fireflies-observability
Configures observability tools like Prometheus and Grafana for Fireflies.ai API tracking.
Install
mkdir -p .claude/skills/fireflies-observability && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/8849" && unzip -o skill.zip -d .claude/skills/fireflies-observability && rm skill.zipInstalls to .claude/skills/fireflies-observability
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.
Monitor Fireflies.ai integration health with metrics, alerts, and dashboards.Key capabilities
- →Instrument GraphQL clients for request latency and error tracking
- →Monitor webhook event processing and queue depth
- →Execute periodic health check probes
- →Track seat utilization and transcript counts per user
- →Configure Prometheus alerting rules for integration health
How it works
It instruments code with Prometheus client libraries to track API performance and webhook processing, while providing alerting rules to monitor system health.
Inputs & outputs
When to use fireflies-observability
- →Track Fireflies API request latency
- →Set up alerts for webhook failures
- →Monitor transcript processing reliability
- →Visualize API seat utilization in Grafana
About this skill
Fireflies Content-Free Observability
Overview
Instrument Fireflies GraphQL and webhook workflows with operation, latency, quota, queue, signature, and processing metrics that exclude meeting content and identities.
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
Observability may include operation name, result class, GraphQL code, duration, response size bucket, retryAfter, event type, signature result, queue depth, and processing latency. It must exclude Authorization, queries with variables, meeting IDs, emails, titles, sentences, summaries, and media URLs.
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
- Define service-level indicators for GraphQL success, webhook acknowledgement, queue processing, and freshness.
- Instrument safe dimensions with a strict allowlist and cardinality budget.
- Track plan and operation-specific throttles separately.
- Measure transcribed-to-summarized and event-to-processing latency without meeting IDs in metrics.
- Alert on auth failures, signature failures, throttle spikes, backlog, dead letters, and stale processing.
- Keep detailed identifiers only in access-controlled audit records when approved.
- Test telemetry redaction with synthetic secrets and meeting data.
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 logging identifiers or response fragments, increasing telemetry retention, or exporting observability data to a new vendor.
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
- High-cardinality label detected: remove it before deployment.
- Sensitive value appears in telemetry: stop export and follow incident handling.
- Metrics disagree with audit receipts: investigate instrumentation before changing workload behavior.
Examples
- "Review fireflies content-free observability" 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
- →Real-time incident response
- →Direct modification of Fireflies.ai account settings
Prerequisites
Limitations
- →Requires Fireflies Business+ plan for full API access
- →Alerting rules assume Prometheus/Grafana stack
How it compares
It provides pre-built instrumentation patterns and alerting rules instead of requiring manual setup of monitoring logic.
Compared to similar skills
fireflies-observability side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| fireflies-observability (this skill) | 0 | 2mo | Caution | Advanced |
| langfuse | 7 | 8mo | No flags | Intermediate |
| appinsights-instrumentation | 6 | 8mo | Review | Beginner |
| instantly-observability | 2 | 2mo | Caution | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
langfuse
davila7
Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production. Use when: langfuse, llm observability, llm tracing, prompt management, llm evaluation.
appinsights-instrumentation
github
Instrument a webapp to send useful telemetry data to Azure App Insights
instantly-observability
jeremylongshore
Set up comprehensive observability for Instantly integrations with metrics, traces, and alerts. Use when implementing monitoring for Instantly operations, setting up dashboards, or configuring alerting for Instantly integration health. Trigger with phrases like "instantly monitoring", "instantly metrics", "instantly observability", "monitor instantly", "instantly alerts", "instantly tracing".
apollo-observability
jeremylongshore
Set up Apollo.io monitoring and observability. Use when implementing logging, metrics, tracing, and alerting for Apollo integrations. Trigger with phrases like "apollo monitoring", "apollo metrics", "apollo observability", "apollo logging", "apollo alerts".
evernote-observability
jeremylongshore
Implement observability for Evernote integrations. Use when setting up monitoring, logging, tracing, or alerting for Evernote applications. Trigger with phrases like "evernote monitoring", "evernote logging", "evernote metrics", "evernote observability".
linear-observability
jeremylongshore
Implement monitoring, logging, and alerting for Linear integrations. Use when setting up metrics collection, creating dashboards, or configuring alerts for Linear API usage. Trigger with phrases like "linear monitoring", "linear observability", "linear metrics", "linear logging", "monitor linear integration".