clay-observability

Monitor Clay enrichment pipeline health, credit consumption, and data quality metrics. Use when setting up dashboards for Clay operations, configuring alerts for credit burn, or tracking enrichment success rates. Trigger with phrases like "clay monitoring", "clay metrics", "clay observability", "monitor clay", "clay alerts", "clay dashboard", "clay credit tracking".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and token-efficient, delivering complete executable code across collection, alerting, and dashboarding. Its weaknesses are the absence of validation/feedback checkpoints in the workflow and a monolithic structure with a dangling reference to a missing runbook file.

Suggestions

Add explicit validation checkpoints between steps (e.g., after Step 1 confirm the webhook is receiving enrichment callbacks; after Step 3 verify each alert fires on a synthetic condition) so the workflow has a validate-then-proceed feedback loop.

Split the Prometheus metric definitions and dashboard panel config into reference files under references/ and link to them one level deep, keeping SKILL.md as a lean overview.

Resolve the dangling "see `clay-incident-runbook`" reference by either adding the runbook as a bundle file or removing/qualifying the pointer so navigation is not broken.

Dimension	Reasoning	Score
Conciseness	Lean prose with no over-explanation of concepts Claude already knows; the bulk is dense, purposeful code where each block teaches a distinct concern (collection, Prometheus export, alerting, dashboard, daily report), matching the lean-every-token-earns-its-place anchor rather than the could-be-tightened level 2.	3 / 3
Actionability	Provides fully executable TypeScript classes, prom-client metric definitions, Prometheus alert rules, and dashboard panel configs that are copy-paste ready, matching the fully-executable anchor rather than the pseudocode/incomplete level 2.	3 / 3
Workflow Clarity	Steps 1–5 are clearly sequenced, but there are no inline validation checkpoints or feedback loops (e.g., verify the webhook receives data before layering alerts, test that an alert fires before relying on it); for a batch enrichment pipeline the missing validation caps this at 2 rather than the explicit-checkpoint level 3, and it is above the steps-unclear level 1.	2 / 3
Progressive Disclosure	Sections are well-organized (Overview, Prerequisites, Steps 1–5, Error Handling, Resources, Next Steps) but the ~244-line body is monolithic with all dashboard/Prometheus content inline that could be split into reference files, and "Next Steps" points to a `clay-incident-runbook` that does not exist in any bundle — matching the some-structure-but-inline anchor rather than the cleanly-split level 3.	2 / 3
	Total	10 / 12 Passed

Description

100%

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, complete, and distinctive, naming concrete monitoring actions with explicit "Use when" triggers and a strong set of natural Clay-prefixed keywords. It uses third-person imperative voice with no first/second-person penalty.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: "Monitor Clay enrichment pipeline health, credit consumption, and data quality metrics" plus "setting up dashboards", "configuring alerts for credit burn", and "tracking enrichment success rates" — matching the multiple-specific-actions anchor, not the names-some-actions level 2.	3 / 3
Completeness	Explicitly answers both what ("Monitor Clay enrichment pipeline health... metrics") and when via a "Use when..." clause plus trigger phrases, matching the clearly-answers-both anchor rather than the what-only level 2.	3 / 3
Trigger Term Quality	Provides good natural coverage a user would actually say — "clay monitoring", "clay metrics", "clay observability", "monitor clay", "clay alerts", "clay dashboard", "clay credit tracking" — matching the good-coverage anchor rather than the missing-variations level 2.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear Clay-specific niche with all triggers prefixed by "clay", making it unlikely to fire for unrelated skills; not the somewhat-generic level 2.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 02d6341

Reviewed: 2 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.