instantly-reference-architecture

Implement Instantly.ai reference architecture with best-practice project layout. Use when designing new Instantly integrations, planning multi-campaign systems, or building an outreach automation platform. Trigger with phrases like "instantly architecture", "instantly project structure", "instantly reference design", "instantly system design", "instantly integration layout".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

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

A thorough, highly actionable reference architecture with executable code and clear structure. Its main weaknesses are inline-heavy content that bypasses progressive disclosure and missing validation checkpoints for batch workflows.

Suggestions

Move the full InstantlyClient and SEQUENCE_TEMPLATES implementations into referenced files (e.g. references/client.ts, references/templates.ts) and keep SKILL.md as a lean overview with signaled links.

Add an explicit validation checkpoint to the lead-import / campaign-activation flow (e.g., verify list counts and API scopes before activating, retry-on-failure loop) to lift workflow clarity.

Trim the inline code to illustrative snippets and point to the full implementations, improving token efficiency without losing actionability.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (no over-explanation of concepts Claude knows), but full inline implementations such as the entire InstantlyClient class and SEQUENCE_TEMPLATES object could be tightened or moved out, leaning toward verbosity.	2 / 3
Actionability	Provides complete, executable TypeScript (full API client with retry/auth, campaign/lead/account/webhook namespaces, and template definitions) plus a concrete project layout and data-flow diagram — copy-paste ready.	3 / 3
Workflow Clarity	A data-flow summary and error-handling table give a loose sequence, but batch operations like lead import lack explicit validation checkpoints or feedback loops, capping workflow clarity at 2.	2 / 3
Progressive Disclosure	Sections are well organized, but all substantial content (full client and template implementations) lives inline in SKILL.md with no bundle files to offload detail to; content that should be separate is inline.	2 / 3
	Total	9 / 12 Passed

Description

90%

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-formed description that clearly states purpose, use conditions, and natural trigger phrases in third person. It is slightly light on enumerating concrete capabilities, but otherwise strong.

Suggestions

Expand the capability statement to list a few concrete actions (e.g., 'design API clients, wire webhook handlers, lay out campaign and lead modules') to lift specificity to level 3.

Dimension	Reasoning	Score
Specificity	Names the domain and a couple of actions ('Implement Instantly.ai reference architecture', 'best-practice project layout') but does not enumerate multiple distinct concrete capabilities, so it stops short of the level-3 anchor.	2 / 3
Completeness	Explicitly answers what ('Implement Instantly.ai reference architecture with best-practice project layout') and when ('Use when designing new Instantly integrations, planning multi-campaign systems, or building an outreach automation platform') with explicit triggers.	3 / 3
Trigger Term Quality	Lists natural trigger phrases a user would plausibly say ('instantly architecture', 'instantly project structure', 'instantly reference design', 'instantly system design', 'instantly integration layout'), giving good coverage of variations.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to Instantly.ai architecture with distinctive triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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: 4 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.