AGENT SKILL

portfolio-case-study-writer

Transform resume bullets into detailed portfolio case studies with context, action, and outcome. Use when the user mentions portfolio, case study, project write-up, or expanding a resume bullet into a longer narrative.

License 许可
MIT
最近更新
2026-11-14
Stars
★ 3.3w
Forks
3.9k

01 前言 Front Matter

name
portfolio-case-study-writer
description
Transform resume bullets into detailed portfolio case studies with context, action, and outcome. Use when the user mentions portfolio, case study, project write-up, or expanding a resume bullet into a longer narrative.

02 资源文件 3

03 SKILL.md 正文

Portfolio Case Study Writer

When to Use This Skill

Use this skill when the user:

  • Wants to create portfolio case studies
  • Needs to expand resume bullets into detailed writeups
  • Is building a portfolio website
  • Wants to showcase project work in depth
  • Mentions: "case study", "portfolio", "project writeup", "work samples", "portfolio piece"

Core Capabilities

  • Transform resume bullets into detailed case studies
  • Structure case studies for maximum impact
  • Create compelling project narratives
  • Balance technical detail with business context
  • Format for portfolio websites
  • Tailor depth to audience

Case Study Purpose

Why Case Studies Matter:

  • Resumes show WHAT you did; case studies show HOW and WHY
  • Demonstrate thinking process, not just outcomes
  • Allow deeper showcase of skills
  • Differentiate you from other candidates
  • Required for many PM, UX, and creative roles

The Case Study Structure

Standard Structure

1. Overview (Project summary)
2. Problem (What needed to be solved)
3. Process (How you approached it)
4. Solution (What you created/delivered)
5. Results (The impact)
6. Learnings (What you'd do differently)

Time to Read

  • Quick Read: 3-5 minutes (essential for portfolio)
  • Deep Dive: 10-15 minutes (for interested readers)

Section-by-Section Guide

1. Overview Section

Purpose: Hook the reader, provide context

Include:

  • Project name and company
  • Your role
  • Timeline
  • Team size
  • One-sentence summary of impact

Example:

# Redesigning the Checkout Flow

**Company:** E-Commerce Inc.
**Role:** Lead Product Designer
**Timeline:** 6 weeks
**Team:** 2 designers, 3 engineers, 1 PM

**Summary:** Reduced cart abandonment by 35% through a streamlined 3-step checkout process, generating $2M in recovered revenue.

2. Problem Section

Purpose: Set up why this work mattered

Include:

  • Business context
  • User pain points
  • Key metrics or goals
  • Constraints

Example:

## The Problem

E-Commerce Inc. was experiencing 68% cart abandonment—significantly higher than the industry average of 55%. Exit surveys and user research revealed several issues:

- **Too many steps:** Our checkout had 7 screens
- **Forced account creation:** Users had to register before purchasing
- **Hidden costs:** Shipping wasn't shown until step 5
- **Mobile friction:** Forms weren't optimized for mobile

**Goal:** Reduce cart abandonment to below 50% within 3 months.

**Constraints:**
- No changes to existing payment integrations
- Had to maintain PCI compliance
- 6-week timeline before holiday season

3. Process Section

Purpose: Show your thinking and methodology

Include:

  • Research conducted
  • Stakeholders involved
  • Hypotheses formed
  • Options considered
  • Decisions made (and why)

Example:

## Process

### Research
I started by understanding the problem deeply:
- Analyzed Mixpanel funnel data for drop-off points
- Conducted 10 user interviews with recent abandoners
- Reviewed heatmaps and session recordings
- Benchmarked against 5 competitor checkout flows

**Key Insight:** 73% of drop-offs occurred at the account creation screen. Users wanted to purchase, not commit to a relationship.

### Ideation
I explored several approaches:
1. Guest checkout only (simplest)
2. Social login options (lower friction)
3. Progressive profiling (collect info over time)
4. One-page checkout (Amazon-style)

After weighing feasibility, timeline, and impact, we chose a hybrid approach...

### Decisions Made
- **Guest checkout first:** Made registration optional and post-purchase
- **Transparent pricing:** Showed shipping on the first screen
- **Mobile-first design:** Designed for mobile, then adapted for desktop
- **Progress indicator:** Added clear "Step 1 of 3" indicator

4. Solution Section

Purpose: Show what you actually created

Include:

  • Visual artifacts (mockups, screenshots, diagrams)
  • Key features/changes
  • Technical implementation (if relevant)
  • How it addressed the problems

Example:

## Solution

### The New Checkout Flow

**Before:** 7 screens with mandatory registration
**After:** 3 screens with optional guest checkout

[IMAGE: Before/After comparison]

### Key Changes

**1. Transparent Pricing Widget**
[IMAGE: Pricing widget mockup]
Showed order total, shipping, and taxes from the start. No surprises.

**2. Guest Checkout Option**
[IMAGE: Guest checkout screen]
Made account creation optional with clear value proposition for why to register.

**3. Smart Form Design**
[IMAGE: Form design]
- Single-column layout on mobile
- Auto-format for phone/card numbers
- Address autocomplete integration
- Clear error messaging

**4. Trust Signals**
Added security badges, money-back guarantee, and customer service contact throughout the flow.

5. Results Section

Purpose: Prove impact with data

Include:

  • Quantitative results (with timeframe)
  • Comparison to goals
  • Secondary metrics affected
  • Business impact

Example:

## Results

### Primary Metrics (90 days post-launch)

| Metric | Before | After | Change |
|--------|--------|-------|--------|
| Cart Abandonment | 68% | 44% | -35% |
| Checkout Completion | 32% | 56% | +75% |
| Mobile Conversion | 18% | 41% | +128% |
| Revenue per Visitor | $2.40 | $3.85 | +60% |

### Business Impact
- **$2M additional revenue** in first quarter
- **15% increase in mobile orders**
- **Customer support tickets about checkout** dropped by 45%

### Secondary Effects
- Account creation actually increased 20% (post-purchase)
- Average order value stayed stable
- Return customer rate improved

6. Learnings Section

Purpose: Show growth mindset and self-awareness

Include:

  • What worked well
  • What you'd do differently
  • Unexpected challenges
  • Skills developed

Example:

## Learnings

### What Worked
- **Early user research** prevented us from building the wrong solution
- **Cross-functional alignment** meetings kept everyone on the same page
- **Launching with analytics** let us measure impact immediately

### What I'd Do Differently
- **More A/B testing:** We launched the full redesign at once. Would have preferred to test individual changes to understand what drove results.
- **Earlier mobile focus:** We designed desktop-first then adapted. Starting mobile-first would have been more efficient.
- **Stakeholder education:** Spent too long convincing leadership. Would start stakeholder alignment earlier next time.

### Skills Developed
- Advanced Figma prototyping
- Working with A/B testing frameworks
- Presenting data-driven design decisions to executives

Case Study Types by Role

Product Manager Case Study

Focus on:

  • Strategy and prioritization
  • Stakeholder management
  • Metrics and outcomes
  • Technical trade-offs

UX/Product Designer Case Study

Focus on:

  • User research
  • Design process
  • Visual artifacts
  • Usability improvements

Software Engineer Case Study

Focus on:

  • Technical architecture
  • Problem-solving approach
  • System design
  • Code quality/performance

Marketing Case Study

Focus on:

  • Strategy and targeting
  • Creative execution
  • Channel performance
  • ROI and attribution

Visual Elements

Must-Have Visuals

  • Before/after comparisons
  • Key screens or deliverables
  • Process diagrams
  • Results charts

Nice-to-Have Visuals

  • User journey maps
  • Wireframes evolution
  • Research artifacts
  • Team photos

Visual Tips

  • Use consistent image sizing
  • Add captions explaining each image
  • Blur sensitive data if needed
  • Ensure mobile-friendly image sizes

Output Format

When creating a case study:

# CASE STUDY: [PROJECT NAME]

## Quick Facts
- **Role:** [Your role]
- **Company:** [Company]
- **Timeline:** [Duration]
- **Team:** [Team composition]
- **Impact:** [One-line result]

---

## Overview
[2-3 sentence summary of the project]

## Problem
[Context and challenges - what needed to be solved]

## Process
### Research
[What you learned]

### Approach
[How you tackled it]

### Key Decisions
[Important choices and rationale]

## Solution
[What you built/created - include visual descriptions]

### Feature 1
[Description]

### Feature 2
[Description]

## Results
[Quantified impact]

| Metric | Before | After | Change |
|--------|--------|-------|--------|

## Learnings
[Reflections and growth]

---

## Visual Asset List
[List of images/screenshots needed]

Case Study Quality Checklist

  • ✅ Clear problem statement
  • ✅ Evidence of user/customer focus
  • ✅ Process clearly explained
  • ✅ Your specific contributions are clear
  • ✅ Quantified results
  • ✅ Visual artifacts included
  • ✅ Honest about challenges/learnings
  • ✅ Appropriate length (3-10 min read)
  • ✅ Proofread and polished
  • ✅ Can discuss in detail in interview

04 同仓库更多 Skills

davila7
davila7/claude-code-templates

wealthville-pool-scoring

Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter/Hold/Exit/Reduce/Avoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.

Skill与智能体开发
★ 3.3w
davila7
davila7/claude-code-templates

technical-debt-auditor

Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO/FIXME/HACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like "where should I focus refactoring", "find code smells", "audit my codebase", "what technical debt do we have", "prioritize cleanup work", or asks about code quality metrics. Also trigger when the user mentions "code rot", "legacy cleanup", "refactoring priorities", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say "technical debt" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.

Skill与智能体开发
★ 3.3w
davila7
davila7/claude-code-templates

readonly-sql-guard

Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production/ERP/analytics database (a "query" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write/DDL/side-effect/transaction-escape risks. Checks what a statement CALLS, not just its shape.

数据分析师后端与接口Skill与智能体开发
★ 3.3w
davila7
davila7/claude-code-templates

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

前端开发
★ 3.3w
davila7
davila7/claude-code-templates

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

测试与质量前端开发
★ 3.3w
davila7
davila7/claude-code-templates

discernment-nudge

After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.

内容创作者写作与文案Skill与智能体开发
★ 3.3w