conversational-intelligence

A guide for building Twilio systems that analyse live or completed conversations using AI. It covers results such as sentiment, summaries, categories, and extracted details.

In plain words
What is it for?
Use it to analyse phone or other captured conversations in real time or after they end, create custom analysis rules, and receive results through webhooks or an API.
Why use it?
It helps developers choose the right Conversation Intelligence version and set up analysis without guessing how the service works.

Skill for Claude CodeCodex

Part of the twilio-claude-plugin plugin — 31 skills, 18 commands, 7 agents, 5 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/wittyreference/twilio-claude-plugin/conversational-intelligence
Any agent
npx skills add wittyreference/twilio-claude-plugin --skill conversational-intelligence
Clone the repo
git clone --depth 1 https://github.com/wittyreference/twilio-claude-plugin

Made for: Claude Code, Codex.

Or install twilio-claude-plugin, the plugin that ships this one along with the rest of its 31 skills, 18 commands, 7 agents, 5 hooks.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,589 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.03589
Opus 5 $0.00007 $0.01795
Sonnet 5 $0.00003 $0.00718
Haiku 4.5 $0.00001 $0.00359

Measured 2d ago against content hash f3594ba54acd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

conversational-intelligence scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

const response = await fetch('https://intelligence.twilio.com/v3/ControlPlane/Operators', { method: 'POST',
skills/conversational-intelligence/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: conversational-intelligence description: Twilio Conversational Intelligence v3 development guide. Use when building real-time or post-call conversation analysis with Language Operators, creating custom operators, or choosing between Intelligence v2 and v3. Do NOT use for recording-based transcription (use Voice Intelligence v2 via /recordings skill). allowed-tools: mcp__twilio__*, Read, Grep, Glob

Twilio Conversational Intelligence v3

Real-time and post-conversation GenAI analysis engine. Processes conversations captured by Conversations Orchestrator (v2) using Language Operators — Twilio-authored or custom. Produces structured results (sentiment, summaries, classifications, extractions) delivered via webhook or queryable via API.

Generally available — HTTP-only (no SDK). Requires Conversations Orchestrator for conversation capture. AI model: OpenAI GPT-4o.

Evidence: Claims sourced from live testing (2026-03-26). MCP tool implementations verified in intelligence-v3.ts of the Twilio MCP server.

Scope

CAN

  • Run Language Operators per-message (COMMUNICATION trigger) for real-time analysis (~4s latency)
  • Run Language Operators post-conversation (CONVERSATION_END trigger) for full-context analysis
  • Run Language Operators on inactivity (CONVERSATION_INACTIVE trigger)
  • Use 4 Twilio-authored operators: Sentiment, Summary, Next Best Response, Script Adherence
  • Create custom Language Operators with free-form prompts and structured output (TEXT, JSON, CLASSIFICATION, EXTRACTION)
  • Deliver results via webhook (POST) with full execution context
  • Query results via REST API (filter by configuration or conversation)
  • Link up to 5 Intelligence Configurations per Conversation Configuration
  • Define up to 5 rules per configuration, each with up to 5 operators and 2 webhook actions
  • Use Enterprise Knowledge context (knowledge bases) in operator rules
  • Access Intelligence-processed conversations read-only via v3 Conversations endpoint

CANNOT

Read the full file on GitHub · 267 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 267 lines · 14 tokens per session scan B f3594ba54acd

Subscribe to this mod's changes

conversational-intelligence is a skill published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 3,589 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens