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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

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 with complete, executable TypeScript covering domain filtering, query policy, freshness, and budget enforcement in a clear step sequence. Its weaknesses are minor redundancy, validation checkpoints that stay implicit in code, and no progressive disclosure into reference files.

Suggestions

Dedupe the Resources section (both links currently point to https://docs.exa.ai/reference/search) and replace the duplicate with a genuinely distinct reference, or drop it.

Make validation checkpoints explicit in the workflow rather than buried in code — e.g., add a 'Validate query and quota before searching; on PolicyViolation, surface the reason and stop' step with a fix-and-retry note.

Consider moving the full ExaUsagePolicy class and BLOCKED_PATTERNS reference data into a separate reference file, keeping SKILL.md as a lean overview that links to the detail.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — no concept explanations Claude already knows and five distinct concrete code blocks — but it could be tightened: the two Resources links point to the identical URL and the Error Handling table restates what each step already covers.	2 / 3
Actionability	Fully executable, copy-paste-ready TypeScript with imports, class definitions, and complete functions for each policy mechanism, matching the anchor for fully executable code with specific examples.	3 / 3
Workflow Clarity	The five steps and the combined enforcedSearch function give a clear sequence, and validation exists (checkQuota, validateQuery), but checkpoints are implicit inside code rather than explicitly called out and there is no validate→fix→retry feedback loop.	2 / 3
Progressive Disclosure	Well-organized into clear sections with a Next Steps pointer to other skills, but all detail lives inline in SKILL.md with no reference files; for a ~240-line skill some of the full class implementations could be split out.	2 / 3
	Total	9 / 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 strong: it states concrete capabilities, gives an explicit 'Use when' clause, and lists natural trigger phrases scoped to Exa. Voice is imperative/third-person throughout with no first- or second-person phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'content policy enforcement, domain filtering, and usage guardrails' plus 'restricting search domains' and 'enforcing query and budget policies' — matching the anchor for several specific concrete actions.	3 / 3
Completeness	Explicitly answers what ('Implement content policy enforcement, domain filtering, and usage guardrails for Exa') and when ('Use when setting up content safety rules, restricting search domains, or enforcing query and budget policies') with an explicit trigger list.	3 / 3
Trigger Term Quality	Provides natural trigger phrases a user would say — 'exa policy', 'exa content filter', 'exa guardrails', 'exa domain allowlist', 'exa content moderation' — giving good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Clearly scoped to Exa with distinctive triggers ('exa policy', 'exa guardrails', 'exa domain allowlist'), giving it a clear niche unlikely to conflict with non-Exa skills.	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: 4 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.