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".
80
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/fireflies-pack/skills/fireflies-reference-architecture/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description with excellent completeness and distinctiveness, clearly scoped to Fireflies.ai meeting intelligence architecture. Its main weakness is that the capabilities described are somewhat abstract ('design architecture') rather than listing concrete actions the skill enables. The trigger terms are well-chosen and cover natural user language.
Suggestions
Replace the abstract 'design meeting intelligence architecture' with more concrete actions like 'query transcripts via GraphQL, configure webhook listeners, map meeting data to CRM fields, and structure transcript processing pipelines'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Fireflies.ai) and some technologies (GraphQL API, webhooks, CRM sync), but the actions are vague — 'design meeting intelligence architecture' is abstract rather than listing concrete actions like 'query transcripts', 'configure webhook endpoints', or 'map CRM fields'. | 2 / 3 |
Completeness | Clearly answers both 'what' (design meeting intelligence architecture with Fireflies.ai GraphQL API, webhooks, CRM sync) and 'when' (explicit 'Use when' clause with triggers for designing integrations, planning transcript pipelines, establishing architecture, plus explicit trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes explicit trigger phrases like 'fireflies architecture', 'fireflies design', 'fireflies project structure', 'meeting intelligence pipeline', plus natural terms like 'transcript pipelines', 'meeting analytics platforms', 'GraphQL API', 'webhooks', and 'CRM sync' — good coverage of terms a user would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — the combination of Fireflies.ai, GraphQL API, meeting intelligence, and transcript pipelines creates a very specific niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid architecture reference with highly actionable, executable TypeScript code covering the full Fireflies.ai integration pipeline. Its main weaknesses are verbosity (too much inline implementation detail for a SKILL.md overview) and missing explicit validation/verification steps in the processing workflow. The content would benefit from being restructured as a concise overview with references to detailed implementation files.
Suggestions
Move detailed service implementations (transcript-store, action-items, analytics, upload) into separate referenced files and keep only the GraphQL client and webhook processor in the main SKILL.md as the core pattern.
Add explicit validation checkpoints to the webhook processing workflow, e.g., verify transcript exists before processing, validate schema before DB upsert, and include a retry/feedback loop for failed steps.
Trim explanatory comments in code that Claude can infer (e.g., '// Store in your database', '// Process in parallel') to reduce token usage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some verbose sections—the full TypeScript implementations for storage, action items, and analytics could be trimmed since Claude can infer these patterns. The architecture diagram and error table are efficient, but the overall length (~200 lines of code) is heavy for an architecture reference. | 2 / 3 |
Actionability | Provides fully executable TypeScript code for every component: GraphQL client, webhook processor, transcript storage, action item sync, analytics, and audio upload. Code is copy-paste ready with real API endpoints, proper headers, and concrete query structures. | 3 / 3 |
Workflow Clarity | The architecture diagram shows the event flow clearly, and the webhook processor outlines the sequence (verify → ACK → queue → process). However, there are no explicit validation checkpoints or error recovery feedback loops in the processing pipeline—the error handling table lists issues but doesn't integrate verification steps into the workflow itself. | 2 / 3 |
Progressive Disclosure | The content has good section structure and a project layout reference, but it's largely monolithic—all implementation details are inline rather than split into referenced files. The external links at the bottom are helpful, but the bulk of code could be better organized with references to separate detailed files for each service. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
c8a915c
- Reviewed
Table of Contents
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.