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).

76

Quality

94%

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 strong, highly actionable body with executable SQL/JSON examples, an explicit validated workflow, and tight error-recovery guidance. The main improvement would be moving the large filter lookup table into a reference file for cleaner progressive disclosure.

Suggestions

Move the 'Starting points → filters' table and the two-step SQL pattern into a reference file (e.g. references/filter-patterns.md) and link to it from SKILL.md to improve progressive disclosure and token efficiency.

Trim the motivational framing in the intro and 'one rule' section ('A raw, unfiltered list is the worst possible answer', 'Treat them as a menu, not a script.') to pure directives.

Consider a brief validation step in step 4 noting how to confirm a shortlisted recording actually matches the goal (e.g. verifying visited_page hit) before deep-linking.

DimensionReasoningScore

Conciseness

Largely lean and directive with concrete tables and code, but a few framing passages ('Most people open session replay with a goal...', 'Treat them as a menu, not a script.') could be trimmed without losing actionability.

4 / 5

Actionability

Fully executable guidance: a copy-paste SQL query for collecting session IDs, concrete JSON filter shapes with exact operators/values, and specific parameter recommendations (filter_test_accounts: true, date_from -7d, order activity_score, limit 10).

5 / 5

Workflow Clarity

Clear 5-step sequence (Pin goal → Discover → Query → Triage → Offer next step) with explicit validation checkpoints ('Confirm with read-data-schema before putting a value in a filter') and an error-recovery feedback loop for zero-result queries.

5 / 5

Progressive Disclosure

Well-organized with clear sections and one-level-deep, clearly-signaled cross-skill references (Related skills); no bundle files exist to offload the sizable starting-points/filter table, which is inlined rather than split out.

4 / 5

Total

18

/

20

Passed

Description

100%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.

An exemplary description: third-person voice, concrete actions, comprehensive trigger phrases, and explicit positive/negative activation boundaries that distinguish it from adjacent replay skills. No meaningful weaknesses.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'Turns a vague intent into a focused RecordingsQuery via `query-session-recordings-list`', 'deep-links the best few', 'hands off to `investigating-replay`' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (turn intent into a focused RecordingsQuery, deep-link, hand off) and 'when' ('Use when the user asks which sessions...'), plus a 'Do NOT use when...' exclusion clause.

5 / 5

Trigger Term Quality

Comprehensive natural terms users would actually say: 'which sessions or replays to watch', 'finding interesting / useful recordings', 'don't know where to start', plus concrete goals (signup, pricing, onboarding, checkout, rageclicks, errors, mobile, a specific person).

5 / 5

Distinctiveness Conflict Risk

Clear niche (shortlisting recordings to watch) with distinct triggers and explicit boundary guidance ('Do NOT use when the user already has a recording/session ID ... use investigating-replay'), minimizing conflict with sibling skills.

5 / 5

Total

20

/

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.