Tessl • The package manager for agent skills

SkillPublic

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

77%

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-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 an exceptionally actionable, well-sequenced scout playbook: concrete tool calls, runnable SQL, explicit validation checkpoints, and clear edit-vs-author feedback loops. Its only weaknesses are moderate redundancy of the bundle-by-root-cause message and some inlined catalog content that could be split into a bundled reference file.

Suggestions

De-duplicate the bundle-by-root-cause and edit-vs-author guidance — state each once authoritatively (e.g. in Decide) and reference it from Explore/Calibration rather than restating.

Move the severity-to-kind cheat sheet and the scratchpad key catalog into a bundled references/ file (e.g. references/kinds.md, references/scratchpad-keys.md) linked from SKILL.md, so the overview stays lean.

Tighten the Calibration paragraph, which restates discriminator examples already covered in the opening and Explore sections.

Dimension	Reasoning	Score
Conciseness	The body is dense with judgment Claude would not already know (the kind-concentration discriminator, calibration, untrusted-data handling) and avoids explaining basic concepts, matching the score-4 anchor of efficient with minor trimmable instances; not a 5 because the bundle-by-root-cause and edit-vs-author guidance is restated several times across Calibration, Explore, and Decide.	4 / 5
Actionability	It gives fully executable, copy-paste-ready guidance — exact MCP calls ("health-issues-list status=active severity=critical dismissed=false"), a runnable SQL query for sdk_outdated traffic share, concrete scratchpad key formats, and explicit priority/actionability mappings — matching the score-5 anchor of copy-paste-ready commands covering common cases.	5 / 5
Workflow Clarity	The run is clearly sequenced (Quick close-out → Get oriented → Profile shape → Explore → Save memory → Decide → Close out) with explicit validation steps (confirm $pageview collapse, corroborate blast radius with execute-sql, check inbox before authoring) and feedback loops (edit-vs-author with append_evidence re-escalation), plus checklists (5 explore patterns, disqualifiers); the skill is read-only/report-authoring so the destructive-batch cap at 3 does not apply.	5 / 5
Progressive Disclosure	Structure is strong with clear headers and well-signaled one-level-deep cross-skill references (authoring-scouts → references/report-contract.md, posthog:querying-posthog-data) that offload generic mechanics rather than restating them, matching the score-4 anchor of good structure with minor gaps; not a 5 because the skill ships no bundle of its own and inlines catalog-like content (the severity-to-kind cheat sheet, the full scratchpad key catalog) that could live in a reference file.	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 is specific and distinct, naming a clear PostHog health-checks niche with three concrete actions, but it omits any explicit "when to use" trigger guidance and carries a narrow set of trigger terms. Completeness is the main drag, capped at 3 by the missing Use-when clause.

Suggestions

Add an explicit trigger clause, e.g. "Use when triaging PostHog setup health, surfacing active health issues, or deciding which health-check findings to report."

Broaden trigger-term coverage with natural synonyms a user would say ("setup health", "health-check findings", "active health issues", "health-check alerts").

Mention the report-authoring outcome (file/edit reports) so the "what" covers the full action surface, not just bundling/weighting/surfacing.

Dimension	Reasoning	Score
Specificity	Names the domain (PostHog health checks/health issues) and 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 score-4 anchor of several specific actions with minor coverage gaps; not a 5 because coverage is incomplete (no mention of authoring/editing reports or dedupe) and "surfaces" is slightly less concrete than the score-5 examples.	4 / 5
Completeness	It clearly states what the skill does (bundle, weight, surface active health issues) but provides no explicit "Use when…" clause or equivalent trigger guidance, so per the judging guidelines completeness is capped at 3; not a 2 because the "what" is clear and specific, not a 4 because the "when" is absent rather than merely implicit.	3 / 5
Trigger Term Quality	"health checks" and "health issues" are relevant natural keywords, but coverage is limited to those two terms with no synonyms or variations, matching the score-3 anchor of some relevant keywords missing common variations; not a 4 because there is no broader set of natural trigger phrases.	3 / 5
Distinctiveness Conflict Risk	"Signals scout over PostHog's own health checks" carves a clear niche with distinct triggers and minimal conflict risk, matching the score-4 anchor of mostly distinct with minor overlap; not a 5 because sibling signals scouts (e.g. a feature-flags scout) share the broader signals-scout framing and could overlap on adjacent issues.	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
Revision: 130f3a1

Reviewed: 29 days ago

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.

signals-scout-health-checks

Table of Contents

Is this your skill?