Name: signals-scout-session-replay
Rating: 64.8 (1 reviews)
Author: PostHog

signals-scout-session-replay

Signals scout for PostHog session replay. Watches that sessions keep recording (capture cliffs) and surfaces friction inside recordings — rage/dead-click clusters, error-after- interaction cohorts.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./products/signals/skills/signals-scout-session-replay/SKILL.md

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 a highly actionable, well-sequenced scout runbook with executable SQL, explicit validation gates, and clean deferral of generic mechanics to a one-level reference; its only real weakness is minor verbosity in a few framing passages and an inlined tools index.

Suggestions

Trim the philosophical framing in the intro and 'concentration-vs-diffusion' paragraph to the essential rule, cutting ~10-15 lines.

Move the long MCP-tools section into a references file (e.g. references/tools.md) and keep only the per-section tool call inline where it is used.

Consider extracting the four friction-pattern SQL templates into a references/queries.md so the decision flow stays lean.

Dimension	Reasoning	Score
Conciseness	Dense and assumes tool competence throughout, with every section encoding actionable judgment rather than padding; it is not a 5 because a few framing passages (the two-promise intro, 'concentration-vs-diffusion') are mildly philosophical and could be trimmed, placing it at anchor 4.	4 / 5
Actionability	Multiple complete, copy-paste-ready SQL queries with exact time filters, named tool calls with parameters, and concrete numeric gates (>= ~3x baseline, >= ~10 sessions, >= ~5 persons) cover the common cases, matching the anchor 5 for fully executable guidance.	5 / 5
Workflow Clarity	A clear sequence (orient -> explore -> save memory -> decide -> close out) carries explicit validation checkpoints and feedback loops — baseline/volume gates, corroboration-before-authoring, inbox-check-before-emit, edit-vs-author rules — plus a Disqualifiers checklist, matching anchor 5; the destructive/batch cap does not apply because validation is pervasive.	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections and defers generic report mechanics to a one-level-deep, clearly signaled reference (authoring-scouts -> references/report-contract.md, readable via skill-file-get); not a 5 because the long inlined MCP-tools index and several full SQL blocks could arguably live in separate reference files, leaving minor organization gaps per anchor 4.	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, third-person, and well-scoped to a distinct niche, but it omits an explicit 'Use when...' trigger clause, capping completeness at 3.

Suggestions

Add an explicit trigger clause, e.g. 'Use when triaging PostHog session replay health or investigating rage-click / dead-click friction on a recorded surface.'

Surface a couple more natural synonyms ('session recordings', 'recording drop-off') to lift trigger-term coverage.

Consider naming the primary deliverable (e.g. 'files scout reports') so the 'what' names the action verb alongside the signals it watches.

Dimension	Reasoning	Score
Specificity	Names the domain (PostHog session replay) and several concrete signal types — 'capture cliffs', 'rage/dead-click clusters', 'error-after-interaction cohorts' — which is several specific actions with only minor coverage gaps, matching the anchor 4 rather than 5 which demands exhaustive coverage.	4 / 5
Completeness	The 'what' is clear (watches capture integrity, surfaces friction) but there is no 'Use when...' or equivalent explicit trigger clause, which per the judging guidelines caps completeness at 3; it is not a 4 because 'when' is only weakly implied, not stated.	3 / 5
Trigger Term Quality	Includes natural product terms a user would say — 'session replay', 'recordings', 'rage/dead-click', 'friction' — giving good keyword coverage; not a 5 because some natural synonyms/extensions (e.g. 'session recordings', 'recording drop') are absent.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche — 'Signals scout for PostHog session replay' scoped to capture cliffs and friction clusters — with distinct triggers and minimal overlap with other skills, matching the anchor 5.	5 / 5
	Total	16 / 20 Passed

Validation

81%

Warnings & errors only

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

Criteria	Description	Result
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-session-replay/SKILL.md
Commit: b0fece0

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.