Agent skill

Cometchat Analytics

by cometchat in cometchat/cometchat-skills

See what your chat is doing — pull usage & message metrics via REST, stream real-time events to your data/observability stack via webhooks, monitor client-side errors & the init/login path, and read…

MITAuto-check passedBackend & APIs

Install Cometchat Analytics

skills CLI
$ npx skills add cometchat/cometchat-skills --skill cometchat-analytics -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cometchat/cometchat-skills cometchat-analytics --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cometchat/cometchat-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cometchat-analytics .claude/skills/cometchat-analytics && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cometchat-analytics
GitHub stars
129
Token cost
~1.5k tokens
SKILL.md length
642 words
Files
1
Skills in repo
97
Repo updated
First seen
Licence
MIT

At a glance

See what your chat is doing — pull usage & message metrics via REST, stream real-time events to your data/observability stack via webhooks, monitor client-side errors & the init/login path, and read…

  • Works in 5 steps: Aggregate metrics (REST, server-side) → Real-time events → your stack (webhooks) → Client-side error & performance… → …
  • Tasks that involve Webhooks
  • SKILL.md covers Use this skill when, Three layers of visibility, 1. Aggregate metrics (REST,… and 2. Real-time events → your…, plus 5 more sections
  • Reaches cometchat.com

What it does

Cometchat Analytics is an agent skill from cometchat/cometchat-skills. See what your chat is doing — pull usage & message metrics via REST, stream real-time events to your data/observability stack via webhooks, monitor client-side errors & the init/login path, and read push/call logs. Cross-family: metrics/webhooks are server-side; client error monitoring wires per family. Triggers: 'chat analytics', 'usage metrics', 'message volume', 'monitor cometchat', 'observability', 'send chat events to datadog/segment/bigquery', 'track delivery', 'error monitoring for chat', 'dashboards for…

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: CometChat Metrics REST API (usage · message) · Webhooks · Notification/Call logs · on-prem Prometheus/Grafana/Loki. Client error monitoring via each family's…

It sits in Backend & APIs, covering Webhooks, Data warehousing and Backend development. It works with CometChat, Google BigQuery and Datadog. The repository describes itself as: Add CometChat chat & messaging and voice & video calls to any React, Next.js, React Native, Angular, Android, iOS, or Flutter project through your AI coding agent. Works with… The licence is MIT.

When your agent uses it

  • Tasks that involve Webhooks
  • Tasks that involve Data warehousing
  • Tasks that involve Backend development

Example prompts

  • “chat analytics”
  • “usage metrics”
  • “message volume”
  • “/cometchat-analytics”

Requirements

  • Docker
  • Compatibility (from SKILL.md): CometChat Metrics REST API (usage · message) · Webhooks · Notification/Call logs · on-prem Prometheus/Grafana/Loki. Client error monitoring via each family's error boundary / listeners.

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Aggregate metrics (REST, server-side)
  2. Real-time events → your stack (webhooks)
  3. Client-side error & performance monitoring (per family)
  4. Delivery & call logs
  5. Self-host observability

What it can do on your machine

Read from SKILL.md and the folder at commit 911b108. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • cometchat.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    CometChat Metrics REST API (usage · message) · Webhooks · Notification/Call logs · on-prem Prometheus/Grafana/Loki. Client error monitoring via each family's error boundary / listeners.

    From compatibility in the SKILL.md frontmatter.

Context cost

Cometchat Analytics loads about 1.5k tokens when it runs. Until then it costs about 136 tokens; SKILL.md has 642 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~136
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from cometchat/cometchat-skills at commit 911b108, republished under its MIT licence (© cometchat). 642 words, ~1,544 tokens.

Download SKILL.mdSave it as .claude/skills/cometchat-analytics/SKILL.md (or your agent's skills folder).
name
cometchat-analytics
description
See what your chat is doing — pull usage & message metrics via REST, stream real-time events to your data/observability stack via webhooks, monitor client-side errors & the init/login path, and read push/call logs. Cross-family: metrics/webhooks are server-side; client error monitoring wires per family. Triggers: 'chat analytics', 'usage metrics', 'message volume', 'monitor cometchat', 'observability', 'send chat events to datadog/segment/bigquery', 'track delivery', 'error monitoring for chat', 'dashboards for chat'.
compatibility
CometChat Metrics REST API (usage · message) · Webhooks · Notification/Call logs · on-prem Prometheus/Grafana/Loki. Client error monitoring via each family's error boundary / listeners.
license
MIT
metadata.author
CometChat
metadata.version
1.0.0
metadata.tags
cometchat analytics observability metrics webhooks monitoring datadog sentry dashboards

Ground truth: shapes are FETCHED from the live docs — {DOCS_BASE}/rest-api/metrics/usage-metrics, /rest-api/metrics/message-metrics, /fundamentals/webhooks (+ /rest-api/management-apis/webhooks/overview), /notifications/logs, /rest-api/calls-apis/get-call, and on-prem /on-premise-deployment/docker/monitoring. DOCS_BASE = https://www.cometchat.com/docs; append .md. Verify each metric field / event name against the docs before charting it; don't invent a metric.

Use this skill when

You need visibility into chat: product analytics (DAU, messages, retention), an ops/observability signal (delivery, errors, latency), or feeding chat events into an existing warehouse/monitoring stack.

Three layers of visibility

LayerSourceUse it for
Aggregate metricsMetrics REST API (usage + message)dashboards, MAU/DAU, message volume, growth
Real-time eventsWebhooksstream every message/user/group/call event to your pipeline
Client healthyour error monitor + the kit's error boundary/listenersinit/login failures, render errors, UX latency

1. Aggregate metrics (REST, server-side)

  • Usage metrics ({DOCS_BASE}/rest-api/metrics/usage-metrics) — active users and usage over time.
  • Message metrics ({DOCS_BASE}/rest-api/metrics/message-metrics) — message volume/counts.
  • Call metrics — per-call detail incl. participant metrics via {DOCS_BASE}/rest-api/calls-apis/get-call. Call these from a server job with the REST API Key (never client-side), on a schedule, into your BI tool. Fetch the exact query params + response fields from each page before building the report.

2. Real-time events → your stack (webhooks)

Webhooks POST an HTTPS notification to your server on message / user / group / call events ({DOCS_BASE}/fundamentals/webhooks; configure via /rest-api/management-apis/webhooks/overview). This is how you get chat into Segment / BigQuery / Snowflake / Datadog / a data lake in real time:

  1. Stand up an HTTPS endpoint (returns 200 to ack). Secure it with the Basic Auth credentials CometChat sends on every webhook request ({DOCS_BASE}/fundamentals/webhooks — the docs describe Basic Auth only, with no payload-signature scheme, so validate the Authorization header rather than looking for an HMAC signature).
  2. Subscribe to the events you need (don't fan out everything if you only need message.sent).
  3. Transform + forward to your warehouse/observability sink; make the handler idempotent and fast (queue heavy work). The same webhook stream doubles as a tamper-evident audit log for cometchat-compliance.

3. Client-side error & performance monitoring (per family)

The metrics API won't tell you a user's chat failed to load — instrument the client:

  • Capture kit render errors — on the React families via the error boundary's hook (React v7: CometChatErrorBoundary onError; Angular/RN have the equivalent); on iOS/Android/Flutter (no error-boundary construct) via the SDK error listeners / the kit's error-state views. Forward to Sentry/Datadog with context.
  • Instrument the critical path — wrap init, the token fetch, and login in spans/breadcrumbs; a spike in login failures is your earliest incident signal (often Region or token issues).
  • Listen for connection state — the SDK's connection/websocket listeners tell you when clients drop; count reconnects.
  • Don't log secrets or message bodies to your monitor — log UIDs/event types/latencies, not content (privacy + cometchat-compliance). Wire these through the resolved family's -core/-production/-troubleshooting skills.
Show full SKILL.md (207 more words)Show less

4. Delivery & call logs

  • Push delivery logs ({DOCS_BASE}/notifications/logs) — FCM/APNs/email/SMS delivery, ~14-day retention; enable when diagnosing "notifications not arriving" and export before they age out.
  • Call logs — the Calls REST APIs for per-call quality/participant metrics.

5. Self-host observability

On-prem ships Prometheus + Grafana + Loki + Promtail ({DOCS_BASE}/on-premise-deployment/docker/monitoring): service metrics, dashboards, alerts, and centralized logs — wire alerts (P95 latency, error rate, WS capacity) to your on-call. SaaS customers use the Metrics API + webhooks instead.

Common pitfalls

  1. Metrics API called client-side — it needs the REST API Key; server only.
  2. Webhook handler slow or non-idempotent — retries pile up; ack fast, queue the work, dedupe.
  3. Charting an invented metric — fetch the real fields from the metrics pages.
  4. Logging message content to your monitor — privacy/compliance risk; log metadata, not bodies.
  5. No client error monitoring — you'll hear about outages from users, not dashboards; wire the error boundary + login-path spans.
  6. Relying on push logs after they age out — export within the retention window.

Verify it works

Usage/message metrics return real numbers into your dashboard · a test message triggers your webhook and lands in your warehouse/monitor · a forced init/login failure shows up in your error monitor with context · push/call logs are readable when needed · (on-prem) Grafana shows the services and alerts fire.

© cometchat, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/cometchat-analytics of cometchat/cometchat-skills.

Open the folder on GitHubat commit 911b108

Compare with similar skills

Cometchat Analytics next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cometchat Analytics compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cometchat Analytics this skillcometchat/cometchat-skills129—~1.5kAutomated safety check: PassMIT
Backend Dev Guidelineslitefuse/litefuse1001 repos~5.8kAutomated safety check: PassCustom licence
Google Agents CLI Observabilitypifferologo/cloud-agents-cli1291 repos~2.5kAutomated safety check: PassApache-2.0
Bigquery Observabilitygoogle/skills21k—~3.5kAutomated safety check: PassApache-2.0
Bigquery Optimizationgoogle/skills21k—~2kAutomated safety check: PassApache-2.0
Bigquery Troubleshootinggoogle/skills21k—~2.5kAutomated safety check: PassApache-2.0

Similar skills

  • Backend Dev Guidelines

    litefuse/litefuse

    Comprehensive backend development guide for Litefuse's Next.js 14/tRPC/Express/TypeScript monorepo.

    100 GitHub starsUsed in 1 repo~5.8k tokens
    Backend & APIsAuto-check passed
  • Google Agents CLI Observability

    pifferologo/cloud-agents-cli

    This skill should be used when the user wants to "set up tracing", "monitor my ADK agent", "configure logging", "add observability", "debug production traffic", or needs guidance on monitoring…

    129 GitHub starsUsed in 1 repo~2.5k tokens
    DevOps & CloudAuto-check passed
  • Official

    Provides data-retrieval best practices, tool selection guidance, and performant SQL query syntax for BigQuery telemetry across INFORMATIONSCHEMA, Cloud Monitoring, and the REST API.

    21k GitHub stars~3.5k tokensUpdated today
    DatabasesAuto-check passed
  • Official

    Provides workflows to optimize BigQuery environments (capacity planning, editions), storage assets (partitioning, clustering, storage lifecycles, billing models), and SQL queries.

    21k GitHub stars~2k tokensUpdated today
    DatabasesAuto-check passed
  • Official

    Provides diagnostic workflows and step-by-step root-cause analysis procedures for actively broken, failing, or slow BigQuery jobs, execution graph and query plan stage bottlenecks, system…

    21k GitHub stars~2.5k tokensUpdated today
    DatabasesAuto-check passed
  • Backend Dev Guidelines

    langfuse/langfuse

    Build or review Langfuse backend code. An agent skill from langfuse/langfuse.

    35k GitHub stars~1.9k tokensUpdated today
    Backend & APIsAuto-check passed

More from cometchat/cometchat-skills

All 97 skills in this repo
  • CometChat Android Calls SDK v5

    cometchat/cometchat-skills

    Adds voice and video calling to an Android app in Kotlin with the headless CometChat Calls SDK v5, covering meeting-style rooms, 1:1 ringing calls, call logs and recording.

    129 GitHub stars~5.2k tokensUpdated 2 days ago
    Auto-check passed
  • CometChat Android v5 Headless SDK

    cometchat/cometchat-skills

    Builds chat on Android with your own UI against the headless CometChat Chat SDK v5, covering install, Jetifier conflicts, credentials and init-before-login ordering.

    129 GitHub stars~4k tokensUpdated 2 days ago
    Auto-check passed
  • CometChat Angular Component Picker

    cometchat/cometchat-skills

    Picks and customizes CometChat's Angular UI Kit components by their verified component list, exact input and output event names, and the surfaces that have no kit component at all.

    129 GitHub stars~2.6k tokensUpdated 2 days ago
    Auto-check passed
  • CometChat Angular Features

    cometchat/cometchat-skills

    Enables or builds CometChat features such as polls, reactions, smart replies and pinned messages in an Angular app, first classifying how much client code each one needs.

    129 GitHub stars~2.6k tokensUpdated 2 days ago
    Auto-check passed
  • CometChat Angular Chat Placement

    cometchat/cometchat-skills

    Decides where CometChat chat UI goes in an Angular app: a dedicated route, a dashboard panel, a support widget or the full multi-pane app, with thread and search panels.

    129 GitHub stars~2.2k tokensUpdated 2 days ago
    Auto-check passed
  • Cometchat iOS V5 SDK

    cometchat/cometchat-skills

    Add voice & video calling to any iOS app FROM SCRATCH with the headless CometChat Calls SDK v5 (CometChatCallsSDK, via Swift Package Manager) — no UI Kit.

    129 GitHub stars~5.2k tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Cometchat Analytics

What does Cometchat Analytics do?

See what your chat is doing — pull usage & message metrics via REST, stream real-time events to your data/observability stack via webhooks, monitor client-side errors & the init/login path, and read…. Cometchat Analytics is an agent skill from cometchat/cometchat-skills. See what your chat is doing — pull usage & message metrics via REST, stream real-time events to your data/observability stack via webhooks, monitor client-side errors & the init/login path, and read push/call logs.

When should I use Cometchat Analytics?

Cometchat Analytics fits situations like: tasks that involve Webhooks; tasks that involve Data warehousing; tasks that involve Backend development.

How do I install Cometchat Analytics in Claude Code?

Run `npx skills add cometchat/cometchat-skills --skill cometchat-analytics -a claude-code`. Or copy the skill folder (skills/cometchat-analytics in cometchat/cometchat-skills) into .claude/skills/cometchat-analytics in your project. Claude Code loads it when a task matches its description.

How do I install Cometchat Analytics in Codex?

Run `npx skills add cometchat/cometchat-skills --skill cometchat-analytics -a codex`. Or copy the skill folder (skills/cometchat-analytics in cometchat/cometchat-skills) into .agents/skills/cometchat-analytics in your project. Codex loads it when a task matches its description.

Can I use Cometchat Analytics in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cometchat/cometchat-skills --skill cometchat-analytics -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cometchat-analytics, .gemini/skills/cometchat-analytics, .github/skills/cometchat-analytics and .opencode/skills/cometchat-analytics in your project.

What does Cometchat Analytics need to run?

SKILL.md names no scripts, command-line tools or credentials: Cometchat Analytics is instructions for the agent only. Our summary lists: Docker. Compatibility (from SKILL.md): CometChat Metrics REST API (usage · message) · Webhooks · Notification/Call logs · on-prem Prometheus/Grafana/Loki. Client error monitoring via each family's error boundary / listeners..

Does Cometchat Analytics access the network?

SKILL.md names 1 domain. In commands or code: cometchat.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Cometchat Analytics safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Cometchat Analytics use?

Cometchat Analytics is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cometchat Analytics use?

About 1.5k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Cometchat Analytics?

Skills that share tags, products or a category with Cometchat Analytics: Backend Dev Guidelines (litefuse/litefuse, 100 stars), Google Agents CLI Observability (pifferologo/cloud-agents-cli, 129 stars), Bigquery Observability (google/skills, 21k stars) and Bigquery Optimization (google/skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cometchat Analytics?

cometchat (a GitHub organization) maintains it in cometchat/cometchat-skills, which has 129 GitHub stars. The repository holds 97 skills in this directory. The repository was last updated on October 5, 2026.

Source: cometchat/cometchat-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.