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

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

71%Weight 40%Scale 1-5

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

The body is actionable and well-sequenced with executable TypeScript examples and validation checkpoints, but it inlines substantial per-service code and API detail that would be better placed in separate reference files, weakening progressive disclosure.

Suggestions

Move the six per-service TypeScript implementations into reference files (e.g. references/webhook-processor.md, references/transcript-store.md) and keep SKILL.md as an overview with one-level-deep links, to improve progressive_disclosure.

Define or stub the undefined helpers (db, taskManager, avgSentiment) so the code examples are fully executable end-to-end, raising actionability.

Add an explicit retry/backoff feedback loop for webhook and rate-limited batch processing (validate -> backoff -> retry) to strengthen workflow_clarity checkpoints.

Dimension	Reasoning	Score
Conciseness	No padded explanation of known concepts; jumps to an architecture diagram and code, but ~280 lines with six full TypeScript blocks is more than lean and some blocks repeat similar GraphQL query patterns.	4 / 5
Actionability	Six concrete, mostly copy-paste-ready TypeScript implementations plus an error-handling table, but helpers like db, taskManager, and avgSentiment are referenced but undefined, leaving minor execution gaps.	4 / 5
Workflow Clarity	The architecture diagram and numbered Core Components give a clear webhook-to-processing sequence with validation checkpoints (HMAC verify, ACK 200, idempotency key, rate-limit queue, duration check); minor gaps in explicit retry/backoff feedback loops.	4 / 5
Progressive Disclosure	No bundle/reference files exist; all six service implementations and API details are inlined in SKILL.md rather than split into one-level-deep reference files, though section structure and external doc links provide some organization.	3 / 5
	Total	15 / 20 Passed

Description

100%Weight 40%Scale 1-5

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 strong: it states concrete capabilities, gives explicit 'Use when' trigger guidance with natural phrases, and occupies a clear niche. It is a model of the 'what AND when with concrete triggers' anchor.

Dimension	Reasoning	Score
Specificity	Names the meeting-intelligence domain and multiple concrete components (GraphQL API, webhooks, CRM sync, transcript pipelines, analytics), giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (design architecture with Fireflies GraphQL API, webhooks, CRM sync) and 'when' (Use when designing integrations, planning transcript pipelines, establishing meeting analytics architecture) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides multiple natural trigger phrases ('fireflies architecture', 'fireflies design', 'fireflies project structure', 'meeting intelligence pipeline') plus a 'Use when' clause covering common situations.	5 / 5
Distinctiveness Conflict Risk	Fireflies.ai plus meeting-intelligence niche with dedicated trigger phrases gives a clear, distinct niche with minimal overlap risk against other skills.	5 / 5
	Total	20 / 20 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/fireflies-pack/skills/fireflies-reference-architecture/SKILL.md
Commit: 0540a62

Reviewed: about 3 hours 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.