marketing-feedback
Skill21 starsChanged 2 months agoMITView on GitHub
Turn what sales hears in the field into marketing actions. Trigger when a meeting note or call recap surfaces a recurring objection, a competitor mention, the buyer's own language, a missing proof point, or a win/loss reason — or when the user says "log this for marketing", "what should marketing know", or "field intel".
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- account-healthSkill
- calendar-followupSkill
- churn-saveSkill
- cold-outreachSkill
- content-repurposeSkill
- event-to-pipelineSkill
- example-skillSkill
- expansion-signalSkill
- follow-upSkill
- inbox-digestSkill
- lead-qualifySkill
- meeting-prepSkill
- onboarding-handoffSkill
- product-signalSkill
- qbr-prepSkill
- retention-feedbackSkill
- status-updateSkill
- support-signalSkill
- triageSkill
The file
Files
Marketing Feedback
The loop that keeps sales and marketing as one system: field intelligence flows from sales back to marketing on a cadence, instead of dying inside a meeting note. This is mechanism #5 from docs/why-align.md — made concrete as a tagged line in a shared log.
From a source — a note in ops/daily-log.md, a file in demo/meetings/, a call recap, a deal update:
Tagged lines live in one place:
ops/feedback-log.md. That's the single home the SessionStart hook surfaces and/weekly-reviewclears — writeMARKETING-ACTIONlines there, not in the daily log, so they don't go invisible.
- Scan for the five signal types:
- Recurring objection — the same pushback in 3+ conversations.
- Competitor mention — who showed up, and how the buyer described them.
- Buyer language — the words they actually used (use them in content; don't translate them into your own).
- Missing proof — evidence they asked for that doesn't exist yet.
- Win/loss reason — the real one, not the polite one.
- Log each as a tagged line in
ops/feedback-log.md, so marketing can act on it without a meeting:MARKETING-ACTION: [signal] — [the content or proof that would answer it]MARKETING-ACTION-URGENT:when a live deal was affected.MARKETING-STRATEGIC:when it signals a positioning or new-segment shift.
- Don't invent signals. One offhand comment isn't a pattern — tag it only when it recurs across deals or clearly cost one. A log full of false patterns is worse than an empty one.
The tag is the hand-off. One file, both functions read it — that's the loop, version-controlled, with a diff and a history. Marketing's job is to clear the MARKETING-ACTION lines; sales' job is to keep them honest and current.
Depth
- quick: scan one note, emit any
MARKETING-ACTIONlines. - standard: the full five-signal scan across recent notes, tagged and ranked by urgency.
- deep: + a one-line content brief for the top signal (who it's for, the claim to make, the proof to find).
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.

