Name: signals-scout-replay-vision
Rating: 58.4 (1 reviews)
Author: PostHog

signals-scout-replay-vision

Signals scout for PostHog Replay Vision scanners. Watches that enabled scanners keep observing (throughput and quota cliffs) and that aggregate score shifts and recurring themes get surfaced.

Quality

69%

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-replay-vision/SKILL.md

Quality

Content

76%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 content is highly actionable with executable SQL and precise tool-call guidance, a clearly sequenced workflow, and good progressive disclosure that defers the shared report contract to a one-level reference. The main weakness is length — the framing prose around the SQL could be trimmed to improve token efficiency.

Suggestions

Tighten the narrative framing around the SQL blocks (e.g. the push/pull and explore sections repeat the same discriminator/baseline points several times) to lift conciseness from 3 toward 4.

Consider extracting the long 'How a run works' sub-procedures or the MCP tools catalog into a referenced file so the SKILL.md body stays a lean overview.

If the referenced references/report-contract.md is the primary deep dive, add a one-line summary of what it covers at the reference link so readers know whether to follow it in-run.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence (no explanation of what PostHog or a scanner is), but at ~245 lines it is long and carries some padded framing/prose around the SQL that could be tightened without losing clarity.	3 / 5
Actionability	Provides fully executable, copy-paste-ready SQL for the close-out count, roster/pulse read, daily series, and tag concentration, plus exact MCP tool calls with argument specifics (e.g. 'id, not scanner_id', 'status: "failed"') covering the common cases.	5 / 5
Workflow Clarity	A clear sequenced run (Get oriented → Explore → Save memory → Decide → Close out) with strong validation guidance (footguns, status filters, SQL upper bounds), but it is an analytics/authoring flow rather than a destructive/batch operation with explicit validate→fix→retry checkpoints, so it sits just below a clean 5.	4 / 5
Progressive Disclosure	Well-structured with clear section headers; it explicitly offloads the report-channel contract to a one-level-deep reference ('authoring-scouts → references/report-contract.md', readable via skill-file-get) and adds only the replay-vision-specific framing. No bundle directories exist locally, so the in-body structure and the signaled single reference carry the score.	4 / 5
	Total	16 / 20 Passed

Description

62%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 and well-targeted to a clear niche with natural trigger terms, but lacks an explicit 'Use when...' clause, which caps completeness at 3. Adding concrete trigger guidance would lift the strongest remaining weakness.

Suggestions

Append an explicit 'Use when...' clause naming the natural triggers, e.g. 'Use when a PostHog Replay Vision scanner may have gone silent or an aggregate signal (verdict-rate, score, tag/theme concentration) needs surfacing across sessions.'

List a couple more concrete actions (e.g. 'detects observation throughput cliffs, flags quota exhaustion, surfaces tag/theme concentration') to push specificity from 4 toward 5.

Add common synonyms/variants users might say (e.g. 'session replay scanners', 'scanner findings', '$recording_observed') to round out trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (Replay Vision scanners) and several concrete actions — 'keep observing', 'throughput and quota cliffs', 'aggregate score shifts and recurring themes get surfaced' — but stops short of a comprehensive enumeration of actions, leaving minor coverage gaps.	4 / 5
Completeness	It clearly states what the skill does ('Watches that enabled scanners keep observing...') but has no explicit 'Use when...' trigger clause telling Claude when to invoke it, which caps completeness at 3 per the guideline.	3 / 5
Trigger Term Quality	Includes natural product terms a user would say ('PostHog Replay Vision', 'scanners', 'throughput', 'quota', 'score shifts', 'recurring themes') with good coverage, though it omits common synonyms or file/extension-style variants.	4 / 5
Distinctiveness Conflict Risk	The narrow niche ('PostHog Replay Vision scanners', aggregate vs per-session signal) is clearly distinct from sibling scouts (session-replay, error-tracking) with only minor overlap risk on the broad word 'scanners'.	4 / 5
	Total	15 / 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-replay-vision/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.