email-campaign-audit

Stars4

Forks0

UpdatedJuly 18, 2026 at 15:25

Audit email campaigns and transactional email for weight and waste — heavy image templates, remote assets fetched per open, tracking-pixel sprawl, missing plain-text alternatives, send-volume hygiene (unengaged segments, over-frequency). Use this skill whenever the user shares email templates or campaign stats, works on newsletters or transactional email at scale, or asks about email sustainability, deliverability weight, or list hygiene. Part of Lean Agentic AI Skills; emits lean-findings.json.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Source

navveenb

navveenb/lean-agentic-ai-skills

View GitHub Repository View Creator Repositories

Download

Related occupationsSOC

Based on SOC occupation classification

Market Research Analysts and Marketing SpecialistsBusiness and Financial Operations Occupations·SOC 13-1161

File Explorer

2 files

SKILL.md

readonly

name

email-campaign-audit

description

Email Campaign Audit

Subject type: emit subject.type: "email-campaign" in findings.

Producer skill. Input: email templates (HTML), campaign stats (list size, send frequency, open/engagement rates), ESP configuration. Output: lean-findings.json.

An email's weight is multiplied by every recipient, every send — a heavy newsletter to a large list moves web-page-scale bytes weekly, then gets stored in millions of inboxes indefinitely. And the cheapest byte in email is the message never sent to someone who stopped reading.

Signatures

Sends to the unengaged — segments with no opens/clicks across many sends still receiving every campaign. High: 100% of those bytes and storage buy zero value, and it damages sender reputation too (a rare finding where efficiency and deliverability point the same way). Evidence: engagement cohort stats. Fix: sunset policy — re-permission campaign, then suppress; state the list-size honesty (smaller engaged list beats larger dead one).
Image-heavy templates — decorative full-width imagery, text rendered as images, uncompressed assets. High at list scale. Evidence: template asset inventory with byte sizes. Fix: compress, size to email width, HTML/CSS instead of image-text (accessibility bonus).
No plain-text alternative — HTML-only sends; text-part absent. Medium (some clients then fetch the heavy part unnecessarily; deliverability cost too). Fix: proper multipart with a real text version.
Tracking sprawl — multiple tracking pixels, per-link redirect chains through several domains, heavy analytics scripts in templates (mostly stripped by clients, still shipped). Medium. Fix: single pixel, direct links where measurement isn't needed; name the analytics trade-off honestly.
Remote assets fetched per open — large hero images loaded from origin on every open with no CDN caching headers. Medium. Fix: CDN + long cache-control on immutable campaign assets.
Over-frequency — send cadence beyond engagement's support (opens declining with frequency in the stats). Medium; this is demand-shaping for email. Fix: preference centers, frequency capping.
Attachment habits — PDFs attached to bulk sends where a link serves. Medium: attachment bytes × recipients, stored forever in every inbox.
Unbounded retention of campaign archives — every variant and asset kept hot at the ESP. Low; pairs with storage-lifecycle-audit logic.

Cost signal (countable)

Cost drivers: ESP send volume (emails/month) and asset egress GB — both countable from campaign stats and template weights (template bytes × recipients is arithmetic on counted numbers, so it is quotable). Suppressing dead segments reduces the send-volume driver directly; that delta is countable before/after.

Honesty rules

Engagement-based suppression trades reach for efficiency — marketing owns that call; present it as a finding with the reputational co-benefit, not a mandate. Inbox-side storage impact is real but unmeasurable from your side: directional language only. Template byte counts: measured from the actual assets, never estimated.

Not this skill's job

The landing pages emails link to (web-carbon-audit), the ESP's infrastructure (their footprint disclosures), marketing strategy beyond efficiency (the team's call).

More from this repository

same repository

agentic-loop-auditor

navveenb/lean-agentic-ai-skills

Audit agent frameworks and agentic workflows for token-burning loop pathologies — unbounded retries, excessive planning depth, tool-call thrashing, context snowballing, missing loop budgets and kill switches. Use this skill whenever the user shares agent configs or traces (LangChain/LangGraph, CrewAI, AutoGen, custom loops), complains an agent is slow or expensive, or is designing any autonomous/multi-step agent. Part of Lean Agentic AI Skills; emits lean-findings.json.

2026-07-184

ai-eval-efficiency-audit

navveenb/lean-agentic-ai-skills

Audit AI evaluation infrastructure for wasted compute — full benchmark suites re-run on unchanged cases, LLM-as-judge grading without caching, oversized judge models, redundant eval passes per commit, and missing result reuse. Use this skill whenever the user shares eval harness configs or CI eval steps, complains that evals are slow or expensive, mentions LLM-as-judge costs, or runs benchmark suites on every change. Part of Lean Agentic AI Skills; emits lean-findings.json.

2026-07-184

api-efficiency-audit

navveenb/lean-agentic-ai-skills

Audit API design for chattiness and over-fetching — REST endpoints requiring N calls per screen, GraphQL resolvers with N+1 fan-out, default-everything payloads, missing pagination and field selection, provider-side polling where webhooks serve, and uncompressed responses. Use this skill whenever the user shares API schemas (OpenAPI, GraphQL SDL), resolver code, endpoint designs, or asks why clients make too many calls or payloads are heavy. Part of Lean Agentic AI Skills; emits lean-findings.json.

2026-07-184

caching-strategy-designer

navveenb/lean-agentic-ai-skills

Design caching layers so work is done once, not per request — HTTP/CDN caching, application-level caches (Redis/Memcached), computed-result caching, and cache-invalidation strategy. Use this skill whenever the user wants to add caching, asks why the same work is recomputed, designs a read-heavy system, or an audit skill (db-efficiency-audit, web-carbon-audit) flags uncached repeated work. Part of Lean Agentic AI Skills; emits a cache design plus lean-findings.json.

2026-07-184

carbon-aware-scheduler

navveenb/lean-agentic-ai-skills

Design time-shifting of flexible workloads (batch jobs, CI, training, backups, crons) to hours and regions when grid electricity is cleanest, using carbon-intensity signals like Electricity Maps, WattTime, or the Carbon Aware SDK. Use this skill whenever the user mentions carbon-aware computing, scheduling flexible/deferrable jobs, demand shifting, running workloads when energy is clean, or asks how to reduce the carbon intensity (not just amount) of their compute. Part of Lean Agentic AI Skills; emits schedule designs plus lean-findings.json.

2026-07-184

carbon-budget-designer

navveenb/lean-agentic-ai-skills

Design per-feature and per-service efficiency budgets — page-weight budgets, token budgets per AI feature, query budgets per endpoint, GPU-hour budgets per training project — with owners, review checkpoints, and enforcement hooks. Use this skill whenever the user wants sustainability targets for teams, asks how to keep efficiency from regressing organizationally, mentions performance-budget-style governance for carbon/energy, or is setting engineering standards. Part of Lean Agentic AI Skills; an advisor emitting budget definitions plus lean-findings.json.

2026-07-184