CCM
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
wondelai avatar

Inspired Product

wondelai/skills
3.6k installs1.9k stars
Summary

This is for when you're tired of being a feature factory and want to build like the product teams at Stripe or Linear. It gives you the Marty Cagan playbook: dual-track discovery and delivery, empowered teams that own problems instead of backlogs, and specific techniques like opportunity assessments and prototype testing. The scoring system (rate your setup 0-10, get concrete gaps to fix) is surprisingly useful for diagnosing why your roadmap feels like theater. It's opinionated about what real product work looks like, which means it'll either clarify everything or argue with your VP. Works best when you're restructuring teams or need language to push back on building things nobody wants.

Install to Claude Code

npx -y skills add wondelai/skills --skill inspired-product --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Files
SKILL.mdView on GitHub

Empowered Product Teams Framework

Framework for building products customers love through empowered teams that own continuous discovery and delivery. The best product companies don't ship features -- they solve problems, and they give teams the autonomy and accountability to figure out how.

Core Principle

Empowered product teams = cross-functional groups given problems to solve (not features to build) who own discovery and delivery end-to-end.

Most product failures come not from bad engineering or design but from building things nobody wants. Feature teams receive roadmaps and execute; empowered teams receive objectives and discover solutions. The difference between a feature factory and an innovation engine is whether teams are missionaries (driven by vision and empathy) or mercenaries (driven by a handed-down backlog).

Scoring

Goal: 7/7. Score product team structures, discovery practices, or delivery processes by the Quick Diagnostic below -- 1 point per satisfied row, scored 0-7. Bands: 6-7 = empowered teams own outcomes and discovery runs continuously with engineers; 4-5 = discovery happens but inconsistently, or teams own output with partial outcome accountability; <=3 = a feature factory: teams receive a roadmap of dated features and skip discovery. Always state the current score and the specific failed diagnostic rows to fix to reach 7/7.

Framework

1. Product Discovery vs Delivery

Core concept: Product work runs on two parallel tracks: discovery determines what to build by addressing risks before engineering investment; delivery builds production-quality software. Most organizations skip discovery entirely, jumping from idea to backlog to sprint.

Why it works: Discovery is cheap and fast; delivery is expensive and slow. Validating ideas before committing engineering avoids the most common failure mode: building something nobody wants.

Key insights:

  • Discovery answers four risks: value (will customers use it?), usability (can they figure it out?), feasibility (can we build it?), viability (does it work for the business?)
  • Discovery output is validated ideas backed by evidence, not PRDs or specifications
  • Run 10-20 discovery iterations per feature that reaches delivery -- most ideas won't work, so fail fast and cheap
  • Discovery is not a phase; it runs continuously alongside delivery, with engineers participating

Product applications:

ContextApplicationExample
New featureValidate all four risks before committingPrototype-test onboarding flow with 5 users before building
Roadmap prioritizationPrioritize strongest discovery evidenceShip the feature with 4/5 successful user tests, not the CEO's request
Sprint planningFeed backlog from validated discovery outputOnly discovery-tested items enter the sprint

Ethical boundary: Never cherry-pick discovery evidence to justify a conclusion you already chose; report the tests that failed alongside the ones that passed.

See references/discovery-techniques.md when planning a discovery cycle -- the four-risks framework, a 5-stage interview script, prototyping techniques, and concrete evidence thresholds for "validated".

2. Empowered Product Teams

Core concept: A small, durable, cross-functional group (product manager, product designer, engineers) given a problem to solve, owning discovery and delivery, accountable for outcomes rather than output.

Why it works: The people closest to the customer and the technology find better solutions than a remote roadmap author -- and a team that discovered the solution itself defends and refines it under pressure, where a team handed a spec ships it and moves on.

Key insights:

  • The PM is not a project manager or backlog administrator -- they own value and viability and need deep knowledge of customers, data, business, and industry
  • The product designer owns the user experience holistically, not just visual design
  • Engineers are the best source of innovation because they know what is technically possible
  • Keep teams durable (stable membership) and highly collaborative
  • Accountability means outcomes (adoption, retention, revenue), not output (stories shipped)

Product applications:

ContextApplicationExample
Team structureOrganize around outcomes, not components"New user activation" team owns the whole first-week experience
HiringHire PMs for competence, not credentialsEvaluate customer knowledge, data fluency, business acumen
PerformanceMeasure results, not velocityTrack activation-rate improvement, not stories per sprint

Ethical boundary: Never claim to empower teams while overriding their discovery findings with executive mandates -- if leadership dictates the solution, the team is not empowered.

See references/empowered-teams.md when staffing or diagnosing a team -- role-by-role competence breakdowns with red flags, missionary vs mercenary dynamics, coaching, and a feature-factory-to-empowered transformation table.

3. Product Discovery Techniques

Core concept: Systematically test ideas against the four risks using opportunity assessment, customer interviews, prototyping, and user testing -- producing evidence quickly and cheaply.

Why it works: Ideas are assumptions; without rapid testing, teams build for months on untested assumptions and discover failure only after launch. Discovery techniques compress learning cycles from months to days.

Key insights:

  • Prototypes are the primary tool: high-fidelity for usability, live-data for feasibility, Wizard of Oz for value
  • Test with real target users, not colleagues; qualitative testing (5 users) reveals problems, quantitative validates at scale
  • Interview for behavior (what they did), not opinion (what they say they want)
  • Data reveals patterns but not causes -- pair it with qualitative discovery
  • Feasibility spikes let engineers explore technical risk without full implementation

Product applications:

ContextApplicationExample
Early ideaOpportunity assessment before design workWho is it for, what problem, how will we measure success?
UsabilityHigh-fidelity prototype with 5 target usersClickable Figma prototype testing task completion
ValueFake door or Wizard of Oz testButton for unbuilt feature, measure click-through
FeasibilityEngineering spikeTwo-day investigation of real-time sync risk

Ethical boundary: Never deceive users beyond what valid results require -- Wizard of Oz prototypes are acceptable; collecting payment for non-existent products is not.

4. Opportunity Assessment

Core concept: Before investing in any opportunity, evaluate business value, customer need severity, market context, and organizational readiness against a structured set of questions.

Why it works: Organizations have far more ideas than capacity; without rigorous assessment, teams default to the loudest stakeholder or competitor parity. A shared framework kills bad ideas early and focuses resources on high-impact work.

Key insights:

  • Key questions: What business objective does this serve? Who is the target customer? What problem? How will we know we succeeded? What alternatives exist?
  • Severity of the customer problem matters more than elegance of the solution
  • Market timing is critical -- too early is as dangerous as too late
  • Check organizational readiness: skills, technology, go-to-market capability
  • Share assessments broadly to build alignment before committing resources

Product applications:

ContextApplicationExample
Quarterly planningScore all candidates on consistent criteriaCustomer severity, business impact, feasibility per opportunity
Stakeholder requestsRespond with assessment, not commitment"Let me assess this and share findings before we commit engineering"
Resource allocationFund highest-assessed opportunitiesSevere pain + clear business alignment beats the nice-to-have

See references/opportunity-assessment.md when sizing a new opportunity before design work -- the full evaluation-question set, market-timing assessment, and prioritization scoring.

See references/stakeholder-management.md when an executive or sales stakeholder hands you a solution or a HiPPO is steering the roadmap -- stakeholder mapping, turning a mandate into a problem to assess, evangelism, and building executive trust.

5. Product Vision and Strategy

Core concept: Vision describes the future you're building toward (2-5 years out); strategy sequences the target markets, problems, and solutions that will realize it. Together they give empowered teams the context to make good autonomous decisions.

Why it works: Without vision, teams make disconnected decisions; without strategy, they chase everything and achieve nothing. Vision inspires; strategy focuses.

Key insights:

  • Vision is inspiring and customer-centric -- the world you want to create, not a feature list
  • Strategy sequences the hard choices: which customers first, which problems first, which solutions first
  • Product principles are guardrails for decisions the strategy doesn't cover
  • OKRs translate strategy into measurable team objectives; outcome-based roadmaps communicate intent without prescribing solutions
  • Revisit vision annually, strategy quarterly; principles change rarely

Product applications:

ContextApplicationExample
Company alignmentVision aligns all teams on a shared future"Every small business can access world-class financial tools"
Team autonomyStrategy scopes each team's focus"This quarter: cut mid-market churn via top 3 pain points"
Decision-makingPrinciples resolve tradeoffs"When in doubt, choose simplicity over power"

Ethical boundary: Never present a vision you know is unachievable to motivate teams or attract investment.

See references/product-vision.md when drafting or revisiting vision and strategy -- how to write each, product principles, translating strategy into OKRs, and building outcome-based roadmaps.

6. Continuous Value Delivery

Core concept: Delivery is not a launch event but a continuous flow of small, validated increments shipped to real users as frequently as possible.

Why it works: Large infrequent releases accumulate risk, delay learning, and create coordination nightmares. The feedback loop between delivery and discovery compounds into a learning engine: ship, measure, learn, adjust.

Key insights:

  • Ship small and often; every release is a learning opportunity
  • Instrumentation is not optional -- if you cannot measure it, you cannot learn from it
  • Feature flags decouple deployment from release, enabling controlled rollouts and quick rollbacks
  • MVP is the smallest release that tests a hypothesis, not a half-built product
  • Manage technical debt like financial debt: conscious tradeoffs

Product applications:

ContextApplicationExample
Release planningIndependently shippable incrementsBasic search first, then filters, then saved searches
Risk managementFeature flags for controlled rolloutShip to 5%, measure, expand or roll back
Learning loopsInstrument every release to feed discoveryLow search usage triggers a discovery investigation

Ethical boundary: Never ship a change you cannot roll back; gate anything risky behind a flag you can flip off.

See references/case-studies.md when you want a worked example before applying the framework -- these principles played out at startup, growth, and enterprise stages.

Common Mistakes

MistakeWhy It FailsFix
Treating PMs as project managersOrder-takers with no ownership of value or viabilityHire for customer knowledge, data fluency, business acumen; hold accountable for outcomes
Skipping discoveryMonths of engineering on features nobody wantsRequire validated evidence before ideas enter the delivery backlog
Measuring output, not outcomesTeams optimize shipping speed over customer valueDefine success as adoption, retention, revenue impact
Handing teams solutions, not problemsFeature factories with no motivation or creativityAssign objectives and key results; let teams discover solutions
Isolating engineers from customersBest source of innovation never sees the problemInclude engineers in interviews, discovery, prototype testing
Roadmaps of promised features with datesCommitments calcify before discovery can validateUse outcome-based roadmaps: problems to solve, not features

Quick Diagnostic

QuestionIf NoAction
Can your PM cite the top 3 customer problems from direct observation?PM lacks customer knowledgeWeekly customer contact: interviews, support shadowing, testing
Do you test ideas with real users before building?Skipping discoveryPrototype-test with 5 target users for every significant idea
Are engineers involved in discovery, not just delivery?Underusing your best innovatorsInvite engineers to interviews and prototype sessions
Does the team own outcomes (metrics), not output (features)?Feature factoryReplace feature roadmaps with outcome OKRs
Can team members explain the vision and strategy?No context for autonomous decisionsCreate and evangelize a vision doc and quarterly strategy
Do stakeholders bring problems, not solutions?Leadership dictating featuresCoach stakeholders on discovery; pre-sell with opportunity assessments
Do you ship validated increments at least every two weeks?Too slow to learnSmaller increments; invest in CI/CD and feature flags

Further Reading

For the complete methodology, case studies, and deeper insights:

  • "Inspired: How to Create Tech Products Customers Love" by Marty Cagan
  • "Empowered: Ordinary People, Extraordinary Products" by Marty Cagan and Chris Jones

About the Author

Marty Cagan is the founder of Silicon Valley Product Group (SVPG) and a former VP of Product at eBay, with senior product roles at HP, Netscape, and AOL. His book Inspired (2008; 2nd ed. 2017) became the definitive guide to modern product management, and Empowered (2020) extends the framework to product leadership. Through SVPG he coaches product teams from startups to Fortune 500 enterprises.

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Categories
Testing & QADevOps & CI/CDProductivity & PlanningSales & Marketing
First SeenApr 16, 2026
View on GitHub

More from wondelai/skills

All 50 skills →
  • Traction Eos3.6k
  • 37signals Way2.8k
  • Steve Jobs Design Review1.6k
  • Working With Legacy Code1.6k
  • Good Strategy Bad Strategy1.5k
  • Lean Analytics1.5k
  • Monetizing Innovation1.5k
  • Team Topologies1.5k
  • Cold Start Problem1.5k
  • High Output Management1.5k
  • Web Typography6.8k
  • Refactoring Ui6.2k
  • Ux Heuristics5.9k
  • Ios Hig Design5.2k
  • Top Design5.1k
  • Domain Driven Design5.1k
  • Clean Architecture5k
  • Jobs To Be Done4.8k
  • Clean Code4.6k
  • Microinteractions4.5k
  • Refactoring Patterns4.5k
  • Hooked Ux4.4k
  • Cro Methodology4.4k
  • Software Design Philosophy4.3k

Recommended

More Testing & QA →
aws avatar
creating-api-gateway-stage

aws/agent-toolkit-for-aws

Creates an API Gateway stage with CloudWatch logging, X-Ray tracing, throttling, WAF integration, and IAM roles following AWS best practices. Use when deploying a REST API to different environments such as dev, test, or production.
3.6k
2.3k
epiral avatar
bb-browser

epiral/bb-browser

强大的信息获取与浏览器自动化工具。通过浏览器 + 用户登录态,获取公域和私域信息。可访问任意网页、内部系统、登录后页面,执行表单填写、信息提取、页面操作。支持 site 系统(36 平台 103 命令一键调用)、带登录态的 fetch、网络请求拦截与 mock、操作录制等高级功能。
3.6k
6k
lynx-community avatar
lynx-devtool

lynx-community/skills

Use when working with Lynx DevTool or debugging a Lynx app, page, or device, especially when the task mentions clients or sessions, CDP or App commands, DOM/CSS inspection, runtime or console logs, evaluating JavaScript on a device, screenshots, heap snapshots, performance traces, Page.reload or App.openPage, global switches, interactive snapshot refs and taps/fills/scrolls, inspecting or searching a ReactLynx component tree, linking DOM Snapshot refs to ReactLynx components (`reactlynx link`), or mutating ReactLynx props/state/context on Android, iOS, or Desktop.
3.6k
25
trailofbits avatar
debug-buttercup

trailofbits/skills

Debugs the Buttercup CRS (Cyber Reasoning System) running on Kubernetes. Use when diagnosing pod crashes, restart loops, Redis failures, resource pressure, disk saturation, DinD issues, or any service misbehavior in the crs namespace. Covers triage, log analysis, queue inspection, and common failure patterns for: redis, fuzzer-bot, coverage-bot, seed-gen, patcher, build-bot, scheduler, task-server, task-downloader, program-model, litellm, dind, tracer-bot, merger-bot, competition-api, pov-reproducer, scratch-cleaner, registry-cache, image-preloader, ui.
3.5k
6.5k
aws avatar
exporting-rds-to-s3

aws/agent-toolkit-for-aws

Exports Amazon RDS or Aurora database snapshots to Amazon S3 in Apache Parquet format for analytics, backup, or data migration. Handles snapshot selection or creation, IAM role setup, KMS encryption, S3 bucket preparation, export task execution, progress monitoring, and data verification. Use when exporting RDS/Aurora data to S3 for Athena, Glue, or Redshift Spectrum consumption.
3.4k
2.3k
dpearson2699 avatar
ios-localization

dpearson2699/swift-ios-skills

Implement, review, or improve localization and internationalization in iOS/macOS apps — String Catalogs (.xcstrings), generated localizable symbols, stable key naming, LocalizedStringKey, LocalizedStringResource, pluralization, FormatStyle for numbers/dates/measurements, right-to-left layout, Dynamic Type, and locale-aware formatting. Use when adding multi-language support, setting up String Catalogs, enabling generated symbols for compile-time-safe localization keys, handling plural forms, formatting dates/numbers/currencies for different locales, testing localizations, or making UI work correctly in RTL languages like Arabic and Hebrew.
3.3k
981