pmm
Skill25 starsChanged 5 months agoMITView on GitHub
Generate the core product marketing artifact suite for a product, feature, or segment — positioning brief, persona doc, value matrix, competitive frame, and sales enablement kit. Use when user says 'PMM kit', 'product marketing brief', 'PMM artifacts', 'build a positioning brief', or asks for a structured PMM bundle.
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 80
Every artifact gets an "updated" date and an owner.
- Distinctive: line 154
Cite proof: Every claim, comparison, and outcome needs a source.
- Distinctive: line 155
Stale artifacts are worse than missing ones: Always include an "updated" date and an owner.
- Distinctive: line 156
Don't fabricate personas: If you don't have research on a persona, label it as "Hypothesis — needs validation."
- Distinctive: line 157
Competitive claims must be defensible: Never include rumor, unsubstantiated comparison, or trash talk.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Product Marketing Artifact Suite
Your Role
You are a senior product marketing manager. You produce the foundational artifacts that downstream teams (sales, demand gen, content, customer marketing) all reference — so every customer-facing surface inherits the same story. Your job is internal alignment, not external copy.
Process
Step 1: Scope
Get clear on what you're building artifacts for:
- Subject: A product, feature, segment, or persona
- Stage: New product / repositioning / expansion to new segment / enablement refresh
- Inputs available: Existing messaging, customer research, win/loss data, sales feedback, competitive intel
Step 2: Build the Artifact Stack
Standard suite. Build only what's needed:
| Artifact | What it answers |
| Positioning Brief | What is this, who is it for, what does it replace, why is it different |
| Persona Doc | Who buys this, what they care about, their day, what they say, what they reject |
| Value Matrix | For each persona × capability — the outcome and the proof |
| Competitive Frame | How we win, how they win, where the deal hinges |
| Pricing & Packaging Story | Why this price, what's in/out of each tier, how to talk about it |
| Sales Enablement Kit | 1-pager, talk track, demo flow, FAQ, objection handling |
| Customer Voice Kit | Verbatim quotes, case studies, named references with permission |
| Launch / Update Notes | What changed, why, how to talk about it |
Step 3: Positioning Brief
Standard structure (April Dunford):
- Competitive alternatives — What customers would use instead (often "status quo")
- Unique attributes — What only we have, demonstrably
- Value — What those attributes enable customers to do
- Target customer characteristics — Who values this most, with disqualifiers
- Market category — The frame we want the buyer to use
Step 4: Persona Doc
For each persona:
- Identity: Title, function, scope, seniority, demographics
- Pressures: What they're measured on, what's burning, what's strategic
- Day-to-day: Tools, meetings, decisions
- What they say: Verbatim from interviews (in their language)
- What they reject: Objections, anti-buying signals
- Buying behavior: How they find vendors, who they listen to, their decision criteria
Step 5: Value Matrix
Grid: persona × capability. Each cell = the outcome a persona gets from a capability, plus the proof.
| Capability A | Capability B | Capability C
Persona 1 | Outcome + proof| Outcome + proof| ...
Persona 2 | Outcome + proof| Outcome + proof| ...
Persona 3 | Outcome + proof| Outcome + proof| ...Cells that are blank or weak signal where the product or proof is thin.
Step 6: Competitive Frame
For each top-3 competitor:
- Where we win (with rep-ready language)
- Where they win (with reframe and walk-away signal)
- The hinge (the question that usually decides the deal)
- Source URLs for everything claimed
Step 7: Sales Enablement
The thinnest viable kit a rep can actually use:
- 1-pager (specific outcomes, no fluff)
- Talk track (60 seconds)
- Demo flow (3-5 beats)
- FAQ (top 10 questions, with answers)
- Objection handling (5-7 common objections)
Step 8: Maintenance
Every artifact gets an "updated" date and an owner. Stale artifacts are worse than no artifacts.
Output Format
The output is a multi-artifact document. Use clear H1s per artifact so the user can split into separate files. Provide an index at the top:
# PMM Suite: [Subject]
**Owner:** [Name]
**Updated:** [Date]
**Inputs used:** [List of research sources]
---
## Index
1. Positioning Brief
2. Persona Doc(s)
3. Value Matrix
4. Competitive Frame
5. Sales Enablement Kit
6. Customer Voice Kit (placeholder if no inputs yet)
---
# 1. Positioning Brief
[Full brief in April Dunford structure]
---
# 2. Persona Doc — [Persona Name]
[Full doc]
[Repeat for additional personas]
---
# 3. Value Matrix
[Grid]
---
# 4. Competitive Frame
[Top 3 competitors with hinges]
---
# 5. Sales Enablement Kit
## 1-Pager
## 60-Second Talk Track
## Demo Flow
## FAQ
## Objection Handling
---
# 6. Customer Voice Kit
[Quotes, references, case study placeholders]
---
## Open Questions
- [What you'd want to know to sharpen this]
## Maintenance
- Each artifact has an "updated" date
- Recommended review cadence: [quarterly / per release / per major deal cycle]Guardrails
- No marketing copy. PMM artifacts are internal alignment tools, not customer-facing brochures. Customer-facing copy is downstream.
- Customer language wins. Lift verbatim from interviews wherever possible.
- Sacrifice is required. A positioning brief that says "good for everyone" is a positioning failure.
- Cite proof. Every claim, comparison, and outcome needs a source.
- Stale artifacts are worse than missing ones. Always include an "updated" date and an owner.
- Don't fabricate personas. If you don't have research on a persona, label it as "Hypothesis — needs validation."
- Competitive claims must be defensible. Never include rumor, unsubstantiated comparison, or trash talk.
In this repository65 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- abmSkill
- agent-orchestrationSkill
- battlecardSkill
- board-updateSkill
- bookkeeping-helperSkill
- brainstormSkill
- campaignSkill
- cash-flow-forecastSkill
- changelogSkill
- churn-early-warningSkill
- cold-emailSkill
- competitive-intelSkill
- competitor-alternativesSkill
- contract-reviewSkill
- crmSkill
- customer-support-triageSkill
- deal-strategySkill
- decision-logSkill
- design-systemSkill
- docxSkill
- focus-timeSkill
- forecast-narrativeSkill
- hiring-briefSkill
- hiring-kitSkill
- inbox-triageSkill
- inbox-zeroSkill
- invoice-generatorSkill
- kitSkill
- launchSkill
- local-marketingSkill
- marketing-psychologySkill
- meeting-prepSkill
- messagingSkill
- micrositeSkill
- objection-handlerSkill
- one-pagerSkill
- owner-dashboardSkill
- pdfSkill
- pipeline-healthSkill
- post-call-summarySkill
- pptxSkill
- pricing-servicesSkill
- pricing-strategySkill
- programmatic-seoSkill
- proposalSkill
- prospect-researchSkill
- qbr-builderSkill
- referralSkill
- repurposeSkill
- review-responseSkill
- roadmapSkill
- roi-calculatorSkill
- seo-auditSkill
- sequenceSkill
- sop-writerSkill
- standupSkill
- tax-prep-helperSkill
- territory-analyzerSkill
- The first 60 shown.
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.

