In brief
Twilio Conversation Intelligence Development Guide. This sheet covers a conversation analysis in real time or after the call, pipelines of language operators, an analysis of feelings, assistance with agent, transversal analysis of channels, or the question of aggregate indicators (feeling trends, escalation rates, dashboards).
What it does
- Analyze a conversation in real time or after the call
- Covers feelings, agent assistance, operator pipelines and dashboards
Who it is for, and an example
Teams that want to analyze Twilio conversations (sentiment, support, escalation) in real time or after the event.
Example request: "Setting up Conversation Intelligence: real-time sentiment analysis, agent assistance, and a chart of escalation rates. »
Typical perimeter: real-time or post-call analysis, operator pipelines, feeling, agent assistance, cross-sectional analysis or aggregated insights. Example written by iadujour.fr from the SKILL.md, not tested.
Install
In Codex: codex plugin add twilio-developer-kit@openai-curated (Official Place of Deposit).
codex plugin add twilio-developer-kit@openai-curatedWorks with
- Codex
Source: README: Codex plugin collection; the deposit marketplace is called "Official Codex". Other officers are not appointed.
Level: Intermediate
Suppose a project already in place at the publisher and the tools described in SKILL.md.
Good to know
SKILL.md excerpt
The original description, which the agent reads to decide whether to load the skill (in English):
Twilio Conversation Intelligence development guide. Use when building real-time or post-call conversation analysis, language operator pipelines, sentiment analysis, agent assist, cross-channel analytics, or querying aggregated conversation insights (sentiment trends, escalation rates, dashboards).
Quoted from SKILL.md at commit 0837304 . The folder also contains 1 extra file (agents/).
The SKILL.md has 612 lines and 39 main sections:
- Use Cases
- Wrap-up Agent Assist (Post-Call)
- Real-time Agent Assist
- Real-time Workflow Automation
- Contact Center QA
- How It Works
- Scope
- CAN
- CANNOT
- Quick Decision
- Decision Frameworks
- v2 (Voice Intelligence) vs v3 (Conversation Intelligence)
- Real-Time vs Post-Conversation
- Operator Version Lifecycle
- Custom Operator Output Formats
- Twilio-Authored Operator Reference
- Integration Patterns
- Authentication Helper
- Create Intelligence Configuration with Rules
- Link to Conversation Orchestrator Conversation Configuration
- Consume Operator Results
- Paginate Through Results
- Enable Customer Memory and Enterprise Knowledge on a Rule
- Create a Custom Operator with Training Examples and Parameters
- Gotchas
- Setup
- Configuration
- Runtime
- Observability
- Error Handling
- JSON Schema
- Conversational Insights (Cross-Conversation Analytics)
- When to Use Insights vs Intelligence REST API
- Endpoints
- Query a Sentiment Distribution
- Pagination
- Discover Available Dimensions and Measures
- Insights CANNOT
- Related Resources
Licence: No licence found
Checked on 10 November 2026 : no licence file in the skill folder or at the repository root.
No licence found: short excerpt quoted only (quotation right). For the full text, see the source.
In the directory
Use cases and guides that share a theme, industry or tool with this skill.
Comments.
A field note, a question, a precision on this skill? Comments are reviewed before publication.
Published comments
Loading comments…
Leave a comment
Moderation charter. Every comment is reviewed before publication. We refuse hate speech, insulting or discriminatory language, advertising, spam and promotional links, off-topic posts and other people’s personal data.