CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

email-deliverability

Make sure email actually reaches inboxes. Use this skill when setting up email authentication (SPF, DKIM, DMARC), diagnosing emails landing in spam, planning a domain reputation strategy, monitoring sender reputation, or hardening against email spoofing. Triggers on email deliverability, SPF, DKIM, DMARC, spam folder, sender reputation, mailbox provider, soft bounces, bounce rate, BIMI, MTA-STS, deliverability audit. Also triggers when a marketing or transactional email isn't reaching users.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is email-deliverability in rampstackco/claude-skills

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 lean, highly actionable reference with copy-paste commands, record templates, and numeric targets, anchored by a well-validated DMARC rollout loop. Weaknesses are modest: a few known-concept explanations, missing verification checkpoints in the non-authentication workflow steps, and an overview that could offload more detail (BIMI, rollout steps) to reference files. The single reference file is well-chosen but thin for a three-pillar domain.

Suggestions

Trim known-concept explanations — the full acronym expansions (e.g. "Domain-based Message Authentication, Reporting, and Conformance") and generic statements like "DKIM proves the message wasn't modified in transit" — since Claude already knows these.

Add verification checkpoints to Steps 4-6, e.g. re-check bounce and complaint rates after list-hygiene changes, and A/B test content flags via mail-tester.com before and after a content audit.

Move the BIMI requirements and the Step 2 DMARC fix order (which duplicates the playbook reference's scope) into references/dmarc-rollout-playbook.md or a dedicated reference, keeping the overview to a summary pointer.

DimensionReasoningScore

Conciseness

The body is dense and imperative ("Get email into inboxes, not spam folders. Set up authentication. Monitor reputation."), but includes a few explanations Claude already knows, e.g. the full acronym expansion "Domain-based Message Authentication, Reporting, and Conformance" and "DKIM proves the message wasn't modified in transit and that the sender controls the domain". Anchor 4 fits: efficient with minor instances of over-explanation that could be trimmed; not 5 since not every token earns its place.

4 / 5

Actionability

Fully executable guidance throughout: copy-paste dig commands ("dig +short txt _dmarc.example.com"), complete TXT record templates, exact thresholds ("target: under 2%", "under 0.1%"), a concrete rollout schedule ("pct=10", "start at 50/day, 2x daily"), and named tools (Google Postmaster Tools, dmarcian, mail-tester). Matches anchor 5's copy-paste-ready commands covering the common cases; no meaningful execution gaps for an instruction-only skill.

5 / 5

Workflow Clarity

A clear 8-step sequence where the risky core (DMARC) has explicit validation ("Verify lookup count is under 10", "check headers for dkim=pass", "Watch reports for at least 2-4 weeks") and a monitor→fix→escalate feedback loop. Anchor 4 fits rather than 5 because steps 4-6 (list hygiene, content audit, growth) lack verification checkpoints, e.g. no re-check of complaint rate after hygiene fixes or before/after content test.

4 / 5

Progressive Disclosure

Good structure with one clearly signaled, one-level-deep reference (references/dmarc-rollout-playbook.md, verified to exist, with a description of its contents) that keeps the deep DMARC rollout detail out of the overview. Anchor 4 rather than 5 because the ~275-line body still inlines content that could be split (BIMI requirements, and Step 2's DMARC fix order that overlaps the playbook's scope), and a multi-pillar domain is served by only one reference file.

4 / 5

Total

17

/

20

Passed

Description

95%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 description that explicitly states both capability and usage triggers with concrete, natural keyword coverage including synonyms. The action list is specific and the domain is clearly delineated from adjacent skills. Only minor improvement possible in covering list hygiene and bounce-handling actions.

DimensionReasoningScore

Specificity

Lists five concrete actions with named protocols ("setting up email authentication (SPF, DKIM, DMARC)", "diagnosing emails landing in spam", "monitoring sender reputation", "hardening against email spoofing"), with minor gaps such as list hygiene and bounce handling absent from the action list. Not a 5 because coverage of the domain's actions is not fully comprehensive; well above anchor 3's 1-2 actions.

4 / 5

Completeness

Explicitly answers both what ("Make sure email actually reaches inboxes" plus the enumerated actions) and when ("Use this skill when...", "Triggers on...", "Also triggers when...") with concrete trigger phrases. Exact match to anchor 5; anchor 4's 'when could be more explicit' does not apply.

5 / 5

Trigger Term Quality

"Triggers on email deliverability, SPF, DKIM, DMARC, spam folder, sender reputation, mailbox provider, soft bounces, bounce rate, BIMI, MTA-STS, deliverability audit" plus "when a marketing or transactional email isn't reaching users" covers natural phrasing and synonyms ("spam folder" / "landing in spam" / "isn't reaching users"). Matches anchor 5's comprehensive coverage including synonyms; no common variant is missing.

5 / 5

Distinctiveness Conflict Risk

The niche is unambiguous — domain-specific protocol acronyms (SPF, DKIM, DMARC, BIMI, MTA-STS) are trigger terms that only apply to email deliverability, giving minimal conflict risk with other skills. Matches anchor 5; not anchor 4 since no closely related skill would plausibly capture these triggers.

5 / 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

rampstackco/claude-skills

Path

dist/codex/.agents/skills/email-deliverability/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.