CtrlK
BlogDocsLog inGet started
Tessl Logo

finding-replay-for-issue

Finds the most informative session recording linked to an error tracking issue. Use when a user has an error tracking issue ID and wants to watch a replay showing what the user was doing when the error occurred. Ranks linked sessions by recency, activity score, and journey completeness, then summarizes the pre-error context. Replaces blind session picking from potentially hundreds of linked recordings.

68

Quality

81%

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

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.

A well-structured, actionable skill body with concrete SQL/tool examples, explicit ranking thresholds, and clear sequencing. It is consistently efficient rather than exemplary, with minor trimmable prose and no explicit verification checkpoint on the main path.

Suggestions

Tighten editorializing lines (e.g. "More candidates means better selection") to lift conciseness toward 5.

Add an explicit verification/presentation checkpoint in the main workflow (e.g. confirm the selected recording still loads and has the exception event before presenting) to strengthen workflow_clarity.

Consider splitting the Replay Vision optional section or the ranking rubric into a reference file to exercise genuine progressive disclosure, which would push that dimension higher.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence (tools table, runnable SQL/JSON, no basic-concept padding), with only a few editorializing lines like "More candidates means better selection" that could be trimmed, so it is efficient rather than perfectly tight.

4 / 5

Actionability

It provides executable SQL and tool-call JSON with explicit placeholders and concrete thresholds (under 10s, over 1hr, 2-15 min, active_seconds / recording_duration > 0.3); placeholders still need substitution and the JSON blocks omit a full envelope, leaving minor gaps.

4 / 5

Workflow Clarity

A clear four-step sequence with an optional check-then-scan loop and edge-case handling in Tips; it is a read-only selection workflow so the destructive-cap does not apply, but the main path lacks an explicit verification checkpoint, holding it at 4.

4 / 5

Progressive Disclosure

Well-organized single-file structure (tools table, numbered steps, Tips, Related skills) with one-level-deep skill references and no nested/buried references; no bundle files exist so there is nothing to offload, keeping it just below a 5 that would require clear external-file disclosure.

4 / 5

Total

16

/

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 strong, specific description that clearly states what the skill does and when to use it, with concrete ranking criteria and a distinct niche. Minor room to broaden trigger synonyms and clarify the summary output.

DimensionReasoningScore

Specificity

Names several concrete actions ("Finds the most informative session recording", "Ranks linked sessions by recency, activity score, and journey completeness, then summarizes the pre-error context"), but the summarize step leaves output coverage slightly unspecified, so it stops just short of 5.

4 / 5

Completeness

It explicitly answers both what (find/rank/summarize the best recording) and when ("Use when a user has an error tracking issue ID and wants to watch a replay showing what the user was doing") with concrete trigger phrasing.

5 / 5

Trigger Term Quality

The "Use when a user has an error tracking issue ID and wants to watch a replay" clause surfaces natural phrases users say (replay, error tracking issue, watch a replay), though a few synonyms/variants are missing, placing it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (most informative replay linked to an error tracking issue) with distinct triggers and minimal overlap risk, reinforced by explicit Related-skills boundaries.

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.