CtrlK
BlogDocsLog inGet started
Tessl Logo

finding-sessions-to-watch

Guides a user from "I want to watch recordings but don't know which ones" to a short, high-signal list of sessions worth watching. Use when the user asks which sessions or replays to watch, wants help finding interesting / useful recordings, says they don't know where to start in session replay, or wants to watch sessions about a goal (signup, pricing, onboarding, checkout, a feature, rageclicks, errors, mobile, a specific person) without naming exact filters. Turns a vague intent into a focused RecordingsQuery via `query-session-recordings-list`, then deep-links the best few and hands off to `investigating-replay`. Do NOT use when the user already has a recording/session ID (use investigating-replay) or wants the replay for a known error issue (use finding-replay-for-issue).

75

Quality

92%

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

85%

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 workflow-clear, with executable examples and explicit verification/recovery steps. Its only weakness is mild verbosity and overlap between the workflow, worked example, and tips sections that could be consolidated.

Suggestions

Trim overlap between the Workflow, Worked example, and Tips sections — e.g. fold the zero-recordings recovery guidance and the activity_score caveat into a single place rather than restating across sections.

Consider condensing the starting-points table by collapsing near-identical approaches (e.g. the two-step rows) into a shared pattern referenced once, reducing the largest token block.

DimensionReasoningScore

Conciseness

Per-line it is lean and assumes Claude's competence with no concept-fluff, but the overall length (~150 lines including a large starting-points table) plus mild repetition between the workflow, worked example, and tips means it could be tightened, matching the 'mostly efficient but could be tightened' anchor.

2 / 3

Actionability

Provides fully executable SQL and JSON query blocks, concrete filter objects with exact operators/values, and specific parameter settings (filter_test_accounts: true, limit: 10, order values), plus a worked end-to-end example that is copy-paste ready.

3 / 3

Workflow Clarity

A clearly sequenced 5-step workflow with an explicit validation checkpoint ('Confirm with read-data-schema... before putting a value in a filter') and an error-recovery loop (zero recordings → widen date range/loosen filter before concluding), matching the clear-sequence-with-validation anchor.

3 / 3

Progressive Disclosure

No bundle files exist and the body is self-contained, but it is cleanly sectioned (one rule, available tools, workflow, starting points, worked example, tips) with no nested references, which per the scoring notes earns a 3 for a self-contained, well-organized skill.

3 / 3

Total

11

/

12

Passed

Description

100%

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, trigger-rich, complete, and well-differentiated, written in the required third person. It cleanly conveys both capability and invocation conditions with explicit positive and negative triggers.

DimensionReasoningScore

Specificity

Names several discrete concrete actions (turn intent into a RecordingsQuery, deep-link the best few, hand off to investigating-replay) plus the specific tool that performs each, matching the 'multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what ('Guides a user from... to a short, high-signal list') and when (a 'Use when...' clause with multiple trigger conditions plus a 'Do NOT use when...' negative), satisfying the both-what-and-when anchor.

3 / 3

Trigger Term Quality

Surfaces natural phrasings a user would actually say ('which sessions or replays to watch', 'finding interesting / useful recordings', 'don't know where to start') plus a broad list of goal keywords (signup, pricing, rageclicks, errors, mobile), giving good coverage of likely trigger terms.

3 / 3

Distinctiveness Conflict Risk

Has a clear niche (replay discovery for vague intent) and explicitly disambiguates from sibling skills via 'Do NOT use when... use investigating-replay' and 'use finding-replay-for-issue', making accidental triggering unlikely.

3 / 3

Total

12

/

12

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.