CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

64

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

—

The risk profile of this skill

SKILL.md
Quality
Evals
Security

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.

The body is highly actionable with executable SQL, clear tooling, and a well-sequenced workflow with validation checkpoints; its main weaknesses are mild verbosity in the framing prose and progressive disclosure that leans on another skill's reference rather than a local bundle.

Suggestions

Tighten the bolded thesis sentences ("The discriminator...", "The linchpin...") into concise statements; the surrounding concrete guidance already carries the meaning.

Consider hosting the report-contract essentials referenced repeatedly (edit-vs-author rules, status mapping, dedupe) as a local references/ file so progressive disclosure is self-contained within this skill's bundle.

Trim restated framing across sections (e.g. the per-account-vs-fleet point is made in the intro, the table, Decide, and Disqualifiers) to reduce token redundancy.

DimensionReasoningScore

Conciseness

Dense and assumes Claude's competence (no explanations of PostHog/SQL/churn), with every section earning its place via concrete SQL and tool calls, but the bolded thesis sentences ("The discriminator...", "The linchpin...") and some restated framing add tokens a leaner version could trim.

4 / 5

Actionability

Fully executable guidance: copy-paste-ready SQL for the join check, engagement cliff, and dormancy detection; named tools with parameters; concrete scratchpad key prefixes; and explicit P2/P3 priority rules covering the common cases.

5 / 5

Workflow Clarity

Clear run sequence (Orient → Profile → Explore → Save memory → Decide → Close out) with explicit validation checkpoints (join verification, fleet-held check, quick close-out), feedback loops (edit-vs-author, re-escalation), and a disqualifier checklist plus "When to stop" conditions.

5 / 5

Progressive Disclosure

Well-signaled one-level-deep reference to references/report-contract.md for generic mechanics and good section structure, but the referenced file belongs to another skill (no local references/scripts/assets bundle here) and generic mechanics are repeatedly pointed away rather than owned locally.

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, distinctive, and uses natural domain keywords, but it omits any explicit "when to use" trigger guidance, capping completeness at 3.

Suggestions

Add a "Use when..." clause naming the situations that should trigger this skill (e.g. renewal reviews, CSM/AE account-health questions, proactively surfacing disengaging or expanding accounts).

Vary the action verbs beyond "watches" to distinguish the concrete behaviors (e.g. "detects engagement cliffs, flags dormancy, surfaces champion departures, and identifies expansion opportunities").

Include a couple of natural synonyms/variations (e.g. "account health", "renewal risk", "upsell") to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain (PostHog Customer analytics/Accounts) and lists several concrete signal shapes — "engagement cliffs, dormancy, champion departure — and the expansion inverse" — but all share the single verb family "watches for", so coverage is several specific actions with minor gaps rather than multiple distinct action types.

4 / 5

Completeness

It clearly states what the skill does (watches per-account engagement for churn-risk shapes) but has no "Use when..." or equivalent explicit trigger guidance for when to invoke it, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Includes natural domain terms a CSM/AE would say ("Customer analytics", "Accounts", "churn-risk", "engagement cliffs", "dormancy", "champion departure", "expansion") with good coverage, but offers no synonyms or variations to reach comprehensive.

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche (PostHog Customer analytics, per-account engagement weighted by commercial ownership) with distinct triggers and minimal overlap with sibling scouts.

5 / 5

Total

16

/

20

Passed

Validation

81%

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

CriteriaDescriptionResult

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

Revision

130f3a1

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill