agent-email-inbox

Use when building any system where email content triggers actions — AI agent inboxes, automated support handlers, email-to-task pipelines, or any workflow processing untrusted inbound email. Always use this skill when the user wants to receive emails and act on them programmatically, even if they don't mention "agent" — the skill contains critical security patterns (sender allowlists, content filtering, sandboxed processing) that prevent untrusted email from controlling your system.

Quality

76%

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 ./skills/agent-email-inbox/SKILL.md

Quality

Content

75%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.

The body is highly actionable with complete executable examples and a clear sequenced workflow backed by well-organized references. Its main weakness is moderate verbosity in rationale sections that re-explain concepts Claude already knows.

Suggestions

Trim the "Why Webhook-Based Receiving?" rationale bullets to one line or remove it; Claude already understands webhook vs polling trade-offs.

Remove the inlined Level 1 Strict Allowlist code block from the body since it duplicates references/security-levels.md, keeping only the link.

Add an explicit validate-before-proceed checkpoint in the Quick Start flow between webhook creation and agent processing.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with actionable tables and code, but sections like "Why Webhook-Based Receiving?" and "Core principle" explain concepts (webhooks vs polling) Claude already knows and could be trimmed.	3 / 5
Actionability	Fully executable copy-paste-ready code for Next.js and Express webhook endpoints, concrete MX/DNS tables, exact SDK version requirements, and explicit environment-variable examples cover the common cases.	5 / 5
Workflow Clarity	A clear 7-step Quick Start sequence with validation present (webhook signature verification, security-level selection before processing, a testing checklist); minor gaps in explicit validate-then-proceed feedback loops within the main flow.	4 / 5
Progressive Disclosure	Well-organized sections with clearly signaled one-level-deep references to security-levels.md, webhook-setup.md, and advanced-patterns.md; minor gap is Level 1 code inlined in the body duplicating the security-levels reference.	4 / 5
	Total	16 / 20 Passed

Description

78%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.

The description is well-constructed with explicit trigger guidance and a clear security-focused niche, though the capability framing leans on use-case enumeration rather than crisp action verbs. It clearly answers both what and when.

Dimension	Reasoning	Score
Specificity	Names the domain (email-triggered agent systems) and a few concrete capabilities ("sender allowlists, content filtering, sandboxed processing"), but the performed actions are framed generically as "act on them programmatically" rather than enumerating concrete verbs.	3 / 5
Completeness	Explicitly answers both what (build systems where email triggers actions with security patterns) and when ("Use when building any system...", "Always use this skill when the user wants to receive emails and act on them programmatically") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural trigger phrases ("AI agent inboxes", "automated support handlers", "email-to-task pipelines", "receive emails and act on them programmatically") cover the common ways users would request this, though a few synonymous phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche around inbound email triggering agent actions with security, distinct from generic sending skills; minor overlap risk with broad "any workflow processing untrusted inbound email" phrasing.	4 / 5
	Total	16 / 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
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: resend/resend-skills
Path: skills/agent-email-inbox/SKILL.md
Commit: 865a368

Reviewed: 1 day 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.