Agent skill · software engineering · jeremylongshore
fireflies-performance-tuning
Reduce Fireflies latency and quota use through field minimization, bounded pagination, caching of non-sensitive metadata, and asynchronous webhook-driven retrieval. Use when calls are slow or wasteful. Trigger with "speed up Fireflies", "optimize Fireflies query", or "reduce Fireflies calls".
Why this skill is useful
Adds executable scripts for optimizing Fireflies.ai GraphQL API performance through field selection, caching, and batching.
What it needs
Requires ioredis, lru-cache, p-queue installed locally. Requires fireflies account access. About 2k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Fireflies GraphQL Performance Tuning Overview Reduce Fireflies latency and quota use through field minimization, bounded pagination, caching of non-sensitive metadata, and asynchronous webhook-driven retrieval. 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 GraphQL performance starts with smaller field selections and fewer calls. transcripts pages at most 50 records; cache only approved metadata, never assume summaries or sentences are immutable while processing, and prefer Webhooks V2 over aggressive polling. Authentication For authenticated operations, inject FIREFLIESAPIKEY from an approved secret manager and send it only as Authorization: Bearer REDACTEDKEY 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 1. Measure latency, response bytes, selected fields, pages, errors, and quota use by operation. 2. Remove unused nested fields and split metadata discovery from sensitive detail retrieval. 3. Set explicit result caps and page only while the caller still needs data. 4. Replace processing-status polling with meeting.transcribed or meeting.summarized events where appropriate. 5. Cache only classified metadata with tenant-aware keys and bounded TTLs. 6. Limit concurrency below the applicable plan and operation budgets. 7. Compare before/after metrics on synthetic or approved records and keep rollback settings. Tool Discipline Use Read, Glob, and Grep to inspect code, configuration, tests, and evidence. Use Write/Edit only for approved implementation or documentation changes. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/fireflies-performance-tuning--b02636