exa-rate-limits

Implement Exa rate limiting, exponential backoff, and request queuing. Use when handling 429 errors, implementing retry logic, or optimizing API request throughput for Exa. Trigger with phrases like "exa rate limit", "exa throttling", "exa 429", "exa retry", "exa backoff", "exa QPS".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

80%

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

A code-dense, highly actionable skill body that stays lean and assumes competence. Its weaknesses are structural: batch workflows lack explicit validation checkpoints, and a 200-line single file does not split detailed techniques into referenced bundle files.

Suggestions

Add an explicit validation/verification checkpoint to the batch workflows (e.g., after processBatch, confirm all queries succeeded and report/log any partial failures before proceeding), which would lift workflow_clarity.

Move the longer technique implementations (adaptive rate limiter, batch processing) into reference files under references/ and keep SKILL.md as an overview plus a quick-start snippet, with clearly signaled one-level-deep links, to improve progressive_disclosure.

Remove or fold the Examples "Simple Retry Wrapper" into Step 1, since it duplicates the withBackoff pattern, to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely executable TypeScript with minimal prose and no explanations of concepts Claude already knows; comments are purposeful. Not a 2 because there is no padded or generic explanatory text, though the Examples "Simple Retry Wrapper" lightly duplicates Step 1.	3 / 3
Actionability	Complete, copy-paste-ready code blocks with real imports and concrete config (e.g. PQueue with intervalCap: 10 matching Exa's QPS limit), covering backoff, queuing, adaptive limiting, and batching.	3 / 3
Workflow Clarity	Steps are clearly sequenced (Step 1–4), but the batch operations (processBatch, batchSearch) lack explicit validation/verification checkpoints, which the rubric caps at 2. Not a 3 because no verify-then-proceed feedback loop is given for batch runs; not a 1 because the sequence and error-handling table are present.	2 / 3
Progressive Disclosure	A single ~200-line file with zero bundle files; all four code techniques are inline rather than split into one-level-deep references. Not a 1 because sections are well organized (not a wall of text) with no nested references; not a 3 because content that could be separate remains inline for a skill over 50 lines.	2 / 3
	Total	10 / 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 strong description: concrete actions, an explicit Use-when clause, and a focused set of natural trigger phrases scoped to Exa. It clearly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Implement Exa rate limiting, exponential backoff, and request queuing" — matching the multi-action anchor. Voice is imperative/third person (no "I"/"you"), so no voice penalty.	3 / 3
Completeness	Explicitly answers both what (implement rate limiting, backoff, queuing) and when ("Use when handling 429 errors, implementing retry logic, or optimizing API request throughput for Exa"), with an explicit Use-when clause.	3 / 3
Trigger Term Quality	Provides good coverage of natural terms users would say: "exa rate limit", "exa throttling", "exa 429", "exa retry", "exa backoff", "exa QPS", with common variations present.	3 / 3
Distinctiveness Conflict Risk	Scoped narrowly to the Exa API with all triggers "exa"-prefixed, giving a clear niche 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: 02d6341

Reviewed: about 15 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.