twilio-reliability-patterns

Handle rate limits, retries, and failures when building on Twilio at scale. Covers 429 exponential backoff with jitter, per-number throughput limits, StatusCallback resilience, thin-receiver pattern, and fallback chains. Use this skill whenever sending messages or making calls at volume, or when building production-grade Twilio integrations.

Quality

82%

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

76%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 reference with executable code and concrete limits throughout. Its main gap is the batch bulk-send flow, which lacks explicit validation/verification checkpoints; conciseness is good with minor trimmable prose.

Suggestions

Add a validation/verification checkpoint to the bulk_send workflow — e.g. dry-run a small batch, verify opt-in consent and quiet-hours before dispatch, and reconcile sent vs failed counts afterward — so the batch flow has a feedback loop.

Trim the Overview marketing prose ('This skill teaches the patterns that prevent production failures') and the redundant '429 concurrency errors are not well documented' line to tighten token efficiency.

Consider moving the throughput and voice-concurrency reference tables into a separate references/ file linked from the body, which would improve progressive disclosure for this 280-line skill.

Dimension	Reasoning	Score
Conciseness	Largely lean — dense code and tables with minimal padding — but the Overview prose ('This skill teaches the patterns that prevent production failures') and a few redundant explanatory asides could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste-ready code in both Python and Node.js for backoff, bulk send, thin-receiver, and fallback, plus concrete limit tables and parameter specs covering the common cases.	5 / 5
Workflow Clarity	Patterns are clearly numbered and a monitoring checklist provides checkpoints, but the bulk_send batch operation has no validation/verification or result-checking feedback loop, capping workflow clarity at 3 per the batch-operations rule.	3 / 5
Progressive Disclosure	Well-organized into clearly headed sections (numbered patterns, tables, checklist) with cross-links to sibling skills; no bundle files exist so everything is inline, but the structure makes navigation easy despite minor gains from splitting reference tables out.	4 / 5
	Total	16 / 20 Passed

Description

88%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, specific description that names concrete patterns and gives explicit, natural trigger conditions for when to use it. Voice is appropriately third-person and it avoids vague fluff. It could add a few synonyms (throttling/quota) and tighten distinctiveness against sibling Twilio skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — '429 exponential backoff with jitter, per-number throughput limits, StatusCallback resilience, thin-receiver pattern, and fallback chains' — giving comprehensive, specific coverage rather than generic actions.	5 / 5
Completeness	Explicitly answers both what (the enumerated reliability patterns) and when ('Use this skill whenever sending messages or making calls at volume, or when building production-grade Twilio integrations') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural terms a user would say ('rate limits', 'retries', '429', 'at volume', 'production-grade Twilio'), but misses common synonyms like 'throttling', 'quota', or 'API limits' that would push it to comprehensive.	4 / 5
Distinctiveness Conflict Risk	The scale/reliability framing ('at scale', '429 backoff', 'thin-receiver') carves a clear niche, but it sits in a family of sibling Twilio skills (messaging-services, send-message) referenced in the body, creating minor overlap risk.	4 / 5
	Total	18 / 20 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-reliability-patterns/SKILL.md
Commit: 1e28582

Reviewed: 10 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.