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

90%

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

Quality

Content

80%Weight 40%Scale 1-3

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, dominated by executable code with no concept padding. Its weaknesses are the absence of validation/feedback checkpoints in the setup workflow and the lack of any real bundle-file structure for progressive disclosure.

Suggestions

Add explicit validation checkpoints to the workflow — e.g., after Step 2 verify Prometheus is scraping clay_* metrics, and after Step 3 dry-run or test-fire the alert rules — to introduce a validate-then-proceed feedback loop.

Split the detailed alerting rules and dashboard panel YAML into a reference file such as references/clay-alerts.yml and link to it from SKILL.md so the main file stays an overview.

Either create the referenced clay-incident-runbook as a real linked file or remove the dangling pointer, so navigation targets actually resolve.

Dimension	Reasoning	Score
Conciseness	Lean, mostly executable code with a one-sentence overview and concise prerequisites; it assumes Claude's knowledge of TypeScript/Prometheus rather than tutorializing concepts, so not the level-2 'unnecessary explanation' anchor.	3 / 3
Actionability	Provides fully executable TypeScript collectors, prom-client metrics, YAML alert rules, dashboard panel configs, and a Slack-posting daily report — copy-paste ready, matching the executable-code anchor.	3 / 3
Workflow Clarity	Steps 1–5 are clearly sequenced, but there are no explicit validation or verification checkpoints (e.g., confirm metrics are being scraped, test that alerts fire), fitting the 'sequence present but checkpoints missing' anchor rather than level 3.	2 / 3
Progressive Disclosure	All code is inline in a single ~240-line file rather than split into referenced bundles; the only pointer — 'see clay-incident-runbook' — is not a real linked file, so it is not the level-3 well-signaled one-level-deep reference structure.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-crafted description that concretely states capabilities, provides an explicit Use-when clause, and lists natural trigger phrases in third-person voice. It cleanly satisfies all four dimensions.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions — 'Monitor Clay enrichment pipeline health, credit consumption, and data quality metrics' plus 'setting up dashboards', 'configuring alerts', 'tracking enrichment success rates' — matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers both what ('Monitor Clay enrichment pipeline health, credit consumption, and data quality metrics') and when ('Use when setting up dashboards... configuring alerts... tracking enrichment success rates') with an explicit 'Use when' clause.	3 / 3
Trigger Term Quality	Lists natural phrases a user would say — 'clay monitoring', 'clay metrics', 'clay observability', 'monitor clay', 'clay alerts', 'clay dashboard', 'clay credit tracking' — with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Has a clear Clay-specific niche and 'clay'-prefixed triggers, making it unlikely to fire for unrelated skills; voice is third-person, incurring no penalty.	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
Path: plugins/saas-packs/clay-pack/skills/clay-observability/SKILL.md
Commit: 4c47e33

Reviewed: 3 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.