exa-load-scale

Implement Exa load testing, capacity planning, and scaling strategies. Use when running performance tests, planning capacity for Exa integrations, or designing high-throughput search architectures. Trigger with phrases like "exa load test", "exa scale", "exa capacity", "exa k6", "exa benchmark", "exa throughput".

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.

An actionable, concise skill body with executable examples and clear sequencing, weakened by missing validation checkpoints in the batch/load-test workflow and an all-inline structure with no progressive file references.

Suggestions

Add an explicit validation gate between steps, e.g. after the k6 run, instruct Claude to verify thresholds (p95<3000, error rate<5%) passed before interpreting results or proceeding to capacity planning.

Move the full k6 load-test script and/or capacity calculator into a `references/` or `scripts/` file and reference it one level deep, keeping SKILL.md as a lean overview.

Add a short feedback loop for 429/timeout errors encountered during the load test (detect → reduce concurrency or switch search type → re-run), mirroring the error-handling table as workflow steps.

Dimension	Reasoning	Score
Conciseness	Lean body of tables and executable code with minimal prose; the few explanatory notes (e.g., the 10 QPS limit) convey Exa-specific facts Claude would not assume, so tokens earn their place rather than restating known concepts.	3 / 3
Actionability	Provides complete, copy-paste-ready artifacts — a runnable k6 script with `k6 run --env ...`, a TypeScript PQueue implementation, caching code, and a capacity calculator — rather than vague or pseudocode direction.	3 / 3
Workflow Clarity	Steps 1–4 are sequenced, but the batch/load-test workflow has no explicit validation checkpoints (e.g., confirm k6 thresholds passed before scaling decisions), which caps batch-operation workflows at 2 per the rubric rather than the score-3 feedback-loop anchor.	2 / 3
Progressive Disclosure	Well-sectioned single file with no nested references, but sizable inline code (the k6 script, capacity calculator) that could be split into reference files is kept inline and no bundle files are provided, fitting the 'content that should be separate is inline' anchor better than the one-level-deep-reference anchor.	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, explicit trigger guidance, natural keywords, and a distinct Exa-scoped niche. It uses third-person voice and avoids vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "load testing, capacity planning, and scaling strategies" — tied to the Exa domain, matching the multiple-specific-actions anchor rather than the partial score-2 example.	3 / 3
Completeness	Explicitly answers both what ("Implement Exa load testing, capacity planning, and scaling strategies") and when ("Use when running performance tests..." plus a "Trigger with phrases like..." clause), matching the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Provides good coverage of natural user phrases ("exa load test", "exa scale", "exa capacity", "exa k6", "exa benchmark", "exa throughput") that a user would naturally say; not merely technical jargon.	3 / 3
Distinctiveness Conflict Risk	The Exa-specific scope and "exa"-prefixed triggers carve a clear niche unlikely to fire for unrelated skills, matching the clear-niche anchor.	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: 1 day 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.