email

Send emails, buy forwarding inboxes, manage custom subdomains, and read messages programmatically via x402. USE FOR: - Sending emails (one-off or from custom addresses) - Buying a forwarding inbox (username@stableemail.dev) - Purchasing custom email subdomains (you@yourname.stableemail.dev) - Reading and managing inbox messages programmatically - Setting up catch-all forwarding for subdomains - Managing authorized signers for shared subdomains TRIGGERS: - "send email", "email this to", "notify by email" - "buy inbox", "forwarding address", "email inbox" - "custom domain", "subdomain", "email subdomain" - "read emails", "check inbox", "list messages" - "email address", "disposable email", "temporary email" ALWAYS use agentcash.fetch for stableemail.dev endpoints. IMPORTANT: Use exact endpoint paths from the Quick Reference table below.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

72%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 for every endpoint, and it is reasonably concise reference material. Its main weaknesses are workflow checklists without validation checkpoints for destructive operations and a large inlined API reference plus a broken getting-started reference.

Suggestions

Add validation/verification steps to destructive workflows — e.g., confirm the inbox status or refund transaction after /api/inbox/cancel, and verify a message is safe to remove before /api/inbox/messages/delete.

Move the large Quick Reference and Free Management Endpoints tables into a separate reference file and keep SKILL.md as an overview pointing to it, fixing the missing rules/getting-started.md link in the process.

De-duplicate the pricing information shared between the Quick Reference table and the Cost Estimation table to tighten the token budget.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean reference tables and executable examples with no padding about what email is, but the Quick Reference and Cost Estimation tables repeat much of the same pricing, so it is efficient with minor redundancy to trim. It is not a 3 because it largely assumes Claude's competence and avoids unnecessary explanation.	4 / 5
Actionability	Every endpoint ships a complete, copy-paste-ready agentcash.fetch MCP call with full request bodies (send, buy inbox, top up, cancel, retention, list, read, buy subdomain, catch-all, signers), covering the common cases exactly as the anchor requires.	5 / 5
Workflow Clarity	The Workflows section provides sequenced checklists (Quick Send, Professional Email, Programmatic Mailbox) but lacks explicit validation checkpoints for destructive operations such as 'Cancel and Refund' and 'Delete messages when processed', which caps this dimension at 3 per the destructive/batch guidance.	3 / 5
Progressive Disclosure	Section structure is reasonable, but ~25 rows of endpoint API reference are inlined in the body rather than split into a separate file, and the one external reference (rules/getting-started.md) points to a path that does not exist in the bundle, leaving references not cleanly backed by real files.	3 / 5
	Total	15 / 20 Passed

Description

100%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 third-person, concise, and lists concrete capabilities with an explicit USE FOR list and a thorough TRIGGERS block, fully answering both what the skill does and when to use it. It is distinct and unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Send emails, buy forwarding inboxes, manage custom subdomains, and read messages programmatically') plus catch-all forwarding and signer management — comprehensive coverage with no vague filler.	5 / 5
Completeness	Explicitly answers both 'what' (the capability sentence and USE FOR list) and 'when' (USE FOR + TRIGGERS with concrete trigger phrases), exactly matching the anchor for clearly answering both.	5 / 5
Trigger Term Quality	A dedicated TRIGGERS block covers natural phrases users say ('send email', 'notify by email', 'forwarding address', 'read emails', 'check inbox') plus synonyms ('disposable email', 'temporary email'), matching comprehensive coverage with synonyms.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (email via stableemail.dev/x402 with named addresses and subdomains) with distinct triggers, minimizing overlap with unrelated skills.	5 / 5
	Total	20 / 20 Passed

Validation

81%

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 — 13 / 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
relative_links	Relative link issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: Merit-Systems/agentcash-skills
Path: mcp/skills/email/SKILL.md
Commit: 522d5da

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.