signals-scout-observability-gaps

Signals scout for observability gaps — significant event volumes with no insight, dashboard, or alert coverage. Recommends new insights, dashboards, or alerts as the product evolves.

Quality

71%

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 skill body is highly actionable, with concrete SQL/thresholds/tool calls and a well-sequenced workflow featuring strong validation and feedback loops. It is token-efficient and well-structured, with only minor conciseness and organization room for improvement.

Dimension	Reasoning	Score
Conciseness	The body is dense and expert-level, assuming PostHog domain knowledge with little padding or basic-concept explanation; a few sections (e.g. the long Disqualifiers list) could be tightened but each item earns its place, fitting the 'efficient; minor instances that could be trimmed' anchor.	4 / 5
Actionability	Provides copy-paste-ready specifics throughout — exact SQL patterns ('query::text ILIKE %event_name%', 'filters::text ILIKE %FunnelsQuery%'), numeric thresholds (>1000/day, ~500 reach, 7d windows), concrete tool calls, and exact scratchpad key formats — fully executable across the common gap families.	5 / 5
Workflow Clarity	Clear sequence (Get oriented → Explore → Decide → Park/watch → Close out) with explicit validation checkpoints (7-complete-day stability bar, dedupe checks, re-verify-live-before-author, saturation tripwires) and a full park→re-verify→guard→retire feedback loop for the batch reporting operation.	5 / 5
Progressive Disclosure	Well-structured with clearly signaled one-level-deep references (authoring-scouts → references/report-contract.md, posthog:* skills) for deferred mechanics, and the body appropriately self-contains the observability-gaps-specific framing; with no bundle files present it can't fully hit the 5 anchor's multi-file split, sitting at good-but-not-exemplary organization.	4 / 5
	Total	18 / 20 Passed

Description

53%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 domain-distinct but lacks an explicit 'Use when...' trigger clause, which caps its completeness and trigger-term quality at the midpoint. Adding concrete trigger phrases and a few more distinct action verbs would lift it toward the top anchors.

Suggestions

Add an explicit 'Use when...' trigger clause naming natural user phrasings (e.g. 'Use when the team has high-volume events with no insight, dashboard, or alert coverage, or when auditing observability gaps').

Expand the action vocabulary beyond the single verb 'Recommends' to distinguish the actions (e.g. 'Detects untracked events, flags stale insights, recommends new insights, dashboards, and alerts').

Include common synonyms/extensions users might say ('untracked events', 'missing alerts', 'no dashboard coverage') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('observability gaps') and lists concrete objects (insights, dashboards, alerts), but the verb coverage is thin — essentially one action ('Recommends') applied to three objects rather than several distinct actions, fitting the 1-2-concrete-actions anchor.	3 / 5
Completeness	Has a clear 'what' (scouts for gaps, recommends coverage) but no explicit 'when/Use when...' trigger guidance; the 'as the product evolves' hint is only weakly implied timing, so per the guideline a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant domain keywords ('observability gaps', 'insight', 'dashboard', 'alert') but misses natural user phrasings and synonyms, and offers no 'Use when...' trigger phrase, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Carves a clear niche (PostHog Signals observability-gap scout) that is mostly distinct from sibling scouts, with only minor overlap risk; it doesn't fully articulate the niche boundary in the description itself, so it sits below the 5 anchor.	4 / 5
	Total	13 / 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: b0fece0

Reviewed: 1 day 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.