clay-policy-guardrails

Implement credit spending limits, data privacy enforcement, and input validation guardrails for Clay pipelines. Use when enforcing spending caps, blocking PII enrichment, or adding pre-enrichment validation rules. Trigger with phrases like "clay policy", "clay guardrails", "clay spending limit", "clay data privacy rules", "clay validation", "clay controls".

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 content is highly actionable and token-lean, delivering four complete executable guardrail implementations with minimal concept padding. Its weaknesses are workflow clarity (batch operations lack explicit validation/feedback checkpoints) and progressive disclosure (heavy inline code that should be split into reference files, plus a dangling external reference).

Suggestions

Add explicit validation checkpoints to the batch workflow — e.g., after validateBatch, instruct Claude to inspect stats (rejected/invalidDomain counts) and only proceed to enrichment/export when valid rows remain, looping back to fix inputs on failure.

Move the four full TypeScript implementations into reference files under references/ (e.g., credit-policy.ts, privacy-policy.ts) and keep SKILL.md as an overview that links to them one level deep, improving progressive disclosure.

Resolve the 'see clay-architecture-variants' Next Steps pointer: either make it a real bundle reference file or reword it so it does not read as a missing local reference.

Dimension	Reasoning	Score
Conciseness	The body is lean code-first content with brief framing (short Overview, Prerequisites, a compact error table, link-only Resources) and no explanation of concepts Claude already knows like what GDPR is; the inline TypeScript is the actionable payload rather than padding.	3 / 3
Actionability	Four complete, typed, copy-paste-ready TypeScript implementations (CreditPolicyEnforcer, checkPrivacy, validateBatch, filterForExport) with full interfaces and constants, matching the 'fully executable code' anchor rather than the pseudocode score-2 case.	3 / 3
Workflow Clarity	Steps 1–4 are clearly sequenced, but this is a batch-operation skill with no validation checkpoints or validate→fix→retry feedback loops, so per the rubric's batch-operations cap it cannot score 3; it is above 1 because the sequence is present.	2 / 3
Progressive Disclosure	Sections are well-organized, but ~280 lines of full implementations live inline in SKILL.md with content that could be split into reference files, and the only pointer ('see clay-architecture-variants') references a non-existent bundle file; this matches the score-2 'content that should be separate is inline' anchor rather than the appropriately-split score-3 case.	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.

The description is specific, complete, and well-triggered: it names concrete actions, gives an explicit 'Use when' clause, and lists natural trigger phrases scoped to a distinct Clay niche. It uses third-person imperative voice with no first/second-person or vague fluff.

Dimension	Reasoning	Score
Specificity	Lists three concrete actions — 'credit spending limits', 'data privacy enforcement', and 'input validation guardrails' — matching the 'multiple specific concrete actions' anchor rather than the single-domain score-2 example.	3 / 3
Completeness	Explicitly answers what ('Implement credit spending limits...') and when ('Use when enforcing spending caps, blocking PII enrichment...') with explicit triggers, satisfying the both-what-and-when anchor; not the score-2 case where 'when' is only implied.	3 / 3
Trigger Term Quality	Provides six natural trigger phrases ('clay policy', 'clay guardrails', 'clay spending limit', 'clay data privacy rules', 'clay validation', 'clay controls') that a Clay user would plausibly say, giving good coverage; not the sparse/jargon score-2 case.	3 / 3
Distinctiveness Conflict Risk	Scoped to the distinct 'Clay pipelines' niche with clay-prefixed triggers, making conflict with unrelated skills unlikely; not the generic score-2 'Works with document files' case.	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-policy-guardrails/SKILL.md
Commit: 0540a62

Reviewed: about 18 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.