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

—

The risk profile of this skill

Fix and improve this skill with Tessl

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

Quality

Content

77%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 scout skill with executable queries, strong workflow sequencing, and explicit validation/checklists. Its weaknesses are repeated security framing and Decide prose that could be trimmed, and two referenced files that are missing from the bundle.

Suggestions

Create references/remediation.md and references/onset-correlation.md (or remove the dead links and inline the essential procedure) so the progressive-disclosure pointers resolve.

Consolidate the attacker-controllable-telemetry guidance into one canonical section and reference it from the others instead of restating it in the SQL block, Explore, and Decide sections.

Tighten the Decide section's repo-naming discussion, which restates the trusted-source / NO_REPO logic across several paragraphs.

Dimension	Reasoning	Score
Conciseness	It avoids explaining basics (no "what is a web vital" padding) and the SQL/decision content earns its place, but the attacker-controllable-telemetry framing is repeated across three separate sections and the Decide prose restates the repo-naming logic multiple times, so it could be noticeably tightened.	3 / 5
Actionability	Fully executable, copy-paste-ready SQL queries with sanitization baked in (standing-poor, improvement-opportunity, band-crossing, site-wide shift), named MCP tool calls with parameters, and concrete scratchpad key patterns cover the common cases.	5 / 5
Workflow Clarity	Clear sequenced run (Get oriented → Profile shape → Explore → Save memory → Decide → Close out) with explicit validation checkpoints (volume gates, confirm-with-count before not-in-use, variant-split confirmation before promoting a cause) and checklists (Disqualifiers; edit/author/remember/skip rails).	5 / 5
Progressive Disclosure	Sectioning and one-level reference pointers are clearly signaled and purpose-labeled, but the two referenced files — references/remediation.md and references/onset-correlation.md — do not exist in the bundle, so the disclosed references are dead ends that break the navigation model.	3 / 5
	Total	16 / 20 Passed

Description

78%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, well-termed description that concretely names the domain, metrics, and actions, with strong trigger vocabulary. Its main gap is the absence of an explicit "Use when..." clause, which leaves the trigger condition implicit and caps completeness.

Suggestions

Append an explicit trigger clause, e.g. "Use when investigating page-speed regressions or Core Web Vitals (LCP/INP/CLS/FCP) findings, p75 thresholds, or band crossings." to lift completeness above 3.

Tighten distinctiveness by naming the sibling-scout boundary inline (e.g. "not for whole-site anomaly detection or capture-health gaps") so it is less likely to collide with related scouts.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Watches each page's p75 LCP / INP / CLS / FCP against Google's thresholds and its own history", finds "poor-band pages, band crossings, sharp regressions", and "dates each regression against deploys and flag rollouts" — giving comprehensive coverage of the scout's capabilities.	5 / 5
Completeness	The "what" is explicit and concrete, but there is no "Use when..." clause or equivalent trigger guidance; per the rubric a missing trigger clause caps completeness at 3 (anchor: clear what, when missing/weakly implied).	3 / 5
Trigger Term Quality	Comprehensive natural terms a user would actually say — "Core Web Vitals", "web vitals", "p75", "LCP / INP / CLS / FCP", "thresholds", "regressions", "deploys", "flag rollouts" — including the synonym pair Core Web Vitals / web vitals.	5 / 5
Distinctiveness Conflict Risk	The Core Web Vitals niche (p75 LCP/INP/CLS/FCP against Google thresholds) is distinct, but the broader "signals scout" family includes closely related sibling scouts covering web-analytics and anomaly detection, creating minor overlap risk rather than a fully isolated niche.	4 / 5
	Total	17 / 20 Passed

Validation

68%

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 — 11 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (627 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
relative_links	Relative link issues: 6 missing	Warning
referenced_paths_exist	Referenced path issues: 12 missing	Warning

	Total	11 / 16 Passed

Repository: PostHog/posthog
Path: products/signals/skills/signals-scout-web-vitals/SKILL.md
Commit: 130f3a1

Reviewed: 9 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.