marketing-audit
Skill6 starsChanged 4 months agoMITView on GitHub
Scores the whole marketing function across seven layers (research, positioning, offer, channels, funnel, creative, measurement), ranks the gaps by revenue impact, and hands back a 90-day fix order. Use when marketing feels busy but revenue is flat, or before committing budget to a new plan.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Insightful-Pipe/marketing-strategy-skillstheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- Insightful-Pipe/marketing-strategy-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository29 other files it gives its agents.
- ad-scriptsSkill
- battlecardSkill
- brand-voiceSkill
- campaign-debriefSkill
- case-study-writerSkill
- channel-pickerSkill
- cmoSkill
- competitor-teardownSkill
- content-calendarSkill
- creative-briefSkill
- customer-deep-diveSkill
- email-sequenceSkill
- experiment-backlogSkill
- funnel-mapSkill
- hook-factorySkill
- kpi-treeSkill
- landing-pageSkill
- launch-planSkill
- lead-magnet-builderSkill
- market-research-sprintSkill
- message-mapSkill
- objection-mapSkill
- offer-builderSkill
- onboardSkill
- positioning-workshopSkill
- pricing-testSkill
- repurposeSkill
- research-to-briefSkill
- weekly-reviewSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Run the dependency check. The layers are ordered: a 2/5 on positioning caps every layer downstream, however polished the creative looks.
- Very specific: line 27
Write the 90-day fix order: one fix per fortnight at most, in dependency order, each routed to the skill that does the work — a mushy …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Marketing Audit — find where the revenue leaks
Most marketing gets fixed at the wrong layer. Teams rewrite ads when the offer is broken, rebuild funnels when the positioning is mush, and buy tools when nobody can name the customer's top pain. This audit scores every layer in dependency order, so effort goes where the leak actually is — not where the work feels most comfortable.
Inputs
- Website, funnel numbers, live channels, recent campaigns, dashboards — whatever exists: $ARGUMENTS
- From
marketing-brief.mdif present: the whole file. The state of the brief is itself evidence — empty or T3-graded sections are research gaps by definition.
Do this
- Inventory the evidence before scoring anything. What actually exists: customer research in the buyer's words, a written position, an offer one-pager, channel numbers, funnel numbers by stage, creative samples with results, a weekly dashboard. Missing evidence is a finding, not a reason to guess.
- Score seven layers 1–5, each with one line of evidence for the score:
- Research — is the customer known in their own words, or only in the company's words?
- Positioning — can anyone state who it is for, against what alternative, and the one difference?
- Offer — clear outcome, price logic, risk reversal, urgency that is real?
- Channels — one primary channel working, or five half-working?
- Funnel — stages mapped with numbers, or a website and hope?
- Creative — enough volume and variety to learn from, with results tracked per piece?
- Measurement — a north star with drivers, reviewed weekly?
- Run the dependency check. The layers are ordered: a 2/5 on positioning caps every layer downstream, however polished the creative looks. Flag any high score sitting on a broken upstream layer as unstable.
- Rank the gaps by revenue impact, not by score. For each gap, weigh the money it touches, how broken it is, and how fast it can be fixed — a small leak at the point of purchase can outrank a big one at the top.
- Write the 90-day fix order: one fix per fortnight at most, in dependency order, each routed to the skill that does the work — a mushy position to
/marketing:positioning-workshop, a weak offer to/marketing:offer-builder, missing customer language to/marketing:customer-deep-dive, no numbers to/marketing:kpi-tree. - Name the score you trust least and the single input that would firm it up.
Output
A one-page audit: the seven-layer scorecard with evidence per score, the top three gaps with the revenue reasoning behind their ranking, the 90-day fix order with named skills, and the least-trusted score. An audit that needs a meeting to explain has failed.
Rules
- Scores follow evidence. A layer with no numbers and no written artefact cannot score above 2, however good it feels.
- Diagnose upstream before prescribing downstream. Never recommend creative fixes for a positioning problem.
- The fix order deletes before it adds. If the audit finds five half-run channels, the first fix is killing four, not starting a sixth.
- Revenue impact beats severity. Rank by money, not by how embarrassing the gap is.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

