fireflies-migration-deep-dive
Provides strategies and step-by-step guides for migrating to Fireflies.ai from legacy transcription platforms.
Install
mkdir -p .claude/skills/fireflies-migration-deep-dive && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/5386" && unzip -o skill.zip -d .claude/skills/fireflies-migration-deep-dive && rm skill.zipInstalls to .claude/skills/fireflies-migration-deep-dive
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.
Migrate to Fireflies.ai from other meeting transcription platforms orKey capabilities
- →Assess existing meeting data inventory
- →Batch upload historical recordings via GraphQL
- →Handle authenticated storage URLs for imports
- →Track migration progress using webhooks
- →Implement adapter patterns for gradual cutover
How it works
The migration process involves inventorying existing data, batching uploads via the uploadAudio mutation, and using an adapter pattern to switch between legacy and Fireflies services during a phased rollout.
Inputs & outputs
When to use fireflies-migration-deep-dive
- →Importing historical meeting data into Fireflies.ai
- →Switching from competitor transcription platforms
- →Executing gradual platform cutover using the adapter pattern
- →Performing pre-migration data inventory assessment
About this skill
Fireflies Governed Audio Ingestion
Overview
Migrate authorized recordings into Fireflies through current uploadAudio or addToLiveMeeting contracts with provenance, consent, limits, callbacks, and rollback planning.
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
uploadAudio accepts a publicly downloadable HTTPS media URL and documented mp3, mp4, wav, m4a, or ogg formats; current size limits differ for audio, free-tier video, and paid-tier video. addToLiveMeeting accepts supported meeting links and is limited to 3 requests per 20 minutes.
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
- Inventory source recordings, ownership, consent, format, size, retention, and destination team.
- Reject preview links, expiring links that cannot survive ingestion, and unauthorized public exposure.
- Choose uploadAudio for recordings or addToLiveMeeting for an approved supported live meeting.
- Attach a non-sensitive client reference and approved callback only when needed.
- Submit a small canary, record the returned status without logging the source URL, and wait for current webhook events.
- Validate transcript identity, expected duration, processing status, and authorized metadata before scaling.
- Batch within quotas, track provenance, remove temporary public access, and reconcile failures.
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 exposing a media URL, uploading real recordings, adding a bot to a live meeting, configuring callbacks, or scaling a batch.
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
- Media URL is not public HTTPS or downloadable: do not weaken storage controls blindly.
- unsupported_platform or invalid language: correct reviewed input instead of retrying.
- Timeout after submission: reconcile by client reference or webhook before resubmitting.
Examples
- "Review fireflies governed audio ingestion" 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
- →Systems requiring immediate, non-gradual platform replacement
- →Environments without access to public HTTPS recording URLs
Prerequisites
Limitations
- →Uploads require a Pro+ plan
- →Files under 50KB require bypass_size_check: true
How it compares
This workflow uses a strangler fig pattern for gradual cutover rather than a high-risk, all-at-once platform migration.
Compared to similar skills
fireflies-migration-deep-dive side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| fireflies-migration-deep-dive (this skill) | 1 | 2mo | Caution | Advanced |
| opencode-cli | 14 | 9mo | Review | Advanced |
| claude-automation-recommender | 47 | 4mo | Review | Beginner |
| mcp-integration | 21 | 10mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
opencode-cli
SpillwaveSolutions
This skill should be used when configuring or using the OpenCode CLI for headless LLM automation. Use when the user asks to "configure opencode", "use opencode cli", "set up opencode", "opencode run command", "opencode model selection", "opencode providers", "opencode vertex ai", "opencode mcp servers", "opencode ollama", "opencode local models", "opencode deepseek", "opencode kimi", "opencode mistral", "fallback cli tool", or "headless llm cli". Covers command syntax, provider configuration, Vertex AI setup, MCP servers, local models, cloud providers, and subprocess integration patterns.
claude-automation-recommender
anthropics
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.
mcp-integration
anthropics
This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
hook-development
anthropics
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.
pdf-processing-pro
davila7
Production-ready PDF processing with forms, tables, OCR, validation, and batch operations. Use when working with complex PDF workflows in production environments, processing large volumes of PDFs, or requiring robust error handling and validation.
agent-factory
alirezarezvani
Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns