Name: signals-scout-health-checks
Rating: 61.6 (1 reviews)
Author: PostHog

signals-scout-health-checks

Signals scout over PostHog's own health checks. Bundles the project's active health issues by kind, weights them by blast radius, and surfaces the ones worth acting on.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./products/signals/skills/signals-scout-health-checks/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 operational runbook: highly actionable with concrete tool calls and SQL, a clearly sequenced workflow with validation gates, and good deferral of generic mechanics to an external reference. The main gaps are minor conciseness redundancy and a missed opportunity to split dense reference-style detail into a bundled file.

Dimension	Reasoning	Score
Conciseness	The body is dense with domain-specific operational detail Claude would not know (tool names, filter guards, dedupe keys, kind tables, SQL) and avoids explaining known concepts, matching 'efficient; minor instances that could be trimmed'; not a 5 because the edit-vs-author logic and untrusted-data rules recur across sections and a few passages could tighten.	4 / 5
Actionability	Guidance is copy-paste ready: exact tool calls with parameters ('health-issues-list kind=<kind> status=active dismissed=false'), a runnable SQL query ('SELECT properties.$lib_version, count() FROM events WHERE timestamp > now() - INTERVAL 7 DAY GROUP BY 1 ORDER BY 2 DESC'), concrete dedupe keys, and explicit priority/actionability mappings covering common cases.	5 / 5
Workflow Clarity	A clear sequence runs from Quick close-out through orient → profile → explore (5 numbered patterns) → save memory → decide → close out, with explicit validation gates ('If total is 0... close out empty', confirm capture 'actually collapsed', 'check before authoring so you edit instead of duplicating') and a Disqualifiers checklist; not capped because report authoring has validation present.	5 / 5
Progressive Disclosure	Generic report mechanics are correctly deferred to a clearly signaled one-level-deep reference ('authoring-scouts → references/report-contract.md') and section structure is clean, matching 'good structure; references mostly clear; minor organization gaps'; not a 5 because no bundle files ship with this skill and dense inline material (the full severity cheat sheet, per-kind weighting) could itself be split into a reference.	4 / 5
	Total	18 / 20 Passed

Description

58%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 states a clear, specific 'what' tied to a distinct PostHog niche, but it omits any 'when to use this' trigger guidance, which caps completeness and weakens trigger-term quality. Adding an explicit 'Use when...' clause with natural user phrases would lift the weakest dimensions.

Suggestions

Add a 'Use when...' clause naming natural trigger phrases (e.g. 'Use when reviewing a PostHog project's setup health, triaging active health issues, or deciding which health-check findings to report').

Include user-natural synonyms/extensions such as 'health checks', 'health issues', 'setup health', and 'triage' to improve trigger-term coverage.

Clarify the surfacing output (e.g. 'files a small number of framed reports to the inbox') so the 'what' is comprehensive rather than stopping at 'surfaces'.

Dimension	Reasoning	Score
Specificity	Quotes three concrete actions — 'Bundles the project's active health issues by kind', 'weights them by blast radius', 'surfaces the ones worth acting on' — matching the 'lists several specific actions; minor gaps' anchor; not a 5 because coverage is not comprehensive (no mention of authoring/editing reports, dedupe, disqualifiers).	4 / 5
Completeness	The 'what' is clear (bundle by kind, weight by blast radius, surface) but there is no 'Use when...' or equivalent explicit trigger guidance, so per the rubric completeness is capped at 3; it is not a 2 because the 'what' is clearly stated rather than vague.	3 / 5
Trigger Term Quality	Relevant domain keywords appear ('health checks', 'health issues', 'blast radius') but they lean technical and lack common user-natural variations/synonyms, matching 'some relevant keywords but missing common variations'; not a 4 because the natural phrasing a user would say is thin.	3 / 5
Distinctiveness Conflict Risk	The niche is specific — 'PostHog's own health checks', issues 'by kind', 'blast radius' — making it mostly distinct with only minor overlap risk against sibling signals-scout skills; not a 5 because the absent explicit triggers leave some ambiguity versus other scouts.	4 / 5
	Total	14 / 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-health-checks/SKILL.md
Commit: 57503b8

Reviewed: 14 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.