Build a deterministic Fireflies development loop with recorded synthetic GraphQL fixtures, schema-contract tests, and no dependency on production meeting data. Use when implementing or debugging locally. Trigger with "Fireflies local development", "mock Fireflies GraphQL", or "Fireflies test fixture".
Make local work reproducible without copying real transcripts, participant lists, summaries, or bearer keys onto developer machines.
Model GraphQL responses as data plus optional errors, preserve nullability, and keep separate fixtures for success, partial data, validation failure, authorization failure, rate limiting, and delayed processing.
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.
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.
Require approval before recording a live response, connecting a local process to production, or storing any real meeting-derived content.
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.
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.
Read official Fireflies.ai evidence before relying on a field, filter, event, permission, plan limit, mutation, or processing state.
88dcf65
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.