create-an-asset

anthropics/knowledge-work-plugins · updated Apr 8, 2026

MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.

$npx skills add https://github.com/anthropics/knowledge-work-plugins --skill create-an-asset
0 commentsdiscussion
summary

Generate custom sales assets tailored to your prospect, audience, and goals. Supports interactive landing pages, presentation decks, executive one-pagers, and workflow/architecture demos.

skill.md

Create an Asset

Generate custom sales assets tailored to your prospect, audience, and goals. Supports interactive landing pages, presentation decks, executive one-pagers, and workflow/architecture demos.


Triggers

Invoke this skill when:

  • User says /create-an-asset or /create-an-asset [CompanyName]
  • User asks to "create an asset", "build a demo", "make a landing page", "mock up a workflow"
  • User needs a customer-facing deliverable for a sales conversation

Overview

This skill creates professional sales assets by gathering context about:

  • (a) The Prospect — company, contacts, conversations, pain points
  • (b) The Audience — who's viewing, what they care about
  • (c) The Purpose — goal of the asset, desired next action
  • (d) The Format — landing page, deck, one-pager, or workflow demo

The skill then researches, structures, and builds a polished, branded asset ready to share with customers.


Phase 0: Context Detection & Input Collection

Step 0.1: Detect Seller Context

From the user's email domain, identify what company they work for.

Actions:

  1. Extract domain from user's email
  2. Search: "[domain]" company products services site:linkedin.com OR site:crunchbase.com
  3. Determine seller context:
Scenario Action
Single-product company Auto-populate seller context
Multi-product company Ask: "Which product or solution is this asset for?"
Consultant/agency/generic domain Ask: "What company or product are you representing?"
Unknown/startup Ask: "Briefly, what are you selling?"

Store seller context:

seller:
  company: "[Company Name]"
  product: "[Product/Service]"
  value_props:
    - "[Key value prop 1]"
    - "[Key value prop 2]"
    - "[Key value prop 3]"
  differentiators:
    - "[Differentiator 1]"
    - "[Differentiator 2]"
  pricing_model: "[If publicly known]"

Persist to knowledge base for future sessions. On subsequent invocations, confirm: "I have your seller context from last time — still selling [Product] at [Company]?"


Step 0.2: Collect Prospect Context (a)

Ask the user:

Field Prompt Required
Company "Which company is this asset for?" ✓ Yes
Key contacts "Who are the key contacts? (names, roles)" No
Deal stage "What stage is this deal?" ✓ Yes
Pain points "What pain points or priorities have they shared?" No
Past materials "Upload any conversation materials (transcripts, emails, notes, call recordings)" No

Deal stage options:

  • Intro / First meeting
  • Discovery
  • Evaluation / Technical review
  • POC / Pilot
  • Negotiation
  • Close

Step 0.3: Collect Audience Context (b)

Ask the user:

Field Prompt Required
Audience type "Who's viewing this?" ✓ Yes
Specific roles "Any specific titles to tailor for? (e.g., CTO, VP Engineering, CFO)" No
Primary concern "What do they care most about?" ✓ Yes
Objections "Any concerns or objections to address?" No

Audience type options:

  • Executive (C-suite, VPs)
  • Technical (Architects, Engineers, Developers)
  • Operations (Ops, IT, Procurement)
  • Mixed / Cross-functional

Primary concern options:

  • ROI / Business impact
  • Technical depth / Architecture
  • Strategic alignment
  • Risk mitigation / Security
  • Implementation / Timeline

Step 0.4: Collect Purpose Context (c)

Ask the user:

Field Prompt Required
Goal "What's the goal of this asset?" ✓ Yes
Desired action "What should the viewer do after seeing this?" ✓ Yes

Goal options:

  • Intro / First impression
  • Discovery follow-up
  • Technical deep-dive
  • Executive alignment / Business case
  • POC proposal
  • Deal close

Step 0.5: Select Format (d)

Ask the user: "What format works best for this?"

Format Description Best For
Interactive landing page Multi-tab page with demos, metrics, calculators Exec alignment, intros, value prop
Deck-style Linear slides, presentation-ready Formal meetings, large audiences
One-pager Single-scroll executive summary Leave-behinds, quick summaries
Workflow / Architecture demo Interactive diagram with animated flow Technical deep-dives, POC demos, integrations

Step 0.6: Format-Specific Inputs

If "Workflow / Architecture demo" selected:

First, parse from user's description. Look for:

  • Systems and components mentioned
  • Data flows described
  • Human interaction points
  • Example scenarios

Then ask for any gaps:

If Missing... Ask...
Components unclear "What systems or components are involved? (databases, APIs, AI, middleware, etc.)"
Flow unclear "Walk me through the step-by-step flow"
Human touchpoints unclear "Where does a human interact in this workflow?"
Scenario vague "What's a concrete example scenario to demo?"
Integration specifics "Any specific tools or platforms to highlight?"

Phase 1: Research (Adaptive)

Assess Context Richness

Level Indicators Research Depth
Rich Transcripts uploaded, detailed pain points, clear requirements Light — fill gaps only
Moderate Some context, no transcripts Medium — company + industry
Sparse Just company name Deep — full research pass

Always Research:

  1. Prospect basics

    • Search: "[Company]" annual report investor presentation 2025 2026
    • Search: "[Company]" CEO strategy priorities 2025 2026
    • Extract: Revenue, employees, key metrics, strategic priorities
  2. Leadership

    • Search: "[Company]" CEO CTO CIO 2025
    • Extract: Names, titles, recent quotes on strategy/technology
  3. Brand colors

    • Search: "[Company]" brand guidelines
    • Or extract from company website
    • Store: Primary color, secondary color, accent

If Moderate/Sparse Context, Also Research:

  1. Industry context

    • Search: "[Industry]" trends challenges 2025 2026
    • Extract: Common pain points, market dynamics
  2. Technology landscape

    • Search: "[Company]" technology stack tools platforms
    • Extract: Current solutions, potential integration points
  3. Competitive context

    • Search: "[Company]" vs [seller's competitors]
    • Extract: Current solutions, switching signals

If Transcripts/Materials Uploaded:

  1. Conversation analysis
    • Extract: Stated pain points, decision criteria, objections, timeline
    • Identify: Key quotes to reference (use their exact language)
    • Note: Specific terminology, acronyms, internal project names

Phase 2: Structure Decision

Interactive Landing Page

Purpose Recommended Sections
Intro Company Fit → Solution Overview → Key Use Cases → Why Us → Next Steps
Discovery follow-up Their Priorities → How We Help → Relevant Examples → ROI Framework → Next Steps
Technical deep-dive Architecture → Security & Compliance → Integration → Performance → Support
Exec alignment Strategic Fit → Business Impact → ROI Calculator → Risk Mitigation → Partnership
POC proposal Scope → Success Criteria → Timeline → Team → Investment → Next Steps
Deal close Value Summary → Pricing → Implementation Plan → Terms → Sign-off

Audience adjustments:

  • Executive: Lead with business impact, ROI, strategic alignment
  • Technical: Lead with architecture, security, integration depth
  • Operations: Lead with workflow impact, change management, support
  • Mixed: Balance strategic + tactical; use tabs to separate depth levels

Deck-Style

Same sections as landing page, formatted as linear slides:

1. Title slide (Prospect + Seller logos, partnership framing)
2. Agenda
3-N. One section per slide (or 2-3 slides for dense sections)
N+1. Summary / Key takeaways
N+2. Next steps / CTA
N+3. Appendix (optional — detailed specs, pricing, etc.)

Slide principles:

  • One key message per slide
  • Visual > text-heavy
  • Use prospect's metrics and language
  • Include speaker notes

One-Pager

Condense to single-scroll format:

┌─────────────────────────────────────┐
│ HERO: "[Prospect Goal] with [Product]" │
├─────────────────────────────────────┤
│ KEY POINT 1     │ KEY POINT 2     │ KEY POINT 3     │
│ [Icon + 2-3     │ [Icon + 2-3     │ [Icon + 2-3     │
│  sentences]     │  sentences]     │  sentences]     │
├─────────────────────────────────────┤
│ PROOF POINT: [Metric, quote, or case study] │
├─────────────────────────────────────┤
│ CTA: [Clear next action] │ [Contact info] │
└─────────────────────────────────────┘

Workflow / Architecture Demo

Structure based on complexity:

Complexity Components Structure
Simple 3-5 Single-view diagram with step annotations
Medium 5-10 Zoomable canvas with step-by-step walkthrough
Complex 10+ Multi-layer view (overview → detailed) with guided tour

Standard elements:

  1. Title bar: [Scenario Name] — Powered by [Seller Product]
  2. Component nodes: Visual boxes/icons for each system
  3. Flow arrows: Animated connections showing data movement
  4. Step panel: Sidebar explaining current step in plain language
  5. Controls: Play / Pause / Step Forward / Step Back / Reset
  6. Annotations: Callouts for key decision points and value-adds
  7. Data preview: Sample payloads or transformations at each step

Phase 3: Content Generation

General Principles

All content should:

  • Reference specific pain points from user input or transcripts
  • Use prospect's language — their terminology, their stated priorities
  • Map seller's productprospect's needs explicitly
  • Include proof points where available (case studies, metrics, quotes)
  • Feel tailored, not templated

Section Templates

Hero / Intro

Headline: "[Prospect's Goal] with [Seller's Product]"
Subhead: Tie to their stated priority or top industry challenge
Metrics: 3-4 key facts about the prospect (shows we did homework)

Their Priorities (if discovery follow-up)

Reference specific pain points from conversation:
- Use their exact words where possible
- Show we listened and understood
- Connect each to how we help

Solution Mapping

For each pain point:
├── The challenge (in their words)
├── How [Product] addresses it
├── Proof point or example
└── Outcome / benefit

Use Cases / Demos

3-5 relevant use cases:
├── Visual mockup or interactive demo
├── Business impact (quantified if possible)
├── "How it works" — 3-4 step summary
└── Relevant to their industry/role

ROI / Business Case

Interactive calculator with:
├── Inputs relevant to their business (from research)
│   ├── Number of users/developers
│   ├── Current costs or time spent
│   └── Expected improvement %
├── Outputs:
│   ├── Annual value / savings
│   ├── Cost of solution
│   ├── Net ROI
│   └── Payback period
└── Assumptions clearly stated (editable)

Why Us / Differentiators

├── Differentiators vs. alternatives they might consider
├── Trust, security, compliance positioning
├── Support and partnership model
└── Customer proof points (logos, quotes, case studies)

Next Steps / CTA

├── Clear action aligned to Purpose (c)
├── Specific next step (not vague "let's chat")
├── Contact information
├── Suggested timeline
└── What happens after they take action

Workflow Demo Content

Component Definitions

For each system, define:

component:
  id: "snowflake"
  label: "Snowflake Data Warehouse"
  type: "database"  # database | api | ai | middleware | human | document | output
  icon: "database"
  description: "Financial performance data"
  brand_color: "#29B5E8"

Component types:

  • human — Person initiating or receiving
  • document — PDFs, contracts, files
  • ai — AI/ML models, agents
  • database — Data stores, warehouses
  • api — APIs, services
  • middleware — Integration platforms, MCP servers
  • output — Dashboards, reports, notifications

Flow Steps

For each step, define:

step:
  number: 1
  from: "human"
  to: "claude"
  action: "Initiates performance review"
  description: "Sarah, a Brand Analyst at [Prospect], kicks off the quarterly review..."
  data_example: "Review request: Nike brand, Q4 2025"
  duration: "~1 second"
  value_note: "No manual data gathering required"

Scenario Narrative

Write a clear, specific walkthrough:

Step 1: Human Trigger
"Sarah, a Brand Performance Analyst at Centric Brands, needs to review
Q4 performance for the Nike license agreement. She opens the review
dashboard and clicks 'Start Review'..."

Step 2: Contract Analysis
"Claude retrieves the Nike contract PDF and extracts the performance
obligations: minimum $50M revenue, 12% margin requirement, quarterly
reporting deadline..."

Step 3: Data Query
"Claude formulates a query and sends it to Workato DataGenie:
'Get Q4 2025 revenue and gross margin for Nike brand from Snowflake'..."

Step 4: Results & Synthesis
"Snowflake returns the data. Claude compares actuals vs. obligations:
Revenue $52.3M ✓ (exceede
how to use create-an-asset

How to use create-an-asset on Cursor

AI-first code editor with Composer

1

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

  • Cursor installed and configured on your development machine
  • Node.js version 16.0+ with npm package manager (verify with node --version)
  • Active project directory or workspace where you want to add create-an-asset
2

Execute installation command

Execute the skills CLI command in your project's root directory to begin installation:

$npx skills add https://github.com/anthropics/knowledge-work-plugins --skill create-an-asset

The skills CLI fetches create-an-asset from GitHub repository anthropics/knowledge-work-plugins and configures it for Cursor.

3

Select Cursor when prompted

The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:

◆ Which agents do you want to install to?
│ ── Universal (.agents/skills) ── always included ────
│ • Amp
│ • Antigravity
│ • Cline
│ • Codex
│ ●Cursor(selected)
│ • Cursor
│ • Windsurf
4

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/create-an-asset

Reload or restart Cursor to activate create-an-asset. Access the skill through slash commands (e.g., /create-an-asset) or your agent's skill management interface.

Security & Verification Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.

List & Monetize Your Skill

Submit your Claude Code skill and start earning

GET_STARTED →

Use Cases

User Story & Requirements Generation

Create detailed user stories, acceptance criteria, and feature specs

Example

Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios

Reduce spec writing time by 50%, ensure comprehensive coverage

Competitive Analysis

Research competitors, compare features, identify gaps

Example

Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities

Complete competitive research in 2 hours instead of 2 days

Roadmap Prioritization

Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs

Example

Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale

Make data-driven prioritization decisions faster

Stakeholder Communication

Draft PRDs, status updates, and stakeholder presentations

Example

Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement

Save 3-5 hours/week on communication overhead

Implementation Guide

Prerequisites

  • Claude Desktop or compatible AI client
  • Access to product documentation and roadmap tools (Jira, Notion, etc.)
  • Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
  • Stakeholder contact information and communication channels

Time Estimate

30-60 minutes to see productivity improvements

Installation Steps

  1. 1.Install product management skill
  2. 2.Start with user story generation for known feature
  3. 3.Progress to competitive analysis: research 2-3 competitors
  4. 4.Use for roadmap prioritization: apply RICE/ICE scoring
  5. 5.Draft stakeholder communications and refine based on feedback
  6. 6.Build template library for recurring PM tasks
  7. 7.Share effective prompts with product team

Common Pitfalls

  • Not validating competitive research—verify facts before sharing
  • Accepting user stories without involving engineering team
  • Over-relying on frameworks without qualitative judgment
  • Not customizing outputs to company culture and communication style
  • Skipping stakeholder validation of generated requirements

Best Practices

✓ Do

  • +Validate research and competitive analysis with real data
  • +Collaborate with engineering when generating technical requirements
  • +Customize frameworks and templates to your company context
  • +Use skill for first drafts, refine with stakeholder input
  • +Document successful prompt patterns for PM tasks
  • +Combine AI efficiency with human judgment and intuition

✗ Don't

  • Don't publish competitive analysis without fact-checking
  • Don't finalize user stories without engineering review
  • Don't make prioritization decisions solely on AI scoring
  • Don't skip customer validation of generated requirements
  • Don't ignore company-specific context and culture

💡 Pro Tips

  • Provide context: company goals, constraints, customer feedback
  • Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
  • Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
  • Use skill for 70% generation + 30% customization to company needs

When to Use This

✓ Use When

Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.

✗ Avoid When

Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.

Learning Path

  1. 1Basic: user stories, feature specs, status updates
  2. 2Intermediate: competitive analysis, prioritization frameworks, PRDs
  3. 3Advanced: product strategy, go-to-market planning, OKR setting
  4. 4Expert: product vision, market positioning, business model innovation

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.670 reviews
  • William Martin· Dec 20, 2024

    create-an-asset reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Nikhil Khanna· Dec 12, 2024

    create-an-asset has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • Charlotte Li· Dec 12, 2024

    I recommend create-an-asset for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Soo Liu· Dec 8, 2024

    Registry listing for create-an-asset matched our evaluation — installs cleanly and behaves as described in the markdown.

  • Nia Harris· Dec 4, 2024

    Solid pick for teams standardizing on skills: create-an-asset is focused, and the summary matches what you get after install.

  • Aanya Harris· Dec 4, 2024

    create-an-asset fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

  • Ishan Lopez· Dec 4, 2024

    Useful defaults in create-an-asset — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Maya Singh· Nov 27, 2024

    Registry listing for create-an-asset matched our evaluation — installs cleanly and behaves as described in the markdown.

  • Aanya Garcia· Nov 23, 2024

    We added create-an-asset from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.

  • Kiara Martinez· Nov 23, 2024

    create-an-asset has been reliable in day-to-day use. Documentation quality is above average for community skills.

showing 1-10 of 70

1 / 7