signals-scout-web-vitals

Signals scout for Core Web Vitals (`$web_vitals`). Watches each page's p75 LCP / INP / CLS / FCP against Google's thresholds and its own history — poor-band pages, band crossings, sharp regressions — and dates each regression against deploys and flag rollouts.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./products/signals/skills/signals-scout-web-vitals/SKILL.md

Quality

Content

81%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 dense, highly actionable scouting procedure with strong workflow sequencing and validation checkpoints, backed by two well-signaled reference files. Its main weakness is verbosity — repeated security caveats and decision-philosophy restatements — that could be trimmed without losing clarity.

Suggestions

Consolidate the attacker-controllable `$host`/`$pathname` sanitization guidance into one canonical section and reference it rather than restating it three times.

Factor the long Decide rails and memory-key examples into a reference file, leaving the body with the decision spine and pointers.

Trim restated decision philosophy ('Name one cause and one change, never a menu' appears multiple times) to a single canonical statement.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and loaded with domain knowledge Claude lacks (band thresholds, volume-gating, deploy-marker dating), but it repeats decision philosophy ('Name one cause and one change, never a menu') and the attacker-controllable `$host`/`$pathname` warning three or more times, so it could be tightened.	3 / 5
Actionability	Copy-paste-ready SQL blocks with exact HAVING thresholds, specific MCP tool calls with arguments, and concrete memory-key formats make the guidance fully executable across the common cases.	5 / 5
Workflow Clarity	A clearly sequenced cycle (oriented → profile → explore → save memory → decide → close out) with explicit validation gates (volume gates, 'confirm with a cheap count', flag-split confirmation) and feedback loops for the batch report-authoring operation.	5 / 5
Progressive Disclosure	Well-signaled one-level-deep references to two real bundle files (remediation.md, onset-correlation.md) with clear 'when to read' framing, but the ~600-line body inlines substantial prose (the Decide rails, memory-key examples) that could partly live in references.	4 / 5
	Total	17 / 20 Passed

Description

75%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 specific, distinctive description that names concrete capabilities and natural trigger terms, but it omits an explicit 'Use when...' trigger clause, capping completeness at the midpoint. Adding a one-sentence trigger clause would raise the completeness anchor.

Suggestions

Append an explicit trigger clause such as 'Use when investigating Core Web Vitals regressions, poor-band pages, or p75 movement against Google's LCP/INP/CLS/FCP thresholds.'

Surface the raw `$web_vitals` event name as a synonym so the description matches telemetry-flavored user phrasing.

Dimension	Reasoning	Score
Specificity	Names the domain (Core Web Vitals, `$web_vitals`) and multiple concrete actions — watches p75 LCP/INP/CLS/FCP, detects 'poor-band pages, band crossings, sharp regressions', and 'dates each regression against deploys and flag rollouts' — giving comprehensive coverage.	5 / 5
Completeness	The 'what' is clear and concrete, but there is no explicit 'Use when...' trigger clause, so per the rubric completeness is capped at 3 with 'when' only weakly implied.	3 / 5
Trigger Term Quality	Strong natural terms ('Core Web Vitals', 'LCP / INP / CLS / FCP', 'p75', 'regressions', 'deploys and flag rollouts') that a user would actually say, with a few synonyms (the raw `$web_vitals` event name, '.pdf'-style extension equivalents) not surfaced.	4 / 5
Distinctiveness Conflict Risk	A clear niche ('Core Web Vitals scout', p75 against Google's thresholds) with sibling-surface boundaries carved out in the body, giving minimal conflict risk.	5 / 5
	Total	17 / 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
skill_md_line_count	SKILL.md is long (610 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: PostHog/posthog
Path: products/signals/skills/signals-scout-web-vitals/SKILL.md
Commit: b0fece0

Reviewed: 4 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.