instantly-performance-tuning

Optimize Instantly.ai API performance with caching, batching, and connection pooling. Use when experiencing slow API responses, implementing caching strategies, or optimizing high-volume lead operations. Trigger with phrases like "instantly performance", "instantly slow", "instantly caching", "instantly batch", "optimize instantly api".

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.

The body is highly actionable and concise, dominated by complete executable TypeScript across five well-sequenced optimization steps. It loses points on workflow clarity (no verification checkpoint for the batch operation) and progressive disclosure (full implementations inline with no bundled reference files).

Suggestions

Add an explicit validation/verification checkpoint after the batch lead import — e.g., confirm created leads via a follow-up list call and re-drive the failed-items queue with a validate→fix→retry feedback loop.

Extract the full class implementations (InstantlyCache, ThrottledEmailClient, batching/pagination helpers) into files under references/ or scripts/, keeping SKILL.md an overview with focused snippets and clearly signaled links, so progressive disclosure is one level deep.

Dimension	Reasoning	Score
Conciseness	The body is lean and code-driven — five executable TypeScript blocks with prose limited to justifying TTL/concurrency choices (e.g., '5-15 minutes', 'leave margin') rather than explaining concepts Claude already knows; not 2 because no padding or beginner-level exposition is present.	3 / 3
Actionability	Each step ships complete, copy-paste-ready executable code (cache class, batching with retries, async-generator pagination, undici pool, throttled client) with specific parameter values; not 2 because nothing is pseudocode or missing key details.	3 / 3
Workflow Clarity	Steps are clearly sequenced (Step 1–5) but the batch lead operation in Step 2 has only 429-retry logic and a failed-items array, with no explicit validation/verification checkpoint confirming leads were actually created; per the rubric this caps batch-operation workflow clarity at 2 rather than 3.	2 / 3
Progressive Disclosure	Content is well-sectioned but ~260 lines of full class implementations live inline in SKILL.md with no references/, scripts/, or assets/ bundle to offload them — matching the anchor where material that could be a separate file is kept inline; not 3 because there are no one-level-deep references to split the detail out.	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.

The description is third-person, concrete, and complete, naming the domain and three specific optimization techniques alongside an explicit 'Use when' clause and natural trigger phrases. It is distinctive to the Instantly.ai niche and free of fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'caching, batching, and connection pooling' on a named domain (Instantly.ai API performance) — matching the multiple-specific-actions anchor; not 2 because the technique set is comprehensive rather than partial.	3 / 3
Completeness	Explicitly answers both 'what' ('Optimize Instantly.ai API performance with caching, batching, and connection pooling') and 'when' via an explicit 'Use when...' clause plus trigger phrases; not 2 because the when-trigger is explicit, not merely implied.	3 / 3
Trigger Term Quality	Provides natural phrases a user would say — 'instantly performance', 'instantly slow', 'instantly caching', 'instantly batch', 'optimize instantly api' — giving good coverage of likely variations; not 2 because several natural phrasings are supplied rather than a single keyword.	3 / 3
Distinctiveness Conflict Risk	Tightly scoped to the Instantly.ai niche with distinct 'instantly'-prefixed triggers, making false-positive activation against other skills unlikely; not 2 because the domain and triggers are uniquely identifying.	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: 1628598

Reviewed: 11 minutes 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.