FI

fireflies-cost-tuning

Provides tools and metrics to audit seat utilization, reduce unused licenses, and optimize subscription costs for Fireflies.ai.

Install

mkdir -p .claude/skills/fireflies-cost-tuning && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/3830" && unzip -o skill.zip -d .claude/skills/fireflies-cost-tuning && rm skill.zip

Installs to .claude/skills/fireflies-cost-tuning

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Optimize Fireflies.ai subscription costs through seat auditing, selective
73 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Audit seat utilization via API
  • Configure selective recording policies
  • Manage storage by deleting old transcripts
  • Right-size subscription plans
  • Optimize API requests by caching
  • Identify inactive seats for potential removal

How it works

The skill uses API calls to audit user activity and storage, then applies documented strategies for selective recording and plan selection. It also provides methods for caching API requests to stay within daily limits.

Inputs & outputs

You give it
Fireflies.ai API key and usage data
You get back
Seat utilization report, recording policy, storage audit, and plan recommendation

When to use fireflies-cost-tuning

  • Audit seat utilization via API
  • Monitor transcript usage counts
  • Analyze per-seat cost efficiency
  • Right-size subscription tier based on activity

About this skill

Fireflies.ai Cost Tuning

Overview

Optimize Fireflies.ai subscription costs. Fireflies charges per-seat per month. The main levers: remove unused seats, configure selective recording, manage storage, and right-size your plan tier.

Pricing Reference

PlanPriceAPI AccessKey Features
Free$050 req/day800 min storage, limited transcription
Pro~$18/seat/month50 req/day8,000 min/seat, AI summaries
Business~$29/seat/month60 req/minUnlimited transcription, CRM, analytics
EnterpriseCustom60 req/minSSO, Super Admin webhooks, custom

Instructions

Step 1: Audit Seat Utilization via API

set -euo pipefail
# List all workspace users with their transcript counts
curl -s -X POST https://api.fireflies.ai/graphql \
  -H "Authorization: Bearer $FIREFLIES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "{ users { name email user_id num_transcripts minutes_consumed } }"}' \
  | jq '.data.users | sort_by(.num_transcripts) | .[] | {name, email, transcripts: .num_transcripts, minutes: .minutes_consumed}'
// Automated utilization report
async function seatUtilizationReport() {
  const data = await firefliesQuery(`{
    users {
      name email user_id
      num_transcripts minutes_consumed
      recent_meeting
    }
  }`);

  const users = data.users;
  const inactive = users.filter((u: any) => u.num_transcripts < 2);
  const active = users.filter((u: any) => u.num_transcripts >= 2);

  console.log(`Total seats: ${users.length}`);
  console.log(`Active (2+ transcripts): ${active.length}`);
  console.log(`Inactive (<2 transcripts): ${inactive.length}`);
  console.log(`Potential savings: ${inactive.length} seats * $29/mo = $${inactive.length * 29}/mo`);

  if (inactive.length > 0) {
    console.log("\nInactive seats to review:");
    for (const u of inactive) {
      console.log(`  ${u.email}: ${u.num_transcripts} transcripts, last meeting: ${u.recent_meeting || "never"}`);
    }
  }

  return { total: users.length, active: active.length, inactive, savings: inactive.length * 29 };
}

Step 2: Configure Selective Recording

Instead of recording every meeting, configure auto-join rules in Fireflies Settings > Auto-Join:

# Recommended recording policy
record_always:
  - External meetings (client/prospect calls)
  - Meetings with 3+ participants
  - Meetings with keywords: "review", "planning", "standup", "demo"

skip_recording:
  - 1-on-1 informal chats
  - Social events
  - Meetings shorter than 5 minutes
  - Recurring "lunch" or "coffee" meetings

Estimated savings: Teams recording every meeting typically waste 30-50% of transcription credits on low-value meetings.

Step 3: Manage Storage to Avoid Forced Upgrades

// Check storage and clean up old transcripts
async function storageAudit() {
  const data = await firefliesQuery(`{
    transcripts(limit: 100) {
      id title date duration
    }
    user { minutes_consumed }
  }`);

  const now = Date.now();
  const transcripts = data.transcripts;

  // Find transcripts older than 90 days
  const old = transcripts.filter((t: any) => {
    const age = (now - new Date(t.date).getTime()) / 86400000;
    return age > 90;
  });

  console.log(`Total transcripts: ${transcripts.length}`);
  console.log(`Older than 90 days: ${old.length}`);
  console.log(`Minutes consumed: ${data.user.minutes_consumed}`);

  return { total: transcripts.length, old, minutesUsed: data.user.minutes_consumed };
}

// Delete old transcripts to free storage
async function deleteOldTranscripts(ids: string[]) {
  for (const id of ids) {
    await firefliesQuery(`
      mutation($id: String!) {
        deleteTranscript(transcript_id: $id)
      }
    `, { id });
    console.log(`Deleted: ${id}`);
    // deleteTranscript is rate limited: 10/min
    await new Promise(r => setTimeout(r, 6500));
  }
}

Step 4: Right-Size Your Plan

# Decision matrix
choose_pro:
  when:
    - Team averages <15 meetings/week per person
    - No CRM integration needed
    - Basic AI summaries sufficient
  saves: $11/seat/month vs Business

choose_business:
  when:
    - Sales team recording every call
    - CRM integration required (Salesforce, HubSpot)
    - Meeting analytics dashboards needed
    - 20+ meetings/week per person

choose_enterprise:
  when:
    - SSO/SAML required
    - Super Admin webhooks needed (org-wide meeting data)
    - Custom data retention policies
    - Dedicated support

Step 5: API Cost Optimization

// Free/Pro plans: 50 requests/day. Make every request count.
// Strategy: Fetch meeting list once, cache aggressively

async function efficientDailySync() {
  // One request: get all recent transcripts
  const data = await firefliesQuery(`{
    transcripts(limit: 50) {
      id title date duration
      summary { overview action_items }
    }
  }`);

  // Process locally -- no additional API calls
  const today = new Date().toDateString();
  const todaysMeetings = data.transcripts.filter(
    (t: any) => new Date(t.date).toDateString() === today
  );

  console.log(`Today's meetings: ${todaysMeetings.length}`);
  console.log(`API requests used: 1 of 50 daily budget`);

  return todaysMeetings;
}

Cost Savings Summary

LeverTypical Savings
Remove inactive seats$29/seat/month
Selective recording30-50% fewer transcriptions
Pro vs Business downgrade$11/seat/month
Storage cleanupAvoid forced tier upgrade
API request cachingStay within Free/Pro limits

Error Handling

IssueCauseSolution
Can't remove seatUser has admin roleReassign admin first
Storage limit warningToo many transcriptsDelete old transcripts
API daily limit hitFree/Pro 50 req/dayCache results, batch efficiently
Unexpected invoice increaseAuto-provisioned membersDisable auto-provisioning

Output

  • Seat utilization report with inactive members identified
  • Selective recording policy configured
  • Storage audit with cleanup recommendations
  • Plan right-sizing recommendation

Resources

Next Steps

For architecture design, see fireflies-reference-architecture.

When not to use it

  • When the goal is to increase Fireflies.ai usage
  • When Fireflies.ai costs are not a concern
  • When not using Fireflies.ai

Limitations

  • Cannot remove seats if the user has an admin role without reassigning admin first
  • DeleteTranscript is rate limited to 10 requests per minute
  • Free/Pro plans have a daily API request limit of 50

How it compares

This skill automates the analysis of Fireflies.ai usage and provides concrete steps for cost reduction, unlike manual billing reviews.

Compared to similar skills

fireflies-cost-tuning side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
fireflies-cost-tuning (this skill)127dReviewIntermediate
korean-public-data-api59moNo flagsIntermediate
apollo-data-handling127dCautionIntermediate
azure-ai-contentunderstanding-py129dReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

More by jeremylongshore

View all by jeremylongshore

analyzing-logs

jeremylongshore

Analyze application logs to detect performance issues, identify error patterns, and improve stability by extracting key insights.

14123

ollama-setup

jeremylongshore

Configure auto-configure Ollama when user needs local LLM deployment, free AI alternatives, or wants to eliminate hosted API costs. Trigger phrases: "install ollama", "local AI", "free LLM", "self-hosted AI", "replace OpenAI", "no API costs". Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

1167

backtesting-trading-strategies

jeremylongshore

Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".

1071

generating-database-seed-data

jeremylongshore

Process this skill enables AI assistant to generate realistic test data and database seed scripts for development and testing environments. it uses faker libraries to create realistic data, maintains relational integrity, and allows configurable data volumes. u... Use when working with databases or data models. Trigger with phrases like 'database', 'query', or 'schema'.

1033

cursor-codebase-indexing

jeremylongshore

Execute set up and optimize Cursor codebase indexing. Triggers on "cursor index setup", "codebase indexing", "index codebase", "cursor semantic search". Use when working with cursor codebase indexing functionality. Trigger with phrases like "cursor codebase indexing", "cursor indexing", "cursor".

885

testing-mobile-apps

jeremylongshore

Execute mobile app testing on iOS and Android devices/simulators. Use when performing specialized testing. Trigger with phrases like "test mobile app", "run iOS tests", or "validate Android functionality".

810

You might also like

korean-public-data-api

swszz

Extract API request/response schema from Korean Public Data Portal (data.go.kr) documentation pages and generate structured JSON representation

596

apollo-data-handling

jeremylongshore

Apollo.io data management and compliance. Use when handling contact data, implementing GDPR compliance, or managing data exports and retention. Trigger with phrases like "apollo data", "apollo gdpr", "apollo compliance", "apollo data export", "apollo data retention", "apollo pii".

12

azure-ai-contentunderstanding-py

microsoft

Azure AI Content Understanding SDK for Python. Use for multimodal content extraction from documents, images, audio, and video. Triggers: "azure-ai-contentunderstanding", "ContentUnderstandingClient", "multimodal analysis", "document extraction", "video analysis", "audio transcription".

12

azure-ai-document-intelligence-dotnet

microsoft

Azure AI Document Intelligence SDK for .NET. Extract text, tables, and structured data from documents using prebuilt and custom models. Use for invoice processing, receipt extraction, ID document analysis, and custom document models. Triggers: "Document Intelligence", "DocumentIntelligenceClient", "form recognizer", "invoice extraction", "receipt OCR", "document analysis .NET".

03

fireflies-core-workflow-a

jeremylongshore

Execute Fireflies.ai primary workflow: Core Workflow A. Use when implementing primary use case, building main features, or core integration tasks. Trigger with phrases like "fireflies main workflow", "primary task with fireflies".

12

openrouter-model-catalog

jeremylongshore

Build explore and query the OpenRouter model catalog programmatically. Use when selecting models or checking availability. Trigger with phrases like 'openrouter models', 'list openrouter models', 'openrouter model catalog', 'available models openrouter'.

03

Search skills

Search the agent skills registry