twilio-sendgrid-deliverability-advisor

Diagnostic and advisory skill for email deliverability problems. Use when a developer asks why emails are going to spam, not reaching the inbox, getting blocked, bouncing, or how to improve sender reputation — with or without a specified platform. Covers SendGrid-specific tooling: SPF, DKIM, DMARC, BIMI, IP warmup, list hygiene, bounce/spam rate thresholds, and Engagement Quality Score (SEQ). Do NOT use for Twilio Email (comms.twilio.com / Account SID + Auth Token) — use twilio-email-deliverability-advisor instead. Do NOT use for general email sending questions — use twilio-sendgrid-email-send (SendGrid) or twilio-email-deliverability-advisor instead.

Quality

84%

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

78%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 thorough, highly actionable diagnostic workflow with clear sequencing, concrete thresholds, and provider-specific reference data. Its main weakness is progressive disclosure: substantial reference tables live inline in a single file rather than being split into bundled reference files.

Suggestions

Move the 'Inbox Provider Requirements' and 'Blocklist Quick Reference' tables into separate bundled reference files (e.g. references/providers.md and references/blocklists.md) and link to them from the main body, so SKILL.md stays a lean overview.

Tighten the small amount of explanatory prose (e.g. 'ISPs treat new sending infrastructure with suspicion — no history = no trust', 'ISPs interpret low open rates as "unwanted"') to assumption-of-competence bullet points.

Add an explicit re-check/feedback step after the recommended immediate actions (e.g. 're-check SEQ and bounce rate 24-48h after applying fixes') to give the diagnostic workflow a validate→retry loop.

Dimension	Reasoning	Score
Conciseness	The body is information-dense — exact thresholds, provider requirements, blocklist tables — with little padding of concepts Claude already knows, fitting the 'efficient; minor instances of over-explanation' anchor. It is not 5 because a few lines over-explain (e.g. 'ISPs treat new sending infrastructure with suspicion — no history = no trust') and could be trimmed.	4 / 5
Actionability	It gives exact numeric thresholds, named tools (Google Postmaster Tools, SNDS, JMRP, MXToolbox, Spamhaus), concrete navigation paths (app.sendgrid.com → Settings → Sender Authentication), specific webhook event names, and the 41-day warmup schedule — fully actionable guidance for an instruction-only skill. It is not 4 because key cases are covered with specifics rather than minor gaps.	5 / 5
Workflow Clarity	A clear Step 0 → Step 5 sequence with explicit gates ("If Twilio Email: Stop", "If unclear: Ask exactly this") and a Foundation Checklist matches the 'clear sequence with most checkpoints present' anchor. It is not 5 because there is no true fix→retry feedback loop, only diagnostic branching.	4 / 5
Progressive Disclosure	The skill is well-sectioned internally but is a ~240-line monolithic SKILL.md with no bundle files; reference-grade material (the Inbox Provider Requirements and Blocklist Quick Reference tables) is inlined rather than split into separate files, matching the 'content that should be separate is inline' anchor. It is not 4 because there is no one-level-deep file reference structure at all.	3 / 5
	Total	16 / 20 Passed

Description

90%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, well-structured description that clearly states what it does, when to use it, and where its boundaries lie against sibling skills. The only soft spot is specificity: it leads with generic verbs ('diagnostic and advisory') and lists covered topics rather than enumerating distinct concrete actions.

Dimension	Reasoning	Score
Specificity	The description opens with only two action verbs ("Diagnostic and advisory skill") and otherwise enumerates covered topics (SPF, DKIM, DMARC, BIMI, IP warmup, list hygiene, thresholds, SEQ) rather than distinct concrete actions, matching the anchor that names the domain with 1-2 actions. It does not reach 4 because it never lists several specific actions comparable to 'extracts/fills/converts'.	3 / 5
Completeness	It explicitly answers both what ("Diagnostic and advisory skill for email deliverability problems… Covers SendGrid-specific tooling…") and when ("Use when a developer asks why emails are going to spam…") with concrete trigger phrases, matching the top anchor. It is not 4 because the 'when' is fully explicit rather than merely adequate.	5 / 5
Trigger Term Quality	It packs in natural user phrases — "emails going to spam," "not reaching the inbox," "getting blocked, bouncing," "how to improve sender reputation" — with synonym-level coverage, matching the comprehensive-natural-terms anchor. It is not below 5 because no common variation a user would actually say is missing.	5 / 5
Distinctiveness Conflict Risk	Explicit "Do NOT use for Twilio Email… use twilio-email-deliverability-advisor instead" and "Do NOT use for general email sending questions" carve out a clear SendGrid-deliverability niche with minimal conflict risk, matching the top anchor. It is not below 5 because boundary guidance is concrete and names the competing skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/twilio-developer-kit/skills/twilio-sendgrid-deliverability-advisor/SKILL.md
Commit: 1e28582

Reviewed: 9 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.