exa-policy-guardrails

Implement content policy enforcement, domain filtering, and usage guardrails for Exa. Use when setting up content safety rules, restricting search domains, or enforcing query and budget policies for Exa integrations. Trigger with phrases like "exa policy", "exa content filter", "exa guardrails", "exa domain allowlist", "exa content moderation".

Quality

85%

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

Quality

Content

82%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 content is executable, well-organized, and efficiently written, with a clear sequenced workflow and validation gates. The main gap is the absence of an explicit validate-fix-retry feedback loop for the policy-enforcement workflow, which limits workflow clarity.

Suggestions

Add an explicit feedback loop for policy violations: when validateQuery or checkQuota throws, show how to surface the error to the user and retry or adjust, rather than only throwing PolicyViolation.

Provide a concrete verification step after enforcedSearch runs (e.g., log/check that results respect includeDomains and startPublishedDate) to confirm policy enforcement took effect.

Consider extracting the large TRUSTED_SOURCES/BLOCKED_DOMAINS config and reusable classes into a referenced file to reduce inline bulk and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Largely lean code-driven content with brief, useful comments and no padding explaining what Exa is or how libraries work; the Overview's rationale sentence is justified context but could be slightly tightened, fitting 'efficient; minor instances of over-explanation'.	4 / 5
Actionability	Fully executable, copy-paste-ready TypeScript covering domain filtering, query validation, freshness, budget enforcement, and a combined function, addressing the common cases comprehensively.	5 / 5
Workflow Clarity	Five clearly sequenced steps plus an explicitly numbered combined-enforcement function with validation gates (quota check, query validation before search); minor gap is the lack of an explicit validate->fix->retry feedback loop, keeping it below a 5.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections/steps with one-level-deep pointers to sibling skills; no bundle files exist, and the cohesive inline code is appropriately structured though some code could conceivably be split out.	4 / 5
	Total	17 / 20 Passed

Description

87%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 well-structured, explicitly covering what the skill does and when to use it, with a clear Exa-specific niche and concrete trigger phrases. Minor specificity and trigger-term variation gaps keep it just below fully comprehensive.

Dimension	Reasoning	Score
Specificity	Names the Exa domain and several concrete actions ('content policy enforcement, domain filtering, and usage guardrails'), but each action is somewhat high-level rather than fully enumerated, fitting 'lists several specific actions; minor gaps in coverage'.	4 / 5
Completeness	Explicitly answers both what ('Implement content policy enforcement, domain filtering, and usage guardrails for Exa') and when ('Use when setting up content safety rules...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides good keyword coverage with natural phrases ('exa policy', 'exa content filter', 'exa guardrails', 'exa domain allowlist', 'exa content moderation'), though all share the 'exa' prefix and a few natural variations are missing.	4 / 5
Distinctiveness Conflict Risk	Targets a clear Exa-specific niche with distinct 'exa'-prefixed triggers, resulting in minimal conflict risk with other skills.	5 / 5
	Total	18 / 20 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/exa-pack/skills/exa-policy-guardrails/SKILL.md
Commit: 0540a62

Reviewed: about 20 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.