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

—

The risk profile of this skill

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 tightly written, highly actionable scout playbook with concrete tool calls, SQL patterns, thresholds, and a well-sequenced workflow featuring explicit validation and feedback loops; its main limitation is that sizable reference-like sections (gap-family detail, MCP tools) are inlined rather than progressively disclosed.

Dimension	Reasoning	Score
Conciseness	The body is information-dense with specialized domain logic (saturation tripwires, the watch lifecycle, escape rules for ILIKE) and assumes Claude's competence rather than explaining PostHog basics; it earns a 4 with only minor rhetorical flourishes ('Recommendations are a budget, not a target') that could be trimmed, and is not verbose enough to drop to 3.	4 / 5
Actionability	Guidance is fully executable: named tool calls (`read-data-schema events`, `execute-sql` over `system.insights`), copy-paste SQL patterns (`query::text ILIKE '%{event_name}%'`, the new-emergence probe), exact scratchpad key formats, and concrete thresholds (>1000/day, ~500 distinct users/7d) cover the common cases, matching the 'fully executable; copy-paste ready' anchor.	5 / 5
Workflow Clarity	A clear sequenced run (orient -> explore -> decide -> park/author -> close out) with explicit validation checkpoints (7-complete-day stability bar, re-verify every discriminating condition before authoring) and a 4-step watch lifecycle feedback loop fits the 'clear sequence with explicit validation steps and feedback loops' anchor.	5 / 5
Progressive Disclosure	Structure is well-organized with clear headers and one-level-deep external references that are clearly signaled (`authoring-scouts` -> `references/report-contract.md`, baked-in `posthog:` skills); minor organization gaps remain since the detailed six-family exploration and the MCP tools catalog are inlined rather than split, keeping it at 4 rather than 5.	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 clearly communicates a specialized niche and a couple of concrete recommendation actions, but it omits any explicit 'when to use' trigger guidance and relies on technical jargon rather than natural user phrasing.

Suggestions

Add a 'Use when ...' clause naming natural trigger phrases (e.g. 'Use when reviewing observability coverage, finding untracked high-volume events, or surfacing missing insights/dashboards/alerts').

Broaden trigger terms with synonyms and concrete artifacts a user might mention ('untracked events', 'missing alerts', 'no insight on a high-volume event') to improve natural keyword coverage.

State the recommendation actions more distinctly (detect gaps, recommend insights, recommend dashboards, configure alerts) to push specificity toward comprehensive.

Dimension	Reasoning	Score
Specificity	Names the domain ('observability gaps', 'significant event volumes with no insight, dashboard, or alert coverage') and concrete recommendation actions ('Recommends new insights, dashboards, or alerts'), matching the 'names domain and 1-2 concrete actions' anchor; it does not enumerate a comprehensive set of distinct actions, so it is not a 4.	3 / 5
Completeness	It clearly answers 'what' (scout for observability gaps and recommend coverage) but provides no 'Use when...' clause or equivalent trigger guidance; per the rubric a missing explicit 'when' caps completeness at 3, so it does not reach 4.	3 / 5
Trigger Term Quality	Relevant domain keywords are present ('observability gaps', 'insight', 'dashboard', 'alert coverage') but they are specialized jargon with no natural synonyms or variations a user would commonly say, fitting the 'some relevant keywords but missing common variations' anchor rather than the broad coverage of a 4.	3 / 5
Distinctiveness Conflict Risk	The 'observability gaps' niche is clearly framed and specific to the Signals scout role, giving it a mostly-distinct profile with only minor overlap risk against sibling scouts, which fits the 'mostly distinct; minor overlap risk' anchor; without an explicit distinguishing trigger phrase it is not a 5.	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: 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.