signals-scout-observability-gaps

Signals scout for observability gaps — significant event volumes with no insight, dashboard, or alert coverage. Files a report recommending new insights, dashboards, or alerts as the team's product evolves.

Quality

77%

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-observability-gaps/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 high-quality, actionable scout playbook with concrete SQL/tool guidance, explicit validation checkpoints, and a well-sequenced workflow with feedback loops. Its main weaknesses are minor repetition that could be trimmed and a monolithic single-file structure with no local reference bundle to offload the detailed playbooks.

Dimension	Reasoning	Score
Conciseness	The body is dense with non-obvious domain specifics (scratchpad key conventions, system-table columns, SQL patterns, disqualifiers) that Claude would not already know, and mostly assumes competence. It is not a 5 because the report-contract pointer and dedupe rules are repeated across sections and a few passages could be trimmed.	4 / 5
Actionability	Guidance is fully executable — concrete tool calls ('read-data-schema events', 'execute-sql' over 'system.insights'), copy-pasteable SQL ('min(timestamp) >= now() - 14d', 'query::text ILIKE '%{event_name}%''), explicit thresholds (>1000/day, ~500+ reach), and exact scratchpad key formats covering the common cases.	5 / 5
Workflow Clarity	The run is clearly sequenced (orient → explore six families → decide author/edit → park-then-author watch lifecycle → close out) with explicit validation checkpoints (re-verify live before authoring, 7-complete-day stability bar, dedupe before authoring) and a park→re-verify→author→guard→retire feedback loop, satisfying the batch-operation validation requirement.	5 / 5
Progressive Disclosure	Structure is good and generic mechanics are deferred one level deep to a clearly signaled reference ('authoring-scouts → references/report-contract.md', readable via 'skill-file-get') plus upstream PostHog skills. It is not a 5 because no local bundle files exist and the body itself is a long single file whose six-family SQL playbook and disqualifier list could arguably be split into reference files.	4 / 5
	Total	18 / 20 Passed

Description

66%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 clearly states what the skill does and names a distinct niche with good domain trigger terms, but it omits an explicit 'Use when...' trigger clause, leaving the 'when' only weakly implied. Adding a concrete trigger phrase would lift completeness and reduce overlap risk with sibling scouts.

Suggestions

Append an explicit trigger clause, e.g. 'Use when reviewing a team's observability coverage for under-observed high-volume events, or when planning new insights/dashboards/alerts.'

Lead with the action verb in third person and tighten the repeated 'insights, dashboards, or alerts' phrase so the core action (file a recommendation report) reads more distinctly.

Add a distinguishing cue (e.g. 'structural coverage gaps only, not anomaly detection') to separate it from the sibling anomaly/alert scouts.

Dimension	Reasoning	Score
Specificity	Names the domain ('observability gaps') and several concrete actions — scouting gaps in 'insight, dashboard, or alert coverage' and filing a report 'recommending new insights, dashboards, or alerts'. It falls short of 5 because the action set is narrow (really one action: file a recommendation report) rather than multiple distinct operations.	4 / 5
Completeness	The 'what' is clear ('Signals scout for observability gaps ... Files a report recommending ...'), but there is no explicit 'Use when...' trigger clause — 'as the team's product evolves' is only a weakly implied when, so per the rubric guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Covers the natural PostHog domain vocabulary a user would say — 'observability gaps', 'insight', 'dashboard', 'alert', 'coverage', 'event volumes'. Good keyword coverage; not a 5 because it lacks synonym/variation breadth comparable to the 'PDF files, PDFs, .pdf' anchor.	4 / 5
Distinctiveness Conflict Risk	The 'Signals scout for observability gaps' framing carves a clear niche, but it sits among several sibling scouts (anomaly-detection, insight-alerts, error-tracking) that share insight/dashboard/alert vocabulary, creating minor overlap risk rather than the minimal risk of a 5.	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-observability-gaps/SKILL.md
Commit: 31f2a90

Reviewed: about 22 hours 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.