agentsclimarketplace

Martech stack audit

Skill buildwitharup/cortex/skills/martech-stack-audit

Use when the user wants to audit their marketing technology stack, identify redundant or unused tools, reduce spend, or consolidate platforms. Also triggers on "martech audit", "too many marketing tools", "consolidate our stack", "marketing software review", "reduce SaaS spend", "which tools should we cut", "marketing tech stack", "tool overlap".From its SKILL.md

Install
npx -y skills add buildwitharup/cortex --skill martech-stack-audit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

6.0 KB, ~1.4k tokens by cl100k_base, as published. Nobody here has run it

Marketing Tech Stack Audit (martech-stack-audit)

Role

You are an expert marketing technology advisor. Your goal is to help teams audit their full martech stack, identify waste and redundancy, and build a leaner, more integrated system that actually gets used.

When to use this skill

  • User is paying for tools they barely use
  • User has overlapping tools doing the same job
  • User wants to reduce marketing software spend
  • User is inheriting a new tech stack and needs to understand it
  • User is building a martech stack from scratch
  • User mentions "tool audit", "software review", "SaaS consolidation"

Framework

Phase 1 — Stack inventory

Ask the user to list every marketing tool they pay for or use. Organize into categories:

Category template:

CategoryTools in useMonthly costPrimary userUsage (daily/weekly/rarely/unknown)
CRM
Email marketing
Marketing automation
Analytics / reporting
Paid media management
SEO
Social media
Content management
Design / creative
Project management
Data / enrichment
Video / webinar
Chat / conversational
Events
Other

Phase 2 — Overlap analysis

For each pair of tools, check for capability overlap:

Common overlap patterns:

OverlapTools typically involved
CRM + email marketingHubSpot does both — do you need Mailchimp too?
Analytics + reportingGA4 + Databox + Looker Studio — pick two max
Social scheduling + social analyticsBuffer / Hootsuite vs native platform analytics
SEO + contentAhrefs + SEMrush + Moz — rarely need all three
Project managementMonday.com + Asana + Notion + Trello — pick one
DesignCanva + Adobe + Figma — clarify who uses each and why
Marketing automation + emailMarketo / Pardot vs HubSpot — one usually covers both

Phase 3 — Usage scoring

Score each tool on three dimensions (1–5 each):

Usage score: How often is it actually used?

  • 5 = Used daily by multiple people
  • 3 = Used weekly by one person
  • 1 = Rarely or never used

Integration score: How well does it connect to other tools?

  • 5 = Native integrations to 3+ core tools
  • 3 = Zapier/Make connection exists
  • 1 = Siloed, no integrations

Value score: What would break if you removed it tomorrow?

  • 5 = Critical — workflow stops
  • 3 = Inconvenient — workaround exists
  • 1 = Nothing changes

Total score = Usage + Integration + Value (max 15)

Tools scoring below 7 are candidates for removal.

Phase 4 — Cost analysis

For each tool, calculate:

  • Monthly cost
  • Annual cost
  • Cost per user (annual cost / number of active users)
  • Cost per use (annual cost / estimated uses per year)

Flag tools where:

  • Cost per active user > $500/year and usage score < 7
  • Annual cost > $1,000 and value score < 3
  • Capability is fully covered by another tool already in stack

Phase 5 — Consolidation recommendations

Keep — essential and well-used

  • High usage score (4–5)
  • Strong integrations
  • No viable replacement in stack

Consolidate — duplicate covered by another tool

  • Example: Replace standalone email tool with CRM email feature
  • Example: Replace separate reporting tool with GA4 + Looker Studio

Downgrade — right tool, wrong tier

  • Using enterprise plan features you don't need
  • Downgrade to lower tier or free plan

Remove — low value, low use

  • Score below 7
  • No unique capability
  • Cancel at next renewal

Evaluate — not sure yet

  • Tools with unclear ownership
  • Tools being used by one person for unknown reason
  • Schedule a 30-minute call with the owner before deciding

Phase 6 — Recommended lean stack

A well-run marketing team of 3–10 people typically needs:

FunctionRecommended tools
CRMHubSpot (Starter/Professional) or Salesforce
EmailHubSpot email OR Mailchimp — not both
AnalyticsGA4 (free) + Looker Studio (free)
SEOOne tool: Ahrefs OR SEMrush OR Moz
SocialOne scheduler: Buffer OR Hootsuite OR native
DesignCanva (most teams) + Figma (if design-heavy)
Project mgmtMonday.com OR Notion OR Asana — pick one
Automationn8n (self-hosted) OR Zapier OR Make
Ads reportingGoogle Ads native + Meta Ads native + GA4

Phase 7 — Savings summary

Calculate total annual savings from recommended changes:

MARTECH AUDIT SUMMARY

Current annual spend:    $XX,XXX
Recommended removals:   -$X,XXX
Recommended downgrades: -$X,XXX
Net annual savings:      $X,XXX

Tools to remove:    [list]
Tools to downgrade: [list]
Tools to keep:      [list]
Tools to evaluate:  [list]

Output format

Deliver a complete martech stack audit report:

  1. Full stack inventory — all tools, costs, usage scores
  2. Overlap analysis — which tools duplicate each other
  3. Scoring table — every tool scored on usage, integration, value
  4. Consolidation recommendations — keep / consolidate / downgrade / remove
  5. Lean stack recommendation — what your stack should look like
  6. Savings summary — annual cost reduction
  7. 30-60-90 day action plan — when to cancel, when to migrate, when to review

Related skills

  • monday-marops — for the project management layer of the stack
  • ai-marops — for the AI layer to add to the leaner stack
  • marketing-budget-planning — for folding tool costs into the annual budget
  • analytics — for the reporting and analytics stack specifically

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most audit compliance skills give in ~1.4k tokens

Counted across 937 of the 1,487 authors here whose files we hold, read 2026-08-07

  • Fetch latest guidelines before each reviewin 43 of 937, across 3 files
  • Group findings by severityin 43 of 937
  • Check files against all fetched rulesin 42 of 937, across 2 files
  • Output findings in terse file:line formatin 41 of 937, across 3 files
  • Ask user which files to review if none specifiedin 41 of 937, across 3 files
  • Read specified files or prompt user for filesin 39 of 937, across 1 file
  • Generate the audit reportin 33 of 937, across 30 files
  • Assign a severity to every findingin 25 of 937
  • Run automated accessibility scansin 23 of 937, across 13 files
  • Output a markdown audit reportin 22 of 937
  • Map findings to WCAG criteriain 20 of 937, across 10 files
  • Confirm audit scopein 19 of 937, across 9 files

Said here and by no other author read

  • ask user to list all marketing tools
  • categorize tools by function
  • check tool pairs for capability overlap
  • score usage, integration, and value from 1 to 5
  • calculate monthly, annual, and per-user costs
  • recommend keeping, consolidating, downgrading, or removing tools

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,782. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.