twilio-call-recordings

Record Twilio voice calls correctly. Covers the critical distinction between Record verb (voicemail) and Dial record (call recording), dual-channel for QA, mid-call pause for PCI, Conference recording, and the ConversationRelay workaround. Use this skill whenever you need to capture call audio for compliance, QA, or analytics.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

80%Weight 40%Scale 1-3

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

A dense, highly actionable reference with no concept fluff and strong domain-specific gotchas. It loses points on workflow clarity (no validation feedback loop on the destructive delete) and progressive disclosure (a long monolith that could offload reference material into bundle files).

Suggestions

Add an explicit verification step after destructive operations, e.g. confirm the recording is gone via `client.recordings(recording_sid).fetch()` handling 404, to satisfy the destructive-operation feedback-loop requirement.

Move the recording-modes tables, Common Errors, and CANNOT list into a one-level-deep reference file (e.g. references/RECORDING-MODES.md) referenced from the body, to improve progressive disclosure.

Consider consolidating to a single canonical language per pattern with a note on SDK parity, or move the per-pattern Node.js blocks into a reference file, to reduce duplication.

Dimension	Reasoning	Score
Conciseness	No explanation of concepts Claude already knows; every section is concrete code or non-obvious domain gotchas (e.g. "record:true ... is silently ignored with ConversationRelay", "PCI Mode is IRREVERSIBLE and account-wide"), so each token earns its place despite the dual-language examples.	3 / 3
Actionability	Fully executable Python and Node.js examples with concrete values and callbacks, plus copy-paste-ready patterns for recording, pause/resume, listing, downloading, and deleting recordings — anchor-3 "copy-paste ready".	3 / 3
Workflow Clarity	Sections are well-structured and the callback checks `status == "completed"`, but there is no sequenced multi-step workflow with explicit validation checkpoints, and the destructive `client.recordings(recording_sid).delete()` lacks a verify/feedback loop — capping it at 2 per the rubric's destructive-operation rule.	2 / 3
Progressive Disclosure	Well-organized single-file sections with clear cross-skill links, but at ~270 lines content such as the recording-modes tables, Common Errors, and the CANNOT list is inline rather than split into one-level-deep reference files, and no bundle files are used for progressive disclosure.	2 / 3
	Total	10 / 12 Passed

Description

90%Weight 40%Scale 1-3

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, specific description that names concrete capabilities and gives an explicit use-trigger, with good natural trigger terms and a clear niche. The only weakness is the second-person phrasing in the trigger clause, which triggers the rubric's voice penalty on specificity.

Suggestions

Rephrase the trigger to third person to avoid the voice penalty, e.g. "Use this skill whenever call audio must be captured for compliance, QA, or analytics."

Consider adding common natural variations such as "record a phone call" or "call recording" near the trigger to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities ("dual-channel for QA, mid-call pause for PCI, Conference recording, and the ConversationRelay workaround"), which meets the anchor-3 bar, but the second-person trigger "you need to capture call audio" incurs the rubric's -1 voice penalty, capping it at 2 rather than 3.	2 / 3
Completeness	Explicitly answers both what ("Record Twilio voice calls correctly. Covers the critical distinction between Record verb (voicemail) and Dial record (call recording)...") and when ("Use this skill whenever you need to capture call audio for compliance, QA, or analytics"), with an explicit "Use this skill whenever..." trigger.	3 / 3
Trigger Term Quality	Natural user-facing terms are well covered — "Record Twilio voice calls", "call recording", and "capture call audio for compliance, QA, or analytics" — matching what a user would say when needing this skill; not merely technical jargon.	3 / 3
Distinctiveness Conflict Risk	A clear, narrow Twilio call-recording niche anchored on the distinctive Record-verb-vs-Dial-record framing, unlikely to trigger for adjacent skills it links out to (twilio-conference-calls, twilio-compliance-traffic).	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/twilio-developer-kit/skills/twilio-call-recordings/SKILL.md
Commit: 11c74d6

Reviewed: 17 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.