fireflies-rate-limits
Guidance on managing Fireflies.ai API rate limits with exponential backoff and request queuing.
Install
mkdir -p .claude/skills/fireflies-rate-limits && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/5450" && unzip -o skill.zip -d .claude/skills/fireflies-rate-limits && rm skill.zipInstalls to .claude/skills/fireflies-rate-limits
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.
Implement Fireflies.ai rate limiting, backoff, and request queuing.Key capabilities
- →Detect rate limit errors in API responses
- →Queue batch operations to respect rate limits
- →Track daily API request budgets
- →Handle specific operation-level throttling
How it works
The skill manages API throughput by detecting 429 errors, applying exponential backoff with jitter for retries, and using a request queue to ensure operations stay within plan-specific limits.
Inputs & outputs
When to use fireflies-rate-limits
- →Implementing exponential backoff for API calls
- →Handling 'too_many_requests' error codes
- →Optimizing concurrent request throughput
- →Adding request queuing to avoid rate hitting
About this skill
Fireflies Request Budget and Backoff
Overview
Enforce current Fireflies plan and operation-specific request limits with bounded concurrency, retryAfter handling, and cost-aware pagination.
Prerequisites
- The target repository or integration path and the requested operator outcome.
- The Fireflies principal, team, environment, and data classification for the work.
- Current Fireflies documentation, credentials only when needed, and an accountable approver.
Current Contract
General documented limits are 50 requests/day for Free and Pro and 60 requests/minute for Business and Enterprise. addToLiveMeeting is 3 requests per 20 minutes, shareMeeting is 10/hour, and deleteTranscript is 10/minute. Treat docs and retryAfter as authoritative over hard-coded assumptions.
Authentication
For authenticated operations, inject FIREFLIES_API_KEY from an approved secret manager and send it only as Authorization: Bearer REDACTED_KEY to https://api.fireflies.ai/graphql. Never print, commit, place in a URL, forward to a browser, or include the key in evidence. Webhook signing secrets are separate credentials and must not be reused as API keys.
Instructions
- Identify the plan and every operation-specific bucket used by the workload.
- Set a conservative request budget and concurrency of one until measured.
- Use pagination caps and field minimization to avoid unnecessary calls.
- On too_many_requests, honor retryAfter when supplied and add bounded jitter.
- Do not retry auth, privilege, invalid-argument, object-not-found, or AI-credit errors.
- Export per-operation usage, throttles, wait time, and exhausted-budget metrics.
- Load-test only against synthetic or approved data within a separate budget.
Tool Discipline
Use Read, Glob, and Grep to inspect code, configuration, tests, and evidence. Use Write/Edit only for approved implementation or documentation changes. Do not query Fireflies, retrieve meeting content, create an AskFred thread, upload media, change account state, replay an event, or deploy merely because this skill was invoked.
Approval Boundaries
Require approval before increasing concurrency, consuming a large daily quota, load testing, or changing the subscribed plan.
Output
Return the exact operation or event surface, environment, authorization class, selected field groups, validation results, content-free metrics, decisions, and a concise pass/fail receipt. Keep secrets and meeting-derived content out of general output.
Validation
Before reporting success, rerun the smallest relevant deterministic check, compare actual state with the requested outcome and current contract, verify no secret or meeting-derived content entered logs or artifacts, and record unresolved uncertainty explicitly.
Error Handling
- No retryAfter: use a conservative documented window and bounded attempts.
- Daily quota exhausted: stop until reset or owner decision.
- Mutation outcome unknown after timeout: reconcile state before replay.
Examples
- "Review fireflies request budget and backoff" produces a bounded plan and redacted receipt.
- A request that widens access or mutates production is paused at the approval boundary.
Resources
Read official Fireflies.ai evidence before relying on a field, filter, event, permission, plan limit, mutation, or processing state.
When not to use it
- →Applications that can tolerate frequent 429 errors
- →Systems where request latency is not a concern
Prerequisites
Limitations
- →Business/Enterprise plans have different limits than Free/Pro
- →Daily limits reset based on the calendar day
How it compares
It replaces naive request loops with a reliable queuing and retry mechanism that prevents hitting API rate limits.
Compared to similar skills
fireflies-rate-limits side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| fireflies-rate-limits (this skill) | 1 | 2mo | Caution | Intermediate |
| deepgram-performance-tuning | 3 | 2mo | Review | Intermediate |
| graphql | 6 | 8mo | No flags | Advanced |
| guidewire-sdk-patterns | 2 | 2mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
deepgram-performance-tuning
jeremylongshore
Optimize Deepgram API performance for faster transcription and lower latency. Use when improving transcription speed, reducing latency, or optimizing audio processing pipelines. Trigger with phrases like "deepgram performance", "speed up deepgram", "optimize transcription", "deepgram latency", "deepgram faster".
graphql
davila7
GraphQL gives clients exactly the data they need - no more, no less. One endpoint, typed schema, introspection. But the flexibility that makes it powerful also makes it dangerous. Without proper controls, clients can craft queries that bring down your server. This skill covers schema design, resolvers, DataLoader for N+1 prevention, federation for microservices, and client integration with Apollo/urql. Key insight: GraphQL is a contract. The schema is the API documentation. Design it carefully.
guidewire-sdk-patterns
jeremylongshore
Master Guidewire SDK patterns including Digital SDK, REST API Client, and Gosu best practices. Use when implementing integrations, building frontends with Jutro, or writing server-side Gosu code. Trigger with phrases like "guidewire sdk", "digital sdk", "jutro sdk", "guidewire patterns", "gosu best practices", "rest api client".
groq-performance-tuning
jeremylongshore
Optimize Groq API performance with caching, batching, and connection pooling. Use when experiencing slow API responses, implementing caching strategies, or optimizing request throughput for Groq integrations. Trigger with phrases like "groq performance", "optimize groq", "groq latency", "groq caching", "groq slow", "groq batch".
openrouter-streaming-setup
jeremylongshore
Implement streaming responses with OpenRouter. Use when building real-time chat interfaces or reducing time-to-first-token. Trigger with phrases like 'openrouter streaming', 'openrouter sse', 'stream response', 'real-time openrouter'.
perplexity-multi-env-setup
jeremylongshore
Configure Perplexity across development, staging, and production environments. Use when setting up multi-environment deployments, configuring per-environment secrets, or implementing environment-specific Perplexity configurations. Trigger with phrases like "perplexity environments", "perplexity staging", "perplexity dev prod", "perplexity environment setup", "perplexity config by env".