CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

twilio-send-message

Send messages via Twilio's Programmable Messaging API across all channels — SMS, MMS, RCS, and WhatsApp. Covers text messages, media, rich content (cards, carousels, buttons), template-based sends, Messaging Services, status callbacks, and WhatsApp's 24-hour service window. Use when the user wants to send a message — whether they say "send SMS", "text message", "branded message", "rich message", "WhatsApp message", "RCS message", "notification", or "alert". For picking the right channel for a use case, first consult twilio-messaging-channel-advisor.

72

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 strong, highly actionable reference: executable multi-language code, concrete error-code remediation, and honest limitations. Weaknesses are minor — repeated fallback explanations, a duplicated quickstart, and no explicit delivery-verification step in the workflow.

Suggestions

State the RCS→SMS fallback rule once (e.g. in the Key Patterns section) and reference it from the table, quickstart comment, and CANNOT section instead of restating it four times.

Show only Python in the Quickstart and note that the Node SDK takes the same call with camelCase params (messagingServiceSid), or move the Node variants to a reference file — the eight near-identical blocks are the largest token cost.

Add an explicit verify step after sending: check the returned message SID/status or confirm the status_callback received a delivered event, making the delivery-verification guidance operational rather than advisory.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence (no library/API tutorials, no PDF-style filler), but the RCS→SMS fallback rule is stated four times (overview table row, quickstart comment, 'Configure RCS→SMS fallback' section, CANNOT) and the Node quickstart repeats all four Python variants verbatim. It fits 'efficient; minor instances of over-explanation that could be trimmed' — not 5 because of that duplication, not 3 because nothing is genuinely padded.

4 / 5

Actionability

Fully executable, copy-paste-ready Python and Node examples for SMS, RCS, WhatsApp, and Messaging Service sends, plus concrete parameter-level patterns (media_url, content_sid with content_variables, status_callback) and an error table mapping codes to specific fixes. This matches the top anchor: executable code covering the common cases.

5 / 5

Workflow Clarity

A clear Prerequisites → Quickstart → Key Patterns → Common Errors sequence, with the error table and 'Always implement status callbacks' providing error-recovery feedback. It is not 5 because the send flow lacks an explicit delivery-verification checkpoint before/at completion, and not 3 because this is a single non-destructive API call where checkpoints are mostly present.

4 / 5

Progressive Disclosure

No bundle files exist, and the single file is well-sectioned with clearly signaled next-step skills (Next Steps, and inline pointers like 'See twilio-messaging-services'). It is not 5 because at ~185 lines the duplicated dual-language quickstart and full error table are inline content that could sit in reference files, and not 3 because structure and navigation are good with nothing buried.

4 / 5

Total

17

/

20

Passed

Description

96%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.

An exemplary description: third person, concrete capability list, explicit 'Use when' with natural trigger phrases, and explicit boundary routing to a sibling skill. The only minor risk is overlap with per-channel skills on channel-specific triggers.

DimensionReasoningScore

Specificity

The description enumerates concrete capabilities comprehensively: 'Send messages via Twilio's Programmable Messaging API across all channels — SMS, MMS, RCS, and WhatsApp' plus media, rich content (cards, carousels, buttons), template-based sends, Messaging Services, status callbacks, and the 24-hour service window. It matches the top anchor (multiple specific concrete actions, comprehensive coverage), not 4, since there are no meaningful coverage gaps.

5 / 5

Completeness

It explicitly answers 'what' (multi-channel message sending with enumerated coverage areas) and 'when' ('Use when the user wants to send a message — whether they say...') with concrete trigger phrases. This matches the anchor for both what and when explicitly; the 'when' clause prevents a score of 4 or lower.

5 / 5

Trigger Term Quality

Quotes natural user phrasings: 'send SMS', 'text message', 'branded message', 'rich message', 'WhatsApp message', 'RCS message', 'notification', or 'alert' — these are exactly what a user would say when they need this skill. Coverage is comprehensive with synonyms, matching the top anchor rather than 4 (no common natural terms missing).

5 / 5

Distinctiveness Conflict Risk

The Twilio message-sending niche is clear and it actively delegates channel selection ('first consult twilio-messaging-channel-advisor'), reducing conflict. However, triggers like 'WhatsApp message' overlap with the channel-specific skills the body references (e.g. twilio-whatsapp-send-message), so it is 'mostly distinct; minor overlap risk' — the anchor for 4 — rather than the minimal-conflict profile of 5.

4 / 5

Total

19

/

20

Passed

Validation

100%

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-send-message/SKILL.md

Reviewed

Table of Contents

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.