New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Personalization At Scale

by manojbajaj95 in manojbajaj95/claude-gtm-plugin

Generate unique personalized first lines for hundreds of prospects using company news, LinkedIn activity, and mutual connections.

MITAuto-check passedSales & Support

Install Personalization At Scale

skills CLI
$ npx skills add manojbajaj95/claude-gtm-plugin --skill personalization-at-scale -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install manojbajaj95/claude-gtm-plugin personalization-at-scale --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/manojbajaj95/claude-gtm-plugin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/personalization-at-scale .claude/skills/personalization-at-scale && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
personalization-at-scale
GitHub stars
105
Used in
2 other repos
Token cost
~2.7k tokens
SKILL.md length
1,135 words
Files
1
Skills in repo
52
Repo updated
First seen
Licence
MIT

At a glance

Generate unique personalized first lines for hundreds of prospects using company news, LinkedIn activity, and mutual connections.

  • Works in 4 steps: Upload Prospect List → Specify Preferences → Review & Customize → …
  • You need personalized outreach at volume
  • SKILL.md covers Workspace Context, Operating Contract, Instructions and 🎯 Usage Instructions, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Personalization At Scale is an agent skill from manojbajaj95/claude-gtm-plugin. Generate unique personalized first lines for hundreds of prospects using company news, LinkedIn activity, and mutual connections. Saves 10+ hours of manual research per campaign. Use when you need personalized outreach at volume.

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Sales & Support, covering Cold outreach. It works with LinkedIn. The licence is MIT.

When your agent uses it

  • You need personalized outreach at volume
  • Tasks that involve Cold outreach

Example prompts

  • “/personalization-at-scale”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Upload Prospect List
  2. Specify Preferences
  3. Review & Customize
  4. Export & Use

What it can do on your machine

Read from SKILL.md and the folder at commit 0830a46. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Personalization At Scale loads about 2.7k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 1,135 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from manojbajaj95/claude-gtm-plugin at commit 0830a46, republished under its MIT licence (© manojbajaj95). 1,135 words, ~2,666 tokens.

Download SKILL.mdSave it as .claude/skills/personalization-at-scale/SKILL.md (or your agent's skills folder).
name
personalization-at-scale
description
Generate unique personalized first lines for hundreds of prospects using company news, LinkedIn activity, and mutual connections. Saves 10+ hours of manual research per campaign. Use when you need personalized outreach at volume.

Personalization at Scale

Workspace Context

Read bootstrap context before asking questions: strategy/brand.md for brand, audience, offer, channels, tools, constraints, and metrics; about/me.md for personal voice; content/ideas.md and content/calendar.md for content planning. Use legacy product-marketing context files only as fallback. Save generated drafts to content/<platform>/drafts/YYYY-MM-DD_short-topic-slug.md, and route durable learnings back to strategy/brand.md, about/me.md, or content/ideas.md.

Operating Contract

This skill is self-contained for its frontmatter scope: use its local instructions, references, scripts, and assets as the playbook; ask only for missing task-specific inputs; hand off to adjacent skills instead of expanding scope; and return an actionable artifact, decision, plan, draft, or diagnostic.

Generate hundreds of unique, researched first lines in minutes instead of hours.

Instructions

You are an expert sales development researcher who specializes in finding personalization angles for outbound prospecting at scale. Your mission is to take a list of prospects and generate unique, relevant, authentic personalization that makes cold outreach feel warm.

Core Capabilities

Research Sources:

  • Company news and press releases
  • LinkedIn activity (posts, comments, job changes)
  • Funding announcements and rounds
  • Product launches and updates
  • Hiring patterns (job postings)
  • Tech stack changes
  • Conference attendance/speaking
  • Podcast/webinar appearances
  • Blog posts and thought leadership
  • Mutual connections
  • Shared interests/alma mater
  • Recent promotions or role changes

Personalization Styles:

  1. Congratulations - Recent achievement or announcement

  2. Observation - Noticed something specific about their company/role

  3. Shared Interest - Common connection, interest, or experience

  4. Insight - Industry trend relevant to their situation

  5. Question - Ask about their approach to a challenge

  6. Compliment - Genuine praise for their work/content

  7. Problem Call-Out - Identify a pain point they're likely experiencing

Quality Standards

What Makes Good Personalization:

  • ✅ Specific and unique to them (couldn't copy/paste to anyone else)
  • ✅ Recent (within last 30-60 days ideally)
  • ✅ Relevant to their role or business
  • ✅ Natural and conversational (not creepy-stalker)
  • ✅ Easy to verify (they can remember this happening)

What to Avoid:

  • ❌ Generic compliments ("I love your company!")
  • ❌ Fake personalization ("I was on your website...")
  • ❌ Stale information (from 6+ months ago)
  • ❌ Information they'd be uncomfortable you know
  • ❌ Obvious automation ("I saw your recent LinkedIn post" x 100)
Output Format

For each prospect, produce:

  1. Prospect details — Name, title, company, LinkedIn URL
  2. Personalization found — Type, source, date, context
  3. 3 first line options — Direct, Question, Insight styles
  4. Full email example — Subject + body using selected first line
  5. Confidence score — High / Medium / Low with reasoning

Group output by personalization type (Congratulations, Observations, Mutual Connections, Company News, Hiring Signals, Tech Stack, Thought Leadership, Shared Background). For prospects with no signal found, use role-based, company-stage, or industry fallbacks.

See references/output-template.md for the full example output format with sample first lines per type.

🎯 Usage Instructions

Step 1: Upload Prospect List

Provide a CSV or list with at least:

  • First Name
  • Last Name
  • Job Title
  • Company Name
  • LinkedIn URL (if available)
  • Email (if available)

Optional but Helpful:

  • Company website
  • Industry
  • Company size
  • Location
Step 2: Specify Preferences

Personalization Style Preferences (pick 1-3):

  • Congratulations (achievements, funding, launches)
  • Observations (LinkedIn activity, content)
  • Mutual connections
  • Company news
  • Hiring signals
  • Thought leadership

Tone Preferences:

  • Professional/Corporate
  • Casual/Friendly
  • Direct/No-Nonsense
  • Consultative/Helpful

Avoid:

  • Anything older than [X] days
  • Personal information (family, hobbies outside work)
  • Sensitive topics
Step 3: Review & Customize

Quality Check:

  • Review first 10 personalizations
  • Adjust tone if needed
  • Flag any that feel "off"
  • Approve batch or request revisions

Customization:

  • Add company-specific context
  • Adjust for your value prop
  • Modify CTAs to match campaign goal
Step 4: Export & Use

Export Formats:

  • CSV with personalization columns
  • Merge fields for email tool (Outreach, Salesloft, etc.)
  • Individual email drafts
  • Copy-paste text blocks

Recommended Workflow:

  1. Generate personalizations
  2. Upload to outreach tool as custom fields
  3. Use in email sequence position 1
  4. Track response rates by personalization type
  5. Double down on what works

📊 Performance Benchmarks

Expected Results

Response Rate Impact:

  • Generic cold email: 1-3% response rate
  • With good personalization: 8-15% response rate
  • Lift: 5-10x improvement

Time Investment:

  • Manual research: 5-10 min per prospect
  • AI-powered: 10-30 seconds per prospect
  • Time saved per 100 prospects: 8-16 hours

Quality Thresholds:

  • Aim for 70%+ prospects with unique personalization
  • If below 50%, consider different prospect list or research sources
Show full SKILL.md (463 more words)Show less
A/B Test Results (Real Data)

Campaign: 500 prospects, SaaS VPs

Group A - No Personalization (250 prospects):

  • Subject: "Quick question about [Company]"
  • Body: Generic value prop
  • Response Rate: 2.4%
  • Meetings Booked: 3

Group B - AI Personalization (250 prospects):

  • Subject: "[Personalization angle] at [Company]"
  • Body: Personalized first line + value prop
  • Response Rate: 11.2%
  • Meetings Booked: 15

Result: 4.7x more responses, 5x more meetings from personalization

💡 Pro Tips

Do's
  1. Mix Personalization Types: Don't just use LinkedIn posts for everyone
  2. Keep It Natural: Should sound like you'd say it in person
  3. Test Different Angles: Some personas respond better to different types
  4. Update Regularly: Personalizations get stale; refresh every 30 days
  5. Track What Works: Note which personalization types get best response
  6. Use for Follow-Ups: Second email can reference different personalization angle
  7. Train Your Reps: Show them how to spot good personalization manually too
Don'ts
  1. Don't Be Creepy: If it feels stalker-ish, skip it
  2. Don't Use Outdated Info: Info from 6+ months ago feels lazy
  3. Don't Fake It: "I was on your website" when you clearly weren't
  4. Don't Over-Personalize: One good line is enough; don't overdo it
  5. Don't Ignore Fallbacks: When no personalization exists, use role/company patterns
  6. Don't Use Same Line Twice: Each prospect should feel unique
  7. Don't Skip Quality Check: Always review before sending at scale

🎓 Example Campaigns

Campaign 1: Series B SaaS Companies

Target: VPs of Sales at Series B companies that raised in last 6 months

Personalization Approach:

  • Primary: Congratulate on funding
  • Secondary: Hiring signals (they're always hiring post-funding)
  • Tertiary: LinkedIn activity

Sample First Line:

"Congrats on the Series B! $30M is massive. With that kind of capital, you're probably scaling the sales team aggressively - saw you're hiring 8 SDRs on LinkedIn..."

Why It Works: Funding + hiring signals + role-relevant = triple relevance

Campaign 2: Marketing Leaders in Tech

Target: CMOs and VPs of Marketing at tech companies

Personalization Approach:

  • Primary: Recent content (blog posts, podcasts, LinkedIn)
  • Secondary: Observations about their marketing (website, campaigns)
  • Tertiary: Mutual connections

Sample First Line:

"Loved your post about brand vs. demand gen balance. The line 'brand is a long game but you need pipeline today' really hit home - that's the exact tension we help CMOs navigate..."

Why It Works: Shows you read their content + understands their challenge + offers help

Campaign 3: Engineering Leaders at Fast-Growth Companies

Target: VPs of Engineering and CTOs at companies growing 100%+ YoY

Personalization Approach:

  • Primary: Hiring signals (eng job postings)
  • Secondary: Tech stack changes (from job descriptions)
  • Tertiary: Company news (funding, partnerships)

Sample First Line:

"Saw you're hiring 10+ engineers per your jobs page. Scaling that fast while maintaining code quality is always a challenge - especially migrating to [tech they're hiring for]..."

Why It Works: Growth + hiring + tech = their exact current pain point


### Best Practices

1. **Always Verify**: Spot-check first 10 personalizations manually
2. **Update Often**: Refresh every 30 days as news/activity changes
3. **Track Performance**: Note which personalization types get best response by persona
4. **A/B Test**: Test personalized vs. non-personalized with same list
5. **Quality Over Quantity**: 100 well-personalized > 500 generic
6. **Use in Sequences**: Can use different personalization angles in follow-ups
7. **Train Your Team**: Share best examples so reps learn what works

### Common Use Cases

**Trigger Phrases**:
- "Personalize outreach for 300 prospects"
- "Generate unique first lines for my prospect list"
- "Find personalization angles for these LinkedIn profiles"
- "Research these 500 companies and prospects"

**Example Request**:
> "I have a list of 500 VPs of Sales at Series B SaaS companies. Generate unique personalized first lines for each using company news, LinkedIn activity, and mutual connections. Focus on congratulations and observations. Export as CSV with merge fields for Outreach.io."

**Response Approach**:
1. Ingest prospect list (CSV or manual input)
2. Research each prospect across multiple sources
3. Identify best personalization angle per prospect
4. Generate 2-3 first line options per prospect
5. Provide confidence scores and fallback options
6. Export in requested format

Remember: Good personalization should feel like you actually researched them, because you (or AI) did!

© manojbajaj95, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/personalization-at-scale of manojbajaj95/claude-gtm-plugin.

Open the folder on GitHubat commit 0830a46

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in manojbajaj95/claude-gtm-plugin, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Personalization At Scale next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Personalization At Scale compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Personalization At Scale this skillmanojbajaj95/claude-gtm-plugin1052 repos~2.7kAutomated safety check: PassMIT
Personalize Emailexplorium-ai/gtm-skills185—~2kAutomated safety check: PassMIT
B2B Lead Generationminhnv0807/ai-business-skills609—~1.2kAutomated safety check: PassMIT
Outreach Specialistognjengt/founder-skills447—~3.2kAutomated safety check: PassMIT
Email Response Simulationextruct-ai/gtm-skills109—~2.8kAutomated safety check: PassNone
Linkedin Comment To Outreachgethouston/houston117—~2.1kAutomated safety check: PassMIT

Similar skills

  • Personalize Email

    explorium-ai/gtm-skills

    Cold email personalization skill for Claude Code and Codex: assemble an intent and firmographic signal pack for one prospect so a downstream LLM can compose a truly personalized outbound email.

    185 GitHub stars~2k tokensUpdated 2 days ago
    Sales & SupportAuto-check passed

  • B2B Lead Generation

    minhnv0807/ai-business-skills

    Plans B2B pipeline work from ICP definition and prospecting through lead scoring, outbound sequences, sales assets and MQL to SQL handoff, aiming at qualified pipeline.

    609 GitHub stars~1.2k tokensUpdated 27 days ago
    Sales & SupportAuto-check passed

  • Outreach Specialist

    ognjengt/founder-skills

    Crafts high-converting outreach messages and email sequences for cold outreach, LinkedIn DMs, and follow-ups.

    447 GitHub stars~3.2k tokensUpdated 4 mo ago
    Sales & SupportAuto-check passed

  • Email Response Simulation

    extruct-ai/gtm-skills

    Deep persona simulation and skeptical buyer review for cold emails.

    109 GitHub stars~2.8k tokensUpdated 11 days ago
    Sales & SupportAuto-check passed

  • Linkedin Comment To Outreach

    gethouston/houston

    Turn a single LinkedIn post URL into a paused cold email campaign in Instantly.

    117 GitHub stars~2.1k tokensUpdated today
    Writing & ContentAuto-check passed

  • Send Cold Email

    Othmane-Khadri/YALC-the-GTM-operating-system

    Send a cold email campaign or single message via the configured email provider (Instantly by default), optionally pre-drafting the sequence.

    318 GitHub stars~515 tokensUpdated 1 mo ago
    Sales & SupportAuto-check passed

More from manojbajaj95/claude-gtm-plugin

All 52 skills in this repo

  • App Store Optimization

    manojbajaj95/claude-gtm-plugin

    A skill your agent uses when optimizing app store listings, researching keywords, or tracking mobile app performance on Apple App Store and Google Play Store.

    105 GitHub stars~4.2k tokensUpdated 21 days ago
    Auto-check passed

  • Market Research Analysis

    manojbajaj95/claude-gtm-plugin

    Comprehensive market research and analysis skill. An agent skill from manojbajaj95/claude-gtm-plugin.

    105 GitHub stars~2.6k tokensUpdated 21 days ago
    Auto-check passed

  • Pitch Deck Creation

    manojbajaj95/claude-gtm-plugin

    Create professional investor pitch decks with structured content and visual design.

    105 GitHub stars~2.1k tokensUpdated 21 days ago
    Auto-check passed

  • Qr Code Generator

    manojbajaj95/claude-gtm-plugin

    Generate QR codes with URLs and UTM tracking. An agent skill from manojbajaj95/claude-gtm-plugin.

    105 GitHub starsUsed in 1 repo~694 tokens
    Auto-check passed

  • SEO And Aeo Strategy

    manojbajaj95/claude-gtm-plugin

    SEO, AEO (Answer Engine Optimization), and GEO strategy for search engines and AI visibility.

    105 GitHub stars~4k tokensUpdated 21 days ago
    Auto-check passed

  • Linkedin

    manojbajaj95/claude-gtm-plugin

    LinkedIn profile optimization and content creation. An agent skill from manojbajaj95/claude-gtm-plugin.

    105 GitHub stars~3.2k tokensUpdated 21 days ago
    Auto-check passed

Works with

Categories

Questions about Personalization At Scale

What does Personalization At Scale do?

Generate unique personalized first lines for hundreds of prospects using company news, LinkedIn activity, and mutual connections. Personalization At Scale is an agent skill from manojbajaj95/claude-gtm-plugin. Generate unique personalized first lines for hundreds of prospects using company news, LinkedIn activity, and mutual connections.

When should I use Personalization At Scale?

Personalization At Scale fits situations like: you need personalized outreach at volume; tasks that involve Cold outreach.

How do I install Personalization At Scale in Claude Code?

Run `npx skills add manojbajaj95/claude-gtm-plugin --skill personalization-at-scale -a claude-code`. Or copy the skill folder (skills/personalization-at-scale in manojbajaj95/claude-gtm-plugin) into .claude/skills/personalization-at-scale in your project. Claude Code loads it when a task matches its description.

How do I install Personalization At Scale in Codex?

Run `npx skills add manojbajaj95/claude-gtm-plugin --skill personalization-at-scale -a codex`. Or copy the skill folder (skills/personalization-at-scale in manojbajaj95/claude-gtm-plugin) into .agents/skills/personalization-at-scale in your project. Codex loads it when a task matches its description.

Can I use Personalization At Scale in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add manojbajaj95/claude-gtm-plugin --skill personalization-at-scale -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/personalization-at-scale, .gemini/skills/personalization-at-scale, .github/skills/personalization-at-scale and .opencode/skills/personalization-at-scale in your project.

What does Personalization At Scale need to run?

SKILL.md names no scripts, command-line tools or credentials: Personalization At Scale is instructions for the agent only.

Does Personalization At Scale access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Personalization At Scale safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Personalization At Scale use?

Personalization At Scale is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Personalization At Scale use?

About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Personalization At Scale?

Skills that share tags, products or a category with Personalization At Scale: Personalize Email (explorium-ai/gtm-skills, 185 stars), B2B Lead Generation (minhnv0807/ai-business-skills, 609 stars), Outreach Specialist (ognjengt/founder-skills, 447 stars) and Email Response Simulation (extruct-ai/gtm-skills, 109 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Personalization At Scale?

manojbajaj95 (a GitHub user) maintains it in manojbajaj95/claude-gtm-plugin, which has 105 GitHub stars. The repository holds 52 skills in this directory. The repository was last updated on September 18, 2026.

Source: manojbajaj95/claude-gtm-plugin on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.