fireflies-core-workflow-a
Retrieves meeting data from Fireflies.ai using GraphQL to extract transcripts, summaries, and action items programmatically.
Install
mkdir -p .claude/skills/fireflies-core-workflow-a && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/6341" && unzip -o skill.zip -d .claude/skills/fireflies-core-workflow-a && rm skill.zipInstalls to .claude/skills/fireflies-core-workflow-a
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.
Retrieve and process Fireflies.ai meeting transcripts with speaker diarizationKey capabilities
- →Build a GraphQL client for Fireflies.ai API
- →List meeting transcripts with filters
- →Fetch full transcripts including speaker diarization and sentences
- →Process meeting intelligence to extract action items and sentiment
- →Export transcripts to text format
How it works
The skill uses a GraphQL client to query the Fireflies.ai API for meeting transcripts. It then processes the retrieved data to extract speaker-diarized sentences, summaries, action items, and other meeting intelligence.
Inputs & outputs
When to use fireflies-core-workflow-a
- →Fetch meeting transcripts via GraphQL
- →Extract action items from meetings
- →Build meeting intelligence pipelines
- →Process speaker-diarized transcript data
About this skill
Fireflies Transcript Retrieval Boundary
Overview
Treat a transcript as sensitive meeting data. Separate metadata, summary, sentences, analytics, media links, attendance, and sharing fields so callers receive only what their use case permits.
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
Use transcript(id: String!) for one record. Meeting ID and transcript ID refer to the same platform identity. Selected fields have different sensitivity and entitlement requirements; analytics requires an eligible plan, and is_live changes whether sentences are live captions or processed transcript data.
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
- Confirm the requesting principal may access the target transcript and state the business purpose.
- Classify each requested field and remove participants, sentences, media URLs, or analytics unless necessary.
- Send a named transcript query with the ID as a variable.
- Reject object_not_found as either absence or inaccessible data without probing other IDs.
- Validate the returned ID, processing status, nullability, and expected organizer or ownership metadata.
- Route content through the approved redaction and retention boundary before downstream use.
- Return a receipt with selected field groups and record count, never the meeting body.
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 retrieving sentences, raw_text, audio_url, video_url, participant identifiers, attendance, analytics, or externally shared access.
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
- object_not_found: do not enumerate adjacent IDs; verify authorization and the supplied ID.
- Summary is null: inspect processing state and wait rather than fabricating a result.
- is_live is true: do not treat captions as a finalized transcript.
Examples
- "Read the title and summary status" requests only those fields.
- "Export every sentence to logs" is rejected.
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
- →When the API key is invalid
- →When the transcript is still processing
- →When the meeting is too short to generate a summary
Prerequisites
Limitations
- →Analytics data requires a Business+ plan
- →Rate limits apply to API requests
- →Empty sentences array indicates the transcript is still processing
How it compares
This skill automates the retrieval and structured processing of Fireflies.ai meeting data via GraphQL, providing specific intelligence like action items and speaker analytics, which is more detailed than manual review.
Compared to similar skills
fireflies-core-workflow-a side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| fireflies-core-workflow-a (this skill) | 1 | 2mo | Caution | Intermediate |
| apollo-data-handling | 1 | 2mo | Caution | Intermediate |
| azure-ai-document-intelligence-ts | 0 | 5mo | Review | Intermediate |
| apollo-migration-deep-dive | 1 | 2mo | Caution | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
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".
azure-ai-document-intelligence-ts
microsoft
Extract text, tables, and structured data from documents using Azure Document Intelligence (@azure-rest/ai-document-intelligence). Use when processing invoices, receipts, IDs, forms, or building custom document models.
apollo-migration-deep-dive
jeremylongshore
Comprehensive Apollo.io migration strategies. Use when migrating from other CRMs to Apollo, consolidating data sources, or executing large-scale data migrations. Trigger with phrases like "apollo migration", "migrate to apollo", "apollo data import", "crm to apollo", "apollo migration strategy".
openevidence-core-workflow-b
jeremylongshore
Execute OpenEvidence DeepConsult workflow for comprehensive medical research. Use when implementing deep research synthesis, complex clinical questions, or when physicians need extensive literature review. Trigger with phrases like "openevidence deepconsult", "deep research", "comprehensive evidence", "literature synthesis".
segment-cdp
davila7
Expert patterns for Segment Customer Data Platform including Analytics.js, server-side tracking, tracking plans with Protocols, identity resolution, destinations configuration, and data governance best practices. Use when: segment, analytics.js, customer data platform, cdp, tracking plan.
groq-cost-tuning
jeremylongshore
Optimize Groq costs through tier selection, sampling, and usage monitoring. Use when analyzing Groq billing, reducing API costs, or implementing usage monitoring and budget alerts. Trigger with phrases like "groq cost", "groq billing", "reduce groq costs", "groq pricing", "groq expensive", "groq budget".