimension	Reasoning	Score
Specificity	Names the domain (PostHog Customer analytics / Accounts) and several concrete detection targets — "engagement cliffs, dormancy, champion departure — and the expansion inverse" — which is multiple specific actions, though it stops short of naming the scoring/reporting mechanics.	4 / 5
Completeness	The "what" is clear (watches per-account engagement for churn-risk shapes), but there is no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes natural terms a CSM/AE would say ("customer analytics", "churn-risk", "engagement", "expansion"), but misses common synonyms like retention, renewal, upsell, and account health that users also voice.	4 / 5
Distinctiveness Conflict Risk	The niche is clear and engagement-scoped (per-account, not revenue), but sibling scouts in the same PostHog family (revenue-analytics, product-analytics) touch overlapping churn/retention territory, leaving minor overlap risk.	4 / 5
	Total	15 / 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: b0fece0

Reviewed: 3 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.