fireflies-reference-architecture

Design meeting intelligence architecture with Fireflies.ai GraphQL API, webhooks, and CRM sync. Use when designing new integrations, planning transcript pipelines, or establishing architecture for meeting analytics platforms. Trigger with phrases like "fireflies architecture", "fireflies design", "fireflies project structure", "meeting intelligence pipeline".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

50%

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

A well-structured, code-first reference architecture that is genuinely useful, but it is monolithic with minor redundancy, a few stubbed helpers, and no validation feedback loops or bundle-file offloading. Tightening these would lift it from adequate to strong.

Suggestions

Remove or merge the redundant "Output" section, which restates the Overview and component list already covered above.

Add an explicit validation/idempotency feedback loop for the webhook→process→CRM-sync pipeline (e.g., verify signature → process → confirm upsert/sync success → retry on failure) to satisfy the workflow-clarity anchor for batch operations.

Move the full GraphQL query fields and TypeScript interfaces into reference files under references/ (e.g., GRAPHQL.md, types/fireflies.ts) and link to them from the body to improve progressive disclosure and reduce inline bulk.

Dimension	Reasoning	Score
Conciseness	Mostly lean and code-first, but the "Output" section restates the Overview ("Event-driven architecture with webhook-triggered processing", "Transcript storage with search-ready schema") and the Project Layout partially duplicates the code-section file comments, so it could be tightened.	2 / 3
Actionability	Provides concrete, largely executable TypeScript for all six components, but undefined helpers (avgSentiment, db.meetings, taskManager) keep it from being fully copy-paste ready as the anchor-3 example demands.	2 / 3
Workflow Clarity	Components are clearly sequenced (numbered 1-6, webhook flow diagram, 3-step receiver list), but there is no explicit validate→fix→retry feedback loop for the batch/CRM-sync/DB-upsert pipeline, capping the score at 2 per the rubric guideline.	2 / 3
Progressive Disclosure	Sections are well-organized, but the body is a ~280-line monolith with all code inline and no bundle files (references/scripts/assets absent); the GraphQL query reference and type definitions are content that could be split into separate reference files.	2 / 3
	Total	8 / 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, third-person description that clearly states concrete capabilities and pairs them with an explicit "Use when" clause and multiple natural trigger phrases. It is specific, complete, and unlikely to conflict with sibling skills.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete capabilities — "Design meeting intelligence architecture with Fireflies.ai GraphQL API, webhooks, and CRM sync" — listing specific technologies rather than vague actions.	3 / 3
Completeness	Explicitly answers both what ("Design meeting intelligence architecture with...GraphQL API, webhooks, and CRM sync") and when ("Use when designing new integrations, planning transcript pipelines, or establishing architecture...") with explicit triggers.	3 / 3
Trigger Term Quality	Provides four explicit trigger phrases ("fireflies architecture", "fireflies design", "fireflies project structure", "meeting intelligence pipeline") that a user would plausibly say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	Targets a narrow, well-defined niche (Fireflies.ai meeting intelligence architecture) with distinct triggers, making conflict with other skills unlikely.	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: 2 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.