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".
67
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
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.
This is a well-crafted skill description that clearly defines its scope around Exa content policy and guardrails. It excels in all dimensions by listing concrete actions, providing explicit 'Use when' and 'Trigger with' clauses, and maintaining a distinct niche through Exa-specific terminology. The third-person voice is used correctly throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'content policy enforcement', 'domain filtering', and 'usage guardrails'. Also mentions specific sub-actions like 'restricting search domains' and 'enforcing query and budget policies'. | 3 / 3 |
Completeness | Clearly answers both 'what' (implement content policy enforcement, domain filtering, usage guardrails for Exa) and 'when' (explicit 'Use when' clause with specific scenarios, plus a 'Trigger with phrases' section). | 3 / 3 |
Trigger Term Quality | Includes a rich set of natural trigger terms explicitly listed: 'exa policy', 'exa content filter', 'exa guardrails', 'exa domain allowlist', 'exa content moderation'. These are terms users would naturally use when needing this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific 'Exa' product scoping combined with the policy/guardrails niche. The trigger terms are all prefixed with 'exa', making conflicts with other skills very unlikely. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with fully executable TypeScript code covering multiple policy enforcement dimensions for Exa integrations. Its main weaknesses are the lack of explicit validation/verification steps in the workflow (e.g., testing that policies work as expected, logging enforcement decisions) and the somewhat monolithic structure that could benefit from splitting detailed implementations into supporting files. The content is mostly efficient but could be tightened in places.
Suggestions
Add explicit validation checkpoints — e.g., a step to test blocked patterns against sample queries, or a logging/audit mechanism to verify policy enforcement is working correctly before deploying.
Consider splitting the detailed class implementations (ExaUsagePolicy, full domain lists) into bundle reference files, keeping SKILL.md as a concise overview with key patterns and pointers to details.
Add a brief testing/verification section showing how to confirm policies are correctly blocking/allowing expected queries and domains.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary verbosity. The overview paragraph explaining what Exa does and why results may be unreliable is somewhat redundant context. The code examples are mostly lean, though the per-user budget enforcement section is quite lengthy for what it accomplishes. Some inline comments are helpful but others state the obvious. | 2 / 3 |
Actionability | All code examples are fully executable TypeScript with proper imports, concrete domain lists, regex patterns, and complete function implementations. The combined enforcement function in Step 5 ties everything together in a copy-paste ready manner. The error handling table maps specific issues to concrete solutions. | 3 / 3 |
Workflow Clarity | The steps are clearly sequenced from individual policy components (Steps 1-4) to combined enforcement (Step 5), which is a logical progression. However, there are no explicit validation checkpoints or feedback loops — for example, no guidance on testing whether blocked patterns work correctly, no logging/auditing step to verify policy enforcement is functioning, and no error recovery guidance beyond the error table. | 2 / 3 |
Progressive Disclosure | The skill references `exa-architecture-variants` and `exa-cost-tuning` in Next Steps, and links to Exa docs, which is good. However, the content is quite long (~150 lines of code) and could benefit from splitting detailed implementations (e.g., the full budget enforcement class) into separate reference files while keeping the SKILL.md as a concise overview. No bundle files exist to support progressive disclosure. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
a04d1a2
- Reviewed
Table of Contents
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.