Agent skill

Email Deliverability Audit

by growthenginenowoslawski in growthenginenowoslawski/coldoutboundskills

Diagnostic audit for a running cold email program. An agent skill from growthenginenowoslawski/coldoutboundskills.

MITAuto-check passedBackend & APIs

Install Email Deliverability Audit

skills CLI
$ npx skills add growthenginenowoslawski/coldoutboundskills --skill email-deliverability-audit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install growthenginenowoslawski/coldoutboundskills email-deliverability-audit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/email-deliverability-audit .claude/skills/email-deliverability-audit && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
email-deliverability-audit
GitHub stars
753
Token cost
~3.4k tokens
SKILL.md length
1,454 words
Files
6 (incl. scripts, references)
Skills in repo
49
Repo updated
First seen
Licence
MIT

At a glance

Diagnostic audit for a running cold email program. An agent skill from growthenginenowoslawski/coldoutboundskills.

  • Works in 6 steps: Pull the inbox inventory → Check domain authentication → Pull sent + reply + bounce metrics per… → …
  • Reply rates drop
  • SKILL.md covers What it checks, The 1% rule — and the floors…, When to use and Inputs, plus 7 more sections
  • Runs TypeScript scripts from its folder; calls npx; needs SMARTLEAD_API_KEY

What it does

Email Deliverability Audit is an agent skill from growthenginenowoslawski/coldoutboundskills. Diagnostic audit for a running cold email program. Checks domain authentication (SPF/DKIM/DMARC), inbox health/reputation from Smartlead, bounce rate by inbox type, and optionally runs a spam placement test via Smartlead's Smart Delivery API. Outputs markdown report + CSV with per-domain/per-inbox scores and concrete action items. Use when reply rates drop, when bounces spike, when onboarding someone else's account, or as a weekly/monthly health check.

Its SKILL.md is about 3.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `references/dns-records.md`, `scripts/audit-inboxes.ts` and `scripts/audit-performance.ts`).

It sits in Backend & APIs, covering Email management, Transactional email and Cold outreach. The repository describes itself as: Open-source Claude Code skills for cold email and outbound sales. Grade campaigns, export Prospeo searches, scrape Google Maps — all from Claude Code. The licence is MIT.

When your agent uses it

  • Reply rates drop
  • Onboarding someone elses account
  • As a weekly/monthly health check

Example prompts

  • “/email-deliverability-audit”

Requirements

  • Node.js
  • A credential in SMARTLEAD_API_KEY

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Pull the inbox inventory
  2. Check domain authentication
  3. Pull sent + reply + bounce metrics per campaign/inbox
  4. (Optional) Run a Smart Delivery spam placement test
  5. Synthesize the report
  6. Act on the action items

What it can do on your machine

Read from SKILL.md and the folder at commit 25c5d85. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 4 files in scripts/ (TypeScript), which the agent can run.

    Shell commands in SKILL.md call:

    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • SMARTLEAD_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Email Deliverability Audit loads about 3.4k tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 121 tokens; SKILL.md has 1,454 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~121
When it runs · the whole SKILL.md, loaded when a task matches
~3.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from growthenginenowoslawski/coldoutboundskills at commit 25c5d85, republished under its MIT licence (© growthenginenowoslawski). 1,454 words, ~3,444 tokens.

Download SKILL.mdSave it as .claude/skills/email-deliverability-audit/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
email-deliverability-audit
description
Diagnostic audit for a running cold email program. Checks domain authentication (SPF/DKIM/DMARC), inbox health/reputation from Smartlead, bounce rate by inbox type, and optionally runs a spam placement test via Smartlead's Smart Delivery API. Outputs markdown report + CSV with per-domain/per-inbox scores and concrete action items. Use when reply rates drop, when bounces spike, when onboarding someone else's account, or as a weekly/monthly health check.

Email Deliverability Audit

If your positive reply rate is dropping and you don't know why, start here. Most of the time the problem is deliverability — your emails aren't reaching inboxes. This skill tells you what's broken.

What it checks

LayerWhatHow
DNS authSPF, DKIM, DMARC present on each sending domaindig commands
Inbox healthWarmup status, reputation, blocks, connection failuresSmartlead email-accounts API
Volume healthDaily sent trending, capacity utilizationSmartlead analytics
Send + reply rate per inboxSent count, reply count, reply rate % over lookback periodSmartlead campaign analytics
Bounce ratePer-inbox and per-domain bounce rate over last 30 daysSmartlead campaign analytics
Spam placementReal inbox-vs-spam test via Smartlead Smart Deliveryoptional

The 1% rule — and the floors that gate it

A healthy domain replies at 1% or better after 200 emails sent. Below 1% on a fair sample, something is broken, and if it stays broken the domain gets cancelled.

The 1% rule is one number: the same 1% that flags a domain here is the line that retires it in /inbox-lifecycle-manager. What separates "flag" from "cancel" is not a softer second threshold — it is the floors. Below a floor, the answer is "we don't know yet", which is a legitimate output rather than a failure.

JudgmentFloor before it counts
Reply rate200 sends in the window
Bounce rate50 sends
Bounce composition (which bucket)30 classified bounces for that domain
Any cancel decision30 days of domain age; unknown age counts as young
Placement test100-300 senders per test

Reporting 0.00% reply on 14 sends as a failure, or condemning a three-week-old domain that has not finished ramping, is how healthy domains get killed.

Reply rate (≥200 sends)Reading
≥ 1.5%Genuinely good. Leave it alone.
1.0 - 1.5%Healthy. The rule passes.
< 1.0%Burned. Hand to /inbox-lifecycle-manager — but only if it also clears the 200-send and 30-day floors.
0 replies on ≥150 sendsDecisive. A flat zero needs less sample than a low-but-nonzero rate.

Possible causes when a domain is below the line (the audit's root-cause suggestions try to pinpoint which):

  • Emails landing in spam — run the spam placement test
  • Domain reputation damaged — check DMARC reports and the bounce codes
  • Copy is broken — re-run /spam-word-checker; confirm with a control-fleet placement test
  • List is cold or wrong ICP — check bounce rate; if >3%, the list is the problem, not the domain
  • Inbox hasn't warmed enough — check warmup status and domain age
The domain-vs-copy isolation test

Low placement alone does not tell you whether the domain is burned or the copy is toxic. Run the same copy from a known-good control fleet:

Your fleetControl fleetVerdict
< 100%~100%Domain-side. Your sending infrastructure is the problem.
< 100%< 100%Copy. Rewrite before you replace a single domain.
≥ 85%≥ 85%Neither. Infrastructure is fine — this is targeting or offer.
control untestable—Assume copy. It is cheaper to fix and reversible.

When to use

  • Reply rate dropped by >30% week-over-week → run the full audit
  • Bounces spiked above 2% → run auth + spam-placement checks
  • Before scaling a campaign (make sure infrastructure is ready)
  • Monthly as routine hygiene
  • When taking over a Smartlead account you didn't set up

Inputs

  • SMARTLEAD_API_KEY (env)
  • Optional: scope the audit
    • --client-id=X (for sub-clients)
    • --campaign-id=X (audit only one campaign's inboxes)
    • --domain=example.com (audit only one domain)
    • --tag=active (audit only inboxes tagged active)

Steps

1. Pull the inbox inventory
bash
npx tsx scripts/audit-inboxes.ts --all --out=/tmp/audit/inboxes.csv

Outputs per inbox: id, email, domain, warmup_status, reputation, max_warmup/day, sent_today, smtp_ok, imap_ok, is_blocked, tags.

2. Check domain authentication
bash
npx tsx scripts/check-domain-auth.ts --from-csv=/tmp/audit/inboxes.csv --out=/tmp/audit/auth.csv

For each unique domain, runs:

bash
dig TXT <domain> +short                             # SPF
dig TXT _dmarc.<domain> +short                      # DMARC

# DKIM has NO single selector. Present if ANY of these resolves:
dig TXT   google._domainkey.<domain>    +short      # Google / Gmail-backed — the common one
dig CNAME selector1._domainkey.<domain> +short      # Microsoft 365 — a CNAME, TXT returns nothing
dig CNAME selector2._domainkey.<domain> +short      # Microsoft 365, second key
dig TXT   default._domainkey.<domain>   +short      # generic fallback, frequently empty

⛔ Never check default._domainkey alone. It is empty on most real fleets, and a default-only check reports every domain as "missing DKIM" — which routes genuinely burned domains to "fix your DNS" and wastes a week republishing records that already exist. The script tries all four and reports which one resolved.

Outputs: domain, spf_present, spf_strict, dkim_present, dmarc_present, dmarc_policy (none/quarantine/reject).

3. Pull sent + reply + bounce metrics per campaign/inbox
bash
npx tsx scripts/audit-performance.ts --days=30 --out=/tmp/audit/performance.csv

Walks all active campaigns, pulls per-inbox analytics for the last 30 days. Output columns: inbox_id, email, domain, type, tags, sent, replies, bounces, reply_rate_pct, bounce_rate_pct, flag_low_reply, flag_high_bounce.

Flagged automatically:

  • flag_low_reply = TRUE if sent ≥200 and reply_rate_pct < 1.0 (the 1% rule)
  • flag_high_bounce = TRUE if sent ≥50 and bounce_rate_pct > 3.0
4. (Optional) Run a Smart Delivery spam placement test
bash
npx tsx scripts/run-spam-test.ts --campaign-id=12345 --senders=100 --out=/tmp/audit/spam-test.json

This creates a real inbox-placement test via Smartlead's Smart Delivery API:

  • Uses the only available provider pools: G Suite + Office365 (provider_ids 20, 21)
  • Sends to ~200 seed mailboxes with 100 of your senders
  • Waits for completion (5-20 min)
  • Pulls: providerwise, spam-filter-details, dkim-details, spf-details, blacklist

Output shows: what % lands in Inbox vs Spam vs Promotions, broken down by your sender and the receiver provider. This is the ground truth.

5. Synthesize the report

Read the three CSVs (inboxes.csv, auth.csv, performance.csv) plus the spam-test JSON if you ran one, and write the report by hand in this shape. There is no generator script; the synthesis is the judgment call, and the template below is what it should look like:

# Deliverability Audit — 2026-04-17

## Summary

- 80 inboxes audited across 40 domains
- 3 inboxes blocked (4% of fleet)
- 5 domains missing DKIM
- 2 domains with DMARC policy=none (no enforcement)
- Fleet performance (last 30d):
    Sent:           42,384
    Replies:          523
    Overall reply rate: 1.23% (PASS — above 1% threshold)
    Bounces:           382
    Bounce rate:      0.90% (PASS — below 2%)
- 4 inboxes failed the 1% rule (sent ≥200, reply rate <1%)
- Spam placement (test run): 83% inbox / 14% spam / 3% tabs (ACCEPTABLE but not great)

## Critical issues (fix within 24h)

1. Domain trygrowth.co has no DMARC record. Add: v=DMARC1; p=none; rua=mailto:dmarc@trygrowth.co
2. Inbox sales@trygrowth.co blocked in warmup — likely flagged by warmup network. Rotate out of campaigns.
3. 12 inboxes have 0 daily sent today despite being in active campaigns. Check campaign schedule.
4. Inbox marketing@other.co failed the 1% rule: 347 sent, 1 reply (0.29% reply rate). Investigate:
   - Check spam placement for this inbox
   - Compare copy vs. a sibling inbox that's passing
   - Rotate inbox out if bad reputation is confirmed

## Warnings (fix within 1 week)

- 5 domains missing DKIM record at default._domainkey
- 3 inboxes reputation dropped "fair" → "bad"
- Spam filter trigger DKIM_INVALID firing 8% of the time — likely for a subset of domains

## Action items (prioritized)

1. [HIGH] Add missing DKIM records to: trygrowth.co, othergrow.co, ...
2. [HIGH] Rotate out blocked inboxes: sales@trygrowth.co, marketing@other.co, ...
3. [MED] Tighten DMARC to p=quarantine on all domains after 2 weeks of p=none observation
4. [MED] Replace 3 bad-reputation inboxes (tag them "retired", provision new)
5. [LOW] Re-run spam placement test after fixing DKIM issues
6. Act on the action items

Feed the action items into the right skills:

  • Missing DKIM / SPF → /zapmail-domain-setup-public to reconnect domains through Zapmail
  • Blocked inboxes → /smartlead-inbox-manager to tag "retired" and rotate in insurance
  • Campaign schedule issues → Smartlead campaign schedule settings
  • Bad copy flagged → /spam-word-checker on the campaign copy

Interpreting the numbers

Show full SKILL.md (584 more words)Show less
Bounce rates
  • <1% — Excellent. Healthy list.
  • 1-2% — Normal for cold. No action.
  • 2-3% — Yellow. Check list quality, might be old emails.
  • >3% — Red. Verify the list (MillionVerifier), consider pausing.
  • >5% — Stop immediately. You're damaging domain reputation.
Spam placement
  • >90% inbox — Great. Ship more.
  • 85-90% inbox — Healthy. This is the line a domain must clear to be considered good metal.
  • 70-84% inbox — Degraded. Look at spam-filter-details to see what's triggering.
  • <70% inbox — Red, and a hard gate: do not attach this domain to a campaign. Pause and fix auth + copy before sending more.

Test with 100-300 senders. Smaller samples swing by double digits run to run.

DMARC policies
  • None — Acceptable for first 2 weeks of a domain's life. After that, tighten.
  • Quarantine — Recommended long-term. Emails that fail auth land in spam.
  • Reject — Strictest. Only use after 30+ days of clean rua= reports confirming all legitimate mail passes.
Warmup reputation
  • Smartlead reports reputation as 0-100. Higher is better.
  • ≥98% — required before promoting a reserve inbox into a live campaign.
  • 80-98% — sending is fine, but don't promote fresh reserves at this level.
  • 50-80% — keep warming, don't use for critical sends.
  • <50% — don't send from this inbox; warmup peers aren't seeing it in their inboxes.

⚠️ Warmup switched OFF is not a reputation of zero — it is no reading at all. An inbox with warmup off reports nothing, so it cannot be evaluated. Treat it as held: out of capacity, not attached to campaigns, reported for a human. Do not silently turn warmup back on to make a number appear — that rewrites the signal you are trying to measure.

Common root causes

  • SPF too lax — v=spf1 +all whitelists everyone. Use v=spf1 include:zapmail.com ~all or similar.
  • DKIM missing — new domain, selector not published. Zapmail publishes at default._domainkey by default.
  • DMARC alignment failure — From-domain doesn't match SPF/DKIM domain. Usually a misconfigured reply-to or a 3rd-party sender.
  • Too many inboxes per domain — Gmail flags domains with >3-5 inboxes as suspicious. Keep it at 2/domain.
  • Judging a domain that is too young or too quiet — under 30 days old or under 200 sends, the numbers cannot distinguish a burned domain from an unlucky week. This is not a root cause; it is the absence of evidence, and it is the single most common way a healthy domain gets killed.
  • Aggressive warmup ramp — Jumping from 5 to 40/day in one week = flag. Ramp over 2-4 weeks.
  • Shared sending IP with spam traffic — Zapmail/most providers use shared pools. If someone else on your IP spammed, you suffer. Not much to do except wait for pool rotation.

What to do next

If any flag fired: /deliverability-incident-response → triage decision tree for whatever was flagged (low reply rate, high bounce, blocked inbox, etc).

If a domain is confirmed burned: /inbox-lifecycle-manager → the cancel/promote/buy decision, with the guards that stop you cancelling into a send shortfall.

If all clean: next Monday, run this again. This audit is the Monday task in /cold-email-weekly-rhythm.

Or wait: if you just applied fixes, wait 7 days then re-audit. Reputation changes propagate slowly.

  • /smartlead-inbox-manager — execute the action items (rotate, retag, warmup settings)
  • /zapmail-domain-setup-public — fix DNS/auth issues at the domain provider
  • /spam-word-checker — check copy for spam-triggering phrases
  • /deliverability-test-public — lighter-weight SMTP vs Gmail vs Outlook reply/bounce comparison
  • /inbox-lifecycle-manager — acts on the verdict: cancel, promote reserves, plan the buy

Scripts

  • scripts/audit-inboxes.ts — pull + format inbox inventory
  • scripts/check-domain-auth.ts — dig-based SPF/DKIM/DMARC checks
  • scripts/audit-performance.ts — per-inbox sent / replies / bounces / rates from campaign analytics (applies the 1% rule)
  • scripts/run-spam-test.ts — create + poll + pull Smart Delivery test

References

  • references/dns-records.md — SPF/DKIM/DMARC record templates + interpretation guide

© growthenginenowoslawski, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (scripts, references) in skills/email-deliverability-audit of growthenginenowoslawski/coldoutboundskills.

  • SKILL.md
  • references/dns-records.md
  • scripts/audit-inboxes.ts
  • scripts/audit-performance.ts
  • scripts/check-domain-auth.ts
  • scripts/run-spam-test.ts

Open the folder on GitHubat commit 25c5d85

Compare with similar skills

Email Deliverability Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Email Deliverability Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Email Deliverability Audit this skillgrowthenginenowoslawski/coldoutboundskills753—~3.4kAutomated safety check: PassMIT
Email AuditAgriciDaniel/claude-email130—~3kAutomated safety check: NotesMIT
Himalaya Email CLIPrismer-AI/PrismerCloud1.6k2 repos~2.3kAutomated safety check: PassMIT
Autopilottokencanopy/e2a193—~2.3kAutomated safety check: PassApache-2.0
Smtp Email Senderopenakita/openakita2k—~693Automated safety check: NotesAGPL-3.0
E2a Setuptokencanopy/e2a193—~820Automated safety check: PassApache-2.0

Similar skills

  • Email Audit

    AgriciDaniel/claude-email

    Audits email domain deliverability setup (SPF, DKIM, DMARC, MX records, blacklists, TLS) and generates health score (0-100) with prioritized fix list.

    130 GitHub stars~3k tokensUpdated 4 mo ago
    Backend & APIsAuto-check: notes
  • Himalaya Email CLI

    Prismer-AI/PrismerCloud

    Operates a mailbox from the terminal with the external Himalaya CLI over IMAP, SMTP, Notmuch or Sendmail, separate from any built-in email gateway adapter.

    1.6k GitHub starsUsed in 2 repos~2.3k tokens
    Backend & APIsAuto-check passed
  • Autopilot

    tokencanopy/e2a

    Conversationally configure and operate a policy-first, always-on local e2a email agent.

    193 GitHub stars~2.3k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Smtp Email Sender

    openakita/openakita

    Send emails via SMTP (Gmail, Outlook, etc.). An agent skill from openakita/openakita.

    2k GitHub stars~693 tokensUpdated 17 days ago
    Backend & APIsAuto-check: notes
  • E2a Setup

    tokencanopy/e2a

    A skill your agent uses when a user wants to connect or authorize the e2a MCP server, select or create an agent inbox, verify first-run readiness, or set up a custom email domain.

    193 GitHub stars~820 tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Cold Outreach

    ericrisco/rsc-harness

    A skill your agent uses when writing a cold email or LinkedIn DM to a stranger and its cadence: first-touch copy under a word ceiling, 4-7 step bump sequences, per-inbox volume and warm-up limits…

    180 GitHub stars~4.1k tokensUpdated yesterday
    Sales & SupportAuto-check passed

More from growthenginenowoslawski/coldoutboundskills

All 49 skills in this repo
  • Icp Onboarding

    growthenginenowoslawski/coldoutboundskills

    Conversational intake for cold email campaigns. An agent skill from growthenginenowoslawski/coldoutboundskills.

    753 GitHub stars~1.9k tokensUpdated 5 days ago
    Auto-check passed
  • List Builder

    growthenginenowoslawski/coldoutboundskills

    META skill — build the largest possible qualified lead list for any request, end to end.

    753 GitHub stars~4.7k tokensUpdated 5 days ago
    Auto-check: notes
  • Auto Research Public

    growthenginenowoslawski/coldoutboundskills

    Autonomous cold email campaign launcher. An agent skill from growthenginenowoslawski/coldoutboundskills.

    753 GitHub stars~2.9k tokensUpdated 5 days ago
    Auto-check passed
  • Blitz List Builder

    growthenginenowoslawski/coldoutboundskills

    Use the Blitz API to find decision-makers at specific companies when you already have a list of company domains.

    753 GitHub stars~2k tokensUpdated 5 days ago
    Auto-check passed
  • Deliverability Test Public

    growthenginenowoslawski/coldoutboundskills

    Compare reply rates, bounce rates, and positive reply rates broken down by inbox type (SMTP / Gmail / Outlook) for a Smartlead account.

    753 GitHub stars~1k tokensUpdated 5 days ago
    Auto-check passed
  • Disco Like

    growthenginenowoslawski/coldoutboundskills

    Find lookalike companies via DiscoLike's 65M+ business domain database.

    753 GitHub stars~1.7k tokensUpdated 5 days ago
    Auto-check passed

Questions about Email Deliverability Audit

What does Email Deliverability Audit do?

Diagnostic audit for a running cold email program. An agent skill from growthenginenowoslawski/coldoutboundskills. Email Deliverability Audit is an agent skill from growthenginenowoslawski/coldoutboundskills. Diagnostic audit for a running cold email program.

When should I use Email Deliverability Audit?

Email Deliverability Audit fits situations like: reply rates drop; onboarding someone elses account; as a weekly/monthly health check.

How do I install Email Deliverability Audit in Claude Code?

Run `npx skills add growthenginenowoslawski/coldoutboundskills --skill email-deliverability-audit -a claude-code`. Or copy the skill folder (skills/email-deliverability-audit in growthenginenowoslawski/coldoutboundskills) into .claude/skills/email-deliverability-audit in your project. Claude Code loads it when a task matches its description.

How do I install Email Deliverability Audit in Codex?

Run `npx skills add growthenginenowoslawski/coldoutboundskills --skill email-deliverability-audit -a codex`. Or copy the skill folder (skills/email-deliverability-audit in growthenginenowoslawski/coldoutboundskills) into .agents/skills/email-deliverability-audit in your project. Codex loads it when a task matches its description.

Can I use Email Deliverability Audit in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add growthenginenowoslawski/coldoutboundskills --skill email-deliverability-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/email-deliverability-audit, .gemini/skills/email-deliverability-audit, .github/skills/email-deliverability-audit and .opencode/skills/email-deliverability-audit in your project.

What does Email Deliverability Audit need to run?

Going by SKILL.md and its folder, Email Deliverability Audit needs TypeScript for the scripts in its folder, the command-line tools its instructions call (npx) and credentials named SMARTLEAD_API_KEY. Our summary lists: Node.js; A credential in SMARTLEAD_API_KEY.

Does Email Deliverability Audit access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Email Deliverability Audit safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Email Deliverability Audit use?

Email Deliverability Audit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Email Deliverability Audit use?

About 3.4k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.5k tokens, read only when the agent opens those files.

What are the alternatives to Email Deliverability Audit?

Skills that share tags, products or a category with Email Deliverability Audit: Email Audit (AgriciDaniel/claude-email, 130 stars), Himalaya Email CLI (Prismer-AI/PrismerCloud, 1.6k stars), Autopilot (tokencanopy/e2a, 193 stars) and Smtp Email Sender (openakita/openakita, 2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Email Deliverability Audit?

growthenginenowoslawski (a GitHub user) maintains it in growthenginenowoslawski/coldoutboundskills, which has 753 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 5, 2026.

Source: growthenginenowoslawski/coldoutboundskills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.