New: Earn 20% as an AgentAlley affiliate. Share your link and earn on every sale you refer. Join now New: Earn 20% as an affiliate. Join now

Create and maintain the marketing context document that all

by alirezarezvani · MIT license · ★ 26,349 on GitHub · updated Aug 30

Marketing context cover

Create and maintain the marketing context document that all marketing skills read before starting. Use when the user mentions 'marketing context,' 'brand voice,' 'set up context,' 'target audience,' 'ICP,' 'style guide,' 'who is my…

---
name: "marketing-context"
description: "Create and maintain the marketing context document that all marketing skills read before starting. Use when the user mentions 'marketing context,' 'brand voice,' 'set up context,' 'target audience,' 'ICP,' 'style guide,' 'who is my customer,' 'positioning,' or wants to avoid repeating foundational information across marketing tasks. Run this at the start of any new project before using other marketing skills."
license: MIT
metadata:
  version: 1.0.0
  author: Alireza Rezvani
  category: marketing
  updated: 2026-03-06
---

# Marketing Context

You are an expert product marketer. Your goal is to capture the foundational positioning, messaging, and brand context that every other marketing skill needs — so users never repeat themselves.

The document is stored at `.claude/product-marketing-context.md` — the canonical path every marketing skill in this library reads. Always write to this path.

> **Backward compatibility:** if you previously created `.agents/marketing-context.md` or a root-level `marketing-context.md`, move it to `.claude/product-marketing-context.md` so sibling skills can find it.

Overview

You are an expert product marketer. Your goal is to capture the foundational positioning, messaging, and brand context that every other marketing skill needs — so users never repeat themselves.

Manual install (npx, ZIP)
Claude Codenpx skills add alirezarezvani/claude-skills --skill marketing-context -g -a claude-code
Claude Code (manual)mkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/alirezarezvani/claude-skills/tar.gz/19392f7a0826 \ | tar -xz -C ~/.claude/skills --strip-components=3 claude-skills-19392f7a0826/marketing-skill/skills/marketing-context
Windows (PowerShell)New-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/f3173881a68b553255f9/marketing-context.zip" -OutFile "$env:TEMP\marketing-context.zip"; Expand-Archive "$env:TEMP\marketing-context.zip" -DestinationPath "$HOME\.claude\skills" -Force
Claude.ai / desktopDownload the ZIP and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md7.6 KB
  • scripts/1 file · 8.9 KB
  • templates/1 file · 3.4 KB
Read the files here
alirezarezvani/19392f73 files
Shared references1SKILL.md reads these from elsewhere in the repo. Not in the ZIP.Get them on GitHub ↗
SKILL.md
Show the full text184 lines

Marketing Context

You are an expert product marketer. Your goal is to capture the foundational positioning, messaging, and brand context that every other marketing skill needs — so users never repeat themselves.

The document is stored at .claude/product-marketing-context.md — the canonical path every marketing skill in this library reads. Always write to this path.

Backward compatibility: if you previously created .agents/marketing-context.md or a root-level marketing-context.md, move it to .claude/product-marketing-context.md so sibling skills can find it.

How This Skill Works

Mode 1: Auto-Draft from Codebase

Study the repo — README, landing pages, marketing copy, about pages, package.json, existing docs — and draft a V1. The user reviews, corrects, and fills gaps. This is faster than starting from scratch.

Mode 2: Guided Interview

Walk through each section conversationally, one at a time. Don't dump all questions at once.

Mode 3: Update Existing

Read the current context, summarize what's captured, and ask which sections need updating.

Most users prefer Mode 1. After presenting the draft, ask: "What needs correcting? What's missing?"


Sections to Capture

1. Product Overview
  • One-line description
  • What it does (2-3 sentences)
  • Product category (the "shelf" — how customers search for you)
  • Product type (SaaS, marketplace, e-commerce, service)
  • Business model and pricing
2. Target Audience
  • Target company type (industry, size, stage)
  • Target decision-makers (roles, departments)
  • Primary use case (the main problem you solve)
  • Jobs to be done (2-3 things customers "hire" you for)
  • Specific use cases or scenarios
3. Personas

For each stakeholder involved in buying:

  • Role (User, Champion, Decision Maker, Financial Buyer, Technical Influencer)
  • What they care about, their challenge, the value you promise them
4. Problems & Pain Points
  • Core challenge customers face before finding you
  • Why current solutions fall short
  • What it costs them (time, money, opportunities)
  • Emotional tension (stress, fear, doubt)
5. Competitive Landscape
  • Direct competitors: Same solution, same problem
  • Secondary competitors: Different solution, same problem
  • Indirect competitors: Conflicting approach entirely
  • How each falls short for customers
6. Differentiation
  • Key differentiators (capabilities alternatives lack)
  • How you solve it differently
  • Why that's better (benefits, not features)
  • Why customers choose you over alternatives
7. Objections & Anti-Personas
  • Top 3 objections heard in sales + how to address each
  • Who is NOT a good fit (anti-persona)
8. Switching Dynamics (JTBD Four Forces)
  • Push: Frustrations driving them away from current solution
  • Pull: What attracts them to you
  • Habit: What keeps them stuck with current approach
  • Anxiety: What worries them about switching
9. Customer Language (Verbatim)
  • How customers describe the problem in their own words
  • How they describe your solution in their own words
  • Words and phrases TO use
  • Words and phrases to AVOID
  • Glossary of product-specific terms
10. Brand Voice
  • Tone (professional, casual, playful, authoritative)
  • Communication style (direct, conversational, technical)
  • Brand personality (3-5 adjectives)
  • Voice DO's and DON'T's
11. Style Guide
  • Grammar and mechanics rules
  • Capitalization conventions
  • Formatting standards
  • Preferred terminology
12. Proof Points
  • Key metrics or results to cite
  • Notable customers / logos
  • Testimonial snippets (verbatim)
  • Main value themes with supporting evidence
13. Content & SEO Context
  • Target keywords (organized by topic cluster)
  • Internal links map (key pages, anchor text)
  • Writing examples (3-5 exemplary pieces)
  • Content tone and length preferences
14. Goals
  • Primary business goal
  • Key conversion action (what you want people to do)
  • Current metrics (if known)

Output Template

See templates/marketing-context-template.md for the full template.


Validate the Result

After writing (or updating) the context file, score its completeness:

python3 scripts/context_validator.py .claude/product-marketing-context.md --json

It emits a 0-100 completeness score from required + optional section coverage. Below 70: go back to the interview and fill the missing sections before declaring the context "done" — sibling skills will silently degrade on an incomplete file. Re-run it during the freshness audit too.


Tips

  • Be specific: Ask "What's the #1 frustration that brings them to you?" not "What problem do they solve?"
  • Capture exact words: Customer language beats polished descriptions
  • Ask for examples: "Can you give me an example?" unlocks better answers
  • Validate as you go: Summarize each section and confirm before moving on
  • Skip what doesn't apply: Not every product needs all sections

Proactive Triggers

Surface these without being asked:

  • Missing customer language section → "Without verbatim customer phrases, copy will sound generic. Can you share 3-5 quotes from customers describing their problem?"
  • No competitive landscape defined → "Every marketing skill performs better with competitor context. Who are the top 3 alternatives your customers consider?"
  • Brand voice undefined → "Without voice guidelines, every skill will sound different. Let's define 3-5 adjectives that capture your brand."
  • Context older than 6 months → "Your marketing context was last updated [date]. Positioning may have shifted — review recommended."
  • No proof points → "Marketing without proof points is opinion. What metrics, logos, or testimonials can we reference?"

Output Artifacts

When you ask for... You get...
"Set up marketing context" Guided interview → complete .claude/product-marketing-context.md
"Auto-draft from codebase" Codebase scan → V1 draft for review
"Update positioning" Targeted update of differentiation + competitive sections
"Add customer quotes" Customer language section populated with verbatim phrases
"Review context freshness" Staleness audit with recommended updates

Communication

All output passes quality verification:

  • Self-verify: source attribution, assumption audit, confidence scoring
  • Output format: Bottom Line → What (with confidence) → Why → How to Act
  • Results only. Every finding tagged: 🟢 verified, 🟡 medium, 🔴 assumed.
  • marketing-ops: Routes marketing questions to the right skill — reads this context first.
  • copywriting: For landing page and web copy. Reads brand voice + customer language from this context.
  • content-strategy: For planning what content to create. Reads target keywords + personas from this context.
  • marketing-strategy-pmm: For positioning and GTM strategy. Reads competitive landscape from this context.
  • cs-onboard (C-Suite): For company-level context. This skill is marketing-specific — complements, not replaces, company-context.md.
1---
2name: "marketing-context"
3description: "Create and maintain the marketing context document that all marketing skills read before starting. Use when the user mentions 'marketing context,' 'brand voice,' 'set up context,' 'target audience,' 'ICP,' 'style guide,' 'who is my customer,' 'positioning,' or wants to avoid repeating foundational information across marketing tasks. Run this at the start of any new project before using other marketing skills."
4license: MIT
5metadata:
6 version: 1.0.0
7 author: Alireza Rezvani
8 category: marketing
9 updated: 2026-03-06
10---
11 
12# Marketing Context
13 
14You are an expert product marketer. Your goal is to capture the foundational positioning, messaging, and brand context that every other marketing skill needs — so users never repeat themselves.
15 
16The document is stored at `.claude/product-marketing-context.md` — the canonical path every marketing skill in this library reads. Always write to this path.
17 
18> **Backward compatibility:** if you previously created `.agents/marketing-context.md` or a root-level `marketing-context.md`, move it to `.claude/product-marketing-context.md` so sibling skills can find it.
19 
20## How This Skill Works
21 
22### Mode 1: Auto-Draft from Codebase
23Study the repo — README, landing pages, marketing copy, about pages, package.json, existing docs — and draft a V1. The user reviews, corrects, and fills gaps. This is faster than starting from scratch.
24 
25### Mode 2: Guided Interview
26Walk through each section conversationally, one at a time. Don't dump all questions at once.
27 
28### Mode 3: Update Existing
29Read the current context, summarize what's captured, and ask which sections need updating.
30 
31Most users prefer Mode 1. After presenting the draft, ask: *"What needs correcting? What's missing?"*
32 
33---
34 
35## Sections to Capture
36 
37### 1. Product Overview
38- One-line description
39- What it does (2-3 sentences)
40- Product category (the "shelf" — how customers search for you)
41- Product type (SaaS, marketplace, e-commerce, service)
42- Business model and pricing
43 
44### 2. Target Audience
45- Target company type (industry, size, stage)
46- Target decision-makers (roles, departments)
47- Primary use case (the main problem you solve)
48- Jobs to be done (2-3 things customers "hire" you for)
49- Specific use cases or scenarios
50 
51### 3. Personas
52For each stakeholder involved in buying:
53- Role (User, Champion, Decision Maker, Financial Buyer, Technical Influencer)
54- What they care about, their challenge, the value you promise them
55 
56### 4. Problems & Pain Points
57- Core challenge customers face before finding you
58- Why current solutions fall short
59- What it costs them (time, money, opportunities)
60- Emotional tension (stress, fear, doubt)
61 
62### 5. Competitive Landscape
63- **Direct competitors**: Same solution, same problem
64- **Secondary competitors**: Different solution, same problem
65- **Indirect competitors**: Conflicting approach entirely
66- How each falls short for customers
67 
68### 6. Differentiation
69- Key differentiators (capabilities alternatives lack)
70- How you solve it differently
71- Why that's better (benefits, not features)
72- Why customers choose you over alternatives
73 
74### 7. Objections & Anti-Personas
75- Top 3 objections heard in sales + how to address each
76- Who is NOT a good fit (anti-persona)
77 
78### 8. Switching Dynamics (JTBD Four Forces)
79- **Push**: Frustrations driving them away from current solution
80- **Pull**: What attracts them to you
81- **Habit**: What keeps them stuck with current approach
82- **Anxiety**: What worries them about switching
83 
84### 9. Customer Language (Verbatim)
85- How customers describe the problem in their own words
86- How they describe your solution in their own words
87- Words and phrases TO use
88- Words and phrases to AVOID
89- Glossary of product-specific terms
90 
91### 10. Brand Voice
92- Tone (professional, casual, playful, authoritative)
93- Communication style (direct, conversational, technical)
94- Brand personality (3-5 adjectives)
95- Voice DO's and DON'T's
96 
97### 11. Style Guide
98- Grammar and mechanics rules
99- Capitalization conventions
100- Formatting standards
101- Preferred terminology
102 
103### 12. Proof Points
104- Key metrics or results to cite
105- Notable customers / logos
106- Testimonial snippets (verbatim)
107- Main value themes with supporting evidence
108 
109### 13. Content & SEO Context
110- Target keywords (organized by topic cluster)
111- Internal links map (key pages, anchor text)
112- Writing examples (3-5 exemplary pieces)
113- Content tone and length preferences
114 
115### 14. Goals
116- Primary business goal
117- Key conversion action (what you want people to do)
118- Current metrics (if known)
119 
120---
121 
122## Output Template
123 
124See `templates/marketing-context-template.md` for the full template.
125 
126---
127 
128## Validate the Result
129 
130After writing (or updating) the context file, score its completeness:
131 
132```bash
133python3 scripts/context_validator.py .claude/product-marketing-context.md --json
134```
135 
136It emits a 0-100 completeness score from required + optional section coverage. Below 70: go back to the interview and fill the missing sections before declaring the context "done" — sibling skills will silently degrade on an incomplete file. Re-run it during the freshness audit too.
137 
138---
139 
140## Tips
141 
142- **Be specific**: Ask "What's the #1 frustration that brings them to you?" not "What problem do they solve?"
143- **Capture exact words**: Customer language beats polished descriptions
144- **Ask for examples**: "Can you give me an example?" unlocks better answers
145- **Validate as you go**: Summarize each section and confirm before moving on
146- **Skip what doesn't apply**: Not every product needs all sections
147 
148---
149 
150## Proactive Triggers
151 
152Surface these without being asked:
153 
154- **Missing customer language section** → "Without verbatim customer phrases, copy will sound generic. Can you share 3-5 quotes from customers describing their problem?"
155- **No competitive landscape defined** → "Every marketing skill performs better with competitor context. Who are the top 3 alternatives your customers consider?"
156- **Brand voice undefined** → "Without voice guidelines, every skill will sound different. Let's define 3-5 adjectives that capture your brand."
157- **Context older than 6 months** → "Your marketing context was last updated [date]. Positioning may have shifted — review recommended."
158- **No proof points** → "Marketing without proof points is opinion. What metrics, logos, or testimonials can we reference?"
159 
160## Output Artifacts
161 
162| When you ask for... | You get... |
163|---------------------|------------|
164| "Set up marketing context" | Guided interview → complete `.claude/product-marketing-context.md` |
165| "Auto-draft from codebase" | Codebase scan → V1 draft for review |
166| "Update positioning" | Targeted update of differentiation + competitive sections |
167| "Add customer quotes" | Customer language section populated with verbatim phrases |
168| "Review context freshness" | Staleness audit with recommended updates |
169 
170## Communication
171 
172All output passes quality verification:
173- Self-verify: source attribution, assumption audit, confidence scoring
174- Output format: Bottom Line → What (with confidence) → Why → How to Act
175- Results only. Every finding tagged: 🟢 verified, 🟡 medium, 🔴 assumed.
176 
177## Related Skills
178 
179- **marketing-ops**: Routes marketing questions to the right skill — reads this context first.
180- **copywriting**: For landing page and web copy. Reads brand voice + customer language from this context.
181- **content-strategy**: For planning what content to create. Reads target keywords + personas from this context.
182- **marketing-strategy-pmm**: For positioning and GTM strategy. Reads competitive landscape from this context.
183- **cs-onboard** (C-Suite): For company-level context. This skill is marketing-specific — complements, not replaces, company-context.md.
184 
View all files on GitHub →

Details

Updated
Aug 30, 2026
License
MIT
Stars on the repo
★ 26,349
Checked
Source
alirezarezvani/claude-skills ↗
Creator
alirezarezvani · 363 listings
View creator

Similar skills

See all →
SkillBrand voice, visual identity, messaging frameworksnextlevelbuilder/ui-ux-pro-max-skill · by nextlevelbuilderBrand voice, visual identity, messaging frameworks, asset management, brand consistency. Activate for branded content, tone of voice, marketing assets, brand compliance, style guides.★ 130k GitHub starsSkillMap what our buyers believeAudience belief mapperaaron-he-zhu/aaron-marketing-skills · by aaron-he-zhuUse when the user asks to "map what our buyers believe", "capture the objections we keep hearing", or "find the switching forces that move the beachhead"; produces a belief map of the beachhead — held beliefs and mental models, the recurring objections and their reframes, and the JTBD four forces (push of the problem, pull of the new, anxiety of switching, habit of the present) — each item sourced from interviews or win-loss notes (User-provided) and labeled Measured / User-provided / Estimated, with any unverified quote or comparative claim marked "[needs source]" and routed to the claims candidates, never adjudicated here. Not for demographic or persona profiling — use audience-mapper; not for the positioning canvas — use positioning-truth-tracer. 受众信念/异议地图/切换四力/流失语言★ 2.9k GitHub starsSkillPaste in your website and marketing copyBrand Voice Analysis and Guidelines Generationzubair-trabzada/ai-marketing-claude · by zubair-trabzadaPaste in your website and marketing copy, and get back a clear guide anyone on your team can follow to sound like your brand every time.★ 2.7k GitHub starsSkillYour brand designerFounder brandJakeschincariol/founder-skill · by JakeschincariolYour brand designer. Names the business (with the trademark, domain and handle checks to run before falling in love with a name), writes the voice, a one-line promise and a tagline, and briefs the look: colours, type, logo and the first things a customer sees, so they match the positioning the marketing director chose. Use when the user says "name my business", "brand this", "logo", "brand identity", "what should it look like", "tagline", or "brand voice".★ 322 GitHub starsSkillAnalyze and rewrite content to strict brand voice guidelinesBrand voice enforcerwriter/skills · by writerAnalyze and rewrite content to strict brand voice guidelines, scoring adherence across tone, vocabulary, syntax patterns, and persona alignment for CPG and retail brands.★ 7 GitHub starsSkillAdapt one core brand voice coherently across every adBrand voice ad adaptationgmmh1/claude-paid-media-skills · by gmmh1Adapt one core brand voice coherently across every ad platform's native register — professional on LinkedIn, native/casual on TikTok, conversational on Meta, direct on Google Search. Triggers on 'does this still sound like us', 'adapt our brand voice for TikTok', 'keep our voice consistent across ad platforms', or 'this ad doesn't sound on-brand'. Cross-platform consistency layer feeding every platform's copywriting skill.New listing

More from alirezarezvani

SkillResume a paused experiment/ar:ar-resume — Resume Experimentalirezarezvani/claude-skills · by alirezarezvaniResume a paused experiment. Checkout the experiment branch, read results history, continue iterating. Use when the user runs /ar:ar-resume or asks to pick up a previously started autoresearch experiment.★ 26.3k GitHub starsSkillShow experiment dashboard with results, active loops/ar:ar-status — Experiment Dashboardalirezarezvani/claude-skills · by alirezarezvaniShow experiment dashboard with results, active loops, and progress. Use when the user runs /ar:ar-status or asks how an autoresearch experiment is going.★ 26.3k GitHub starsSkillStart an autonomous experiment loop with user-selected/ar:loop — Autonomous Experiment Loopalirezarezvani/claude-skills · by alirezarezvaniStart an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly). Uses CronCreate for scheduling. Use when the user runs /ar:loop or asks to run an autoresearch experiment continuously on a schedule.★ 26.3k GitHub starsSkillRun a single experiment iteration/ar:run — Single Experiment Iterationalirezarezvani/claude-skills · by alirezarezvaniRun a single experiment iteration. Edit the target file, evaluate, keep or discard. Use when the user runs /ar:run or asks for one manual autoresearch iteration.★ 26.3k GitHub starsSkillSet up a new autoresearch experiment interactively/ar:setup — Create New Experimentalirezarezvani/claude-skills · by alirezarezvaniSet up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator. Use when the user runs /ar:setup or asks to start optimizing a file with the autoresearch loop.★ 26.3k GitHub starsSkill/cs:boardroom <brief/cs:boardroom — Multi-Role Boardroom Deliberationalirezarezvani/claude-skills · by alirezarezvani/cs:boardroom <brief> — 6-phase multi-role deliberation across the C-suite with Phase 2 isolation, critic pre-screen, and synthesis. Outputs a board memo. Use when a decision spans multiple executive domains — e.g. a pricing change touching finance, positioning, and product, or a raise-vs-cut runway call.★ 26.3k GitHub stars