Build a Fireflies CI lane with static GraphQL validation, synthetic fixtures, secret scanning, webhook vectors, and narrowly gated live tests. Use when adding automated verification. Trigger with "Fireflies CI", "test Fireflies GraphQL", or "Fireflies contract test".
Build a Fireflies CI lane with static GraphQL validation, synthetic fixtures, secret scanning, webhook vectors, and narrowly gated live tests.
Most CI should be offline and deterministic. Live tests require an explicitly provisioned read-only test identity, selected metadata fields, strict budgets, and no production meeting data.
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 enabling live CI, adding a mutation test, storing a Fireflies key, or retaining any API response artifact.
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.