apollo-reference-architecture

Implement Apollo.io reference architecture. Use when designing Apollo integrations, establishing patterns, or building production-grade sales intelligence systems. Trigger with phrases like "apollo architecture", "apollo system design", "apollo integration patterns", "apollo best practices architecture".

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

80%Weight 40%Scale 1-3

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

A dense, highly actionable reference architecture with executable code throughout and excellent token efficiency. It loses points on workflow clarity (no explicit validation/feedback checkpoints) and progressive disclosure (an available reference file is never linked from the body).

Suggestions

Add explicit validation checkpoints and a validate-fix-retry loop to the build/deploy workflow — e.g. a step that runs a request against a sandbox Apollo key and fails fast before bulk enrichment.

Link references/implementation-guide.md from the body with a clearly signaled 'See [implementation-guide.md](references/implementation-guide.md) for full setup' so the inline architecture can stay a lean overview.

Move the Prisma schema comment block and TypeORM entity duplication into the reference file to reduce body length while keeping SKILL.md an overview.

Dimension	Reasoning	Score
Conciseness	Lean throughout: each section jumps straight to executable TypeScript with file-path headers and no padding explaining what Node, BullMQ, or Prisma are; every section earns its tokens.	3 / 3
Actionability	Provides complete, copy-paste-ready code for services, jobs, models, and routes with real Apollo endpoints, correct snake_case payloads, and concrete config values, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Steps are sequenced (diagram → services → jobs → data → routes) but the build-and-deploy path has no explicit validation checkpoints or feedback loops; the error-handling table describes strategy but no validate-fix-retry loop, so checkpoints are only implicit.	2 / 3
Progressive Disclosure	A bundled references/implementation-guide.md exists but the body never signals or links it; nearly all detail is inline in a single ~270-line SKILL.md, so structure is present but content that should be split out is not clearly separated.	2 / 3
	Total	10 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 specific, complete, and distinctive description that clearly states capabilities and explicit triggers. The only soft spot is trigger-term naturalness, where the listed phrases skew formal rather than colloquial.

Suggestions

Add shorter, more natural trigger phrasings a user might actually type (e.g. 'apollo integration', 'apollo.io setup', 'apollo sales intelligence') alongside the current formal ones.

Trim the multi-line padding inside the description to a tighter single paragraph; the extra blank lines add noise without aiding discoverability.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Implement Apollo.io reference architecture', 'designing Apollo integrations', 'establishing patterns', 'building production-grade sales intelligence systems' — matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ('Implement Apollo.io reference architecture') and when ('Use when designing Apollo integrations...'), with an explicit 'Use when' clause and named triggers, matching the top anchor.	3 / 3
Trigger Term Quality	Provides several trigger phrases ('apollo architecture', 'apollo system design', 'apollo integration patterns', 'apollo best practices architecture') but these are somewhat formal/technical and lack the common natural variations a user might actually say; missing shorter everyday phrasings.	2 / 3
Distinctiveness Conflict Risk	Clearly scoped to Apollo.io reference architecture with distinct Apollo-specific 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
Path: plugins/saas-packs/apollo-pack/skills/apollo-reference-architecture/SKILL.md
Commit: 399d94c

Reviewed: 3 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.