CtrlK
BlogDocsLog inGet started
Tessl Logo

planning-voice-agent-user-interviews

Plan a round of user interviews conducted by PostHog's AI voice agent (a "robo interviewer") — the automated voice-agent interview product. Captures a UserInterviewTopic (who to target, what to ask, framing context, question list) and calls user-interview-topics-create. ONLY trigger when the user clearly wants an AI voice agent to actually run the interview calls (e.g. "set up robo user interviews", "have the voice agent interview these users"). Do NOT trigger for ordinary user research that does not involve the voice agent — finding or shortlisting users to talk to ("who'd be a good fit to interview about Y"), planning questions for a human-run interview, or analysing feedback are audience discovery, handled with normal data queries, not this skill. Also do NOT trigger for uploading a recorded interview audio file or browsing topics with user-interview-topics-list. When intent is ambiguous, first confirm what kind of research it is and whether they want an AI voice agent to conduct it (see Step 0).

72

Quality

88%

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

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 dense, actionable workflow with executable HogQL templates, strong validation checkpoints, and thoughtful batch/destructive-operation UX. It is slightly verbose in a couple of rationale passages but earns its length with concrete guidance and edge-case handling.

Suggestions

Tighten the inline coalesce rationale in 'Finding users by behavior' into a one-line note and move the detailed explanation into a reference file to reduce token cost.

The Step 0 confirmation guidance repeats the intro paragraph's scope statement; consider collapsing the overlap to a single scoping note.

With this much SQL template detail, splitting the per-segment queries into a reference file would improve progressive_disclosure and conciseness without losing actionability.

DimensionReasoningScore

Conciseness

Efficient overall with executable templates and purposeful sections, but the inlined rationale for the coalesce query and mild redundancy between the intro and Step 0 could be trimmed.

4 / 5

Actionability

Provides fully executable, copy-paste-ready HogQL templates per segment, a concrete JSON create payload, named tool calls, and explicit routing rules covering the common cases.

5 / 5

Workflow Clarity

Clear Steps 0-5 sequence with explicit validation checkpoints (500-member cap UX, 'Never proceed without an explicit decision', identifier-mismatch warnings) and feedback loops for batch operations.

5 / 5

Progressive Disclosure

Well-organized into clearly headed sections that keep related content inline with no nested references; good structure though no one-level-deep external file split is used.

4 / 5

Total

18

/

20

Passed

Description

87%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.

A highly specific, well-bounded description that names the concrete product, the API call, and its captured fields, while giving explicit positive and negative trigger phrases plus an ambiguity fallback. It is somewhat long but every clause earns its place by clarifying scope.

DimensionReasoningScore

Specificity

Names the concrete target (UserInterviewTopic) and the exact API call (user-interview-topics-create) plus its captured fields, listing several specific capabilities with only minor gaps in coverage.

4 / 5

Completeness

Explicitly answers both 'what' (captures a UserInterviewTopic and calls user-interview-topics-create) and 'when' with concrete trigger phrases and anti-trigger guidance, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural user phrases like 'set up robo user interviews' and 'have the voice agent interview these users' with good synonym coverage ('robo interviewer', 'voice agent', 'automated calls'), though a few common variants are missing.

4 / 5

Distinctiveness Conflict Risk

Has a clear niche with explicit boundary guidance distinguishing it from audience discovery, query-posthog-data, audio upload, and list operations, minimizing conflict risk.

5 / 5

Total

18

/

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.