exa-sdk-patterns

Apply production-ready exa-js SDK patterns with type safety, singletons, and wrappers. Use when implementing Exa integrations, refactoring SDK usage, or establishing team coding standards for Exa. Trigger with phrases like "exa SDK patterns", "exa best practices", "exa code patterns", "idiomatic exa", "exa wrapper".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A strong, actionable pattern library: executable code throughout, a clear build sequence with embedded validation and retry patterns, and no wasted prose. The main weakness is that ~250 lines of code live entirely inline in SKILL.md with no bundle files for progressive disclosure.

Suggestions

Move the five TypeScript file templates (client.ts, search.ts, safe.ts, retry.ts, validate.ts) into a scripts/ or references/ bundle and have SKILL.md summarize each pattern with a link, keeping the overview shallow.

Add a short 'Quick start' section at the top showing the combined resilientSearch() example so the most common usage is reachable without reading all five steps.

Replace the inline '## Error Handling' summary table with a pointer to a reference doc once the code is externalized, to avoid duplicating the patterns already shown in the code blocks.

Dimension	Reasoning	Score
Conciseness	The body is lean: a tight overview, a prerequisites list, and dense executable code with no padding explaining basics Claude already knows (e.g., no 'what a singleton is' filler). Every section earns its tokens.	3 / 3
Actionability	Each of the five steps ships complete, copy-paste-ready TypeScript with imports, typed interfaces, and usage comments — fully executable rather than pseudocode.	3 / 3
Workflow Clarity	Steps 1–5 are logically sequenced (client → typed wrapper → safe wrapper → retry → validation), each importing from the prior, and embed error-recovery (retry/backoff) and validation (Zod) patterns; the 'Combined' example shows composition. This is not a destructive/batch workflow, so the missing-checkpoint cap does not apply.	3 / 3
Progressive Disclosure	Sections are well-organized, but all five full TypeScript files are inlined in SKILL.md with no references/, scripts/, or assets/ bundle to offload them into — matching the anchor where content that could be separate stays inline. Not a 1 because organization is clear and there are no nested/dead references; not a 3 because there is no one-level-deep reference structure.	2 / 3
	Total	11 / 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.

A well-crafted description that concretely states capabilities, gives an explicit 'Use when' trigger, and lists natural trigger phrases scoped to a clear niche. It uses the imperative voice seen in the good examples rather than first/second person, so no voice penalty applies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'type safety, singletons, and wrappers' — rather than vague abstractions, matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers what ('Apply production-ready exa-js SDK patterns with type safety, singletons, and wrappers') and when ('Use when implementing Exa integrations, refactoring SDK usage, or establishing team coding standards'), with explicit trigger guidance.	3 / 3
Trigger Term Quality	'Trigger with phrases like "exa SDK patterns", "exa best practices", "exa code patterns", "idiomatic exa", "exa wrapper"' gives good coverage of natural terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Scoped to the exa-js SDK niche with distinct 'exa'-prefixed triggers, making it unlikely to fire for unrelated 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: 6e3a65f

Reviewed: 5 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.