conversation-intelligence

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).

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/twilio-developer-kit/skills/twilio-conversation-intelligence/SKILL.md

Quality

Content

65%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-structured API reference with excellent concrete code and decision tables, but it is a large monolith with redundant content between the Scope and Gotchas sections and lacks both validation checkpoints on its destructive workaround and progressive-disclosure file splits.

Suggestions

De-duplicate content that appears in both 'Scope/CANNOT' and 'Gotchas' (JSON-only API, PUT inactive version, unsupported JSON-schema features, pagination) — keep each fact in one place and cross-reference.

Add an explicit validation/verification checkpoint to the destructive 'DELETE and POST to recreate' workaround (e.g., confirm no active rules depend on the config, verify the new config returns results) to lift workflow clarity above the destructive-operation cap.

Split the inlined 'Conversational Insights' section and the 27-item 'Gotchas' into one-level-deep reference files (e.g., INSIGHTS.md, GOTCHAS.md) linked from the overview to improve progressive disclosure for this large skill.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and avoids explaining concepts Claude already knows, but there is notable redundancy: the JSON-only API, PUT-inactive-version, JSON-schema unsupported features, and pagination points each appear in both the Scope/CANNOT list and the Gotchas section, which is more than the 'minor' trimming of anchor 4.	3 / 5
Actionability	Provides fully executable, copy-paste-ready fetch() examples covering the common cases (auth, create config + rules, consume/paginate results, custom operator with training examples, Insights queries) alongside concrete operator IDs, error codes, and parameter formats.	5 / 5
Workflow Clarity	Sequencing is present (numbered Step 1/Step 2 creation flow, the 5-stage How-It-Works pipeline), but validation checkpoints are absent or implicit, and the destructive 'DELETE the configuration and POST to recreate it' workaround carries no verification step — the rubric's destructive-operation cap at 3 applies.	3 / 5
Progressive Disclosure	The file is well-organized with clear section headers, but at ~617 lines it is a monolith: a distinct second API (Conversational Insights) and the 27-item Gotchas are inlined rather than split into one-level-deep reference files, and there are no references to this skill's own detail files (only links to sibling skills).	3 / 5
	Total	14 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that cleanly answers both what the skill does and when to use it, with concrete trigger phrases and good keyword coverage. Minor room to tighten generic capability terms and further distinguish from sibling Twilio conversation skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — 'conversation analysis', 'language operator pipelines', 'sentiment analysis', 'agent assist', 'cross-channel analytics', 'querying aggregated conversation insights' — with only minor gaps; not quite the comprehensive enumeration of anchor 5 and a few terms lean generic.	4 / 5
Completeness	Explicitly states the 'what' ('Twilio Conversation Intelligence development guide') and a concrete 'when' ('Use when building real-time or post-call conversation analysis, ... sentiment trends, escalation rates, dashboards'), matching the anchor-5 pattern of clearly answering both with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage including synonyms ('sentiment analysis' + 'sentiment trends', 'escalation rates', 'dashboards', 'agent assist'); 'language operator pipelines' is more jargon, and a few natural terms (transcription, call QA) are absent, so it falls just short of comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The named 'Twilio Conversation Intelligence' product is a clear niche, but the Related Resources point to adjacent skills (Conversation Orchestrator, Customer Memory) and triggers like 'conversation analysis'/'agent assist' carry minor overlap risk with those closely related skills.	4 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (618 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: openai/plugins
Path: plugins/twilio-developer-kit/skills/twilio-conversation-intelligence/SKILL.md
Commit: 1dc1958

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.