empathy
Use to measure cognitive load of code — what's frustrating, what's hard to understand, where readers waste mental cycles. Outputs friction map + ranked refactor candidates by user pain, not architectural elegance.
What this skill does
# empathy
Code review from the **next reader's** perspective. Quantifies friction. Refactor candidates ranked by reader pain, not abstract code-smell metrics.
## Method
1. **Pick the reader.** Most useful is "engineer joining the team next week, has 2 hours to get oriented". Tailor to a different persona if user requests.
2. **Friction probes** (per file/function):
- **Naming** — does the name match what it does? Unsurprising?
- **Length** — can the reader hold it in their head?
- **Indentation** — > 3 levels = where am I
- **Implicit context** — needs to know X, Y, Z to understand
- **Surprises** — does anything diverge from the codebase's idioms
- **Doc coverage** — public API has rationale or just signature?
3. **Score each finding 1-5** on reader pain.
4. **Rank.** Top 10 friction sources by score × use-frequency (how often readers encounter this).
5. **Recommend** smallest-change-highest-impact refactors. Not "rewrite everything" — "rename X, extract Y, add a comment to Z".
## Output shape
```
Reader persona: <e.g. "new hire, 2-hour orientation">
Files reviewed: N
Top friction sources:
#1 [pain 5] <file:line>
Friction: <what hurts>
Why: <reader perspective>
Fix: <smallest change>
Cost: <minutes>
Use freq: high|med|low
#2 ...
Friction map:
Naming ███░░░░ 3
Length ██████ 5
Indent ██░░░░ 2
Implicit █████░ 4
Surprise ██░░░░ 2
Doc ████░░ 3
```
## Rules
- **Reader-first.** Don't flag things readers don't actually hit.
- **Smallest change.** A rename beats a refactor. A comment beats a rename if naming would break ABI.
- **Quantify pain.** Score 1-5 with rationale. Vague flagging = noise.
- **Use-frequency matters.** Painful internals nobody reads are lower priority than mildly painful hot paths.
## Anti-patterns
- Style-policing (handled by linter)
- "Could be more elegant" — that's `/siftcoder:zen`, not empathy
- Recommending wholesale rewrites
- Ignoring use-frequency — fixing cold code is low ROI
## When NOT to use
- Code review of a specific PR — `/review`
- Performance — `/optimize`
- Pre-shipping cleanup — `/zen`
- Active feature work — empathy interrupts flow
## Subagent dispatch
- `Explore` for breadth
- `general-purpose` for the ranking and recommendations
- `reviewer` agent (if installed) for the persona-driven pass
## Value over native CC
CC will critique code. CC won't naturally adopt a specific reader persona, score by reader pain, or weight by use-frequency. The persona-driven framing IS the value.
Related in Code Review
gstack
IncludedFast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)
startup-due-diligence
IncludedLegal due diligence review for seed-stage and Series A startups (US, Delaware C-Corp focus). Supports both investor and founder perspectives. Capabilities include: (1) Interactive document review and issue spotting; (2) Document request list generation; (3) Cap table and SAFE/convertible note analysis; (4) Red flag identification with severity ratings; (5) Diligence report generation. TRIGGERS: due diligence, DD, startup investment, cap table review, Series A, seed round, investor diligence, legal review startup, SAFE analysis, convertible note, 409A, founder vesting.
interview-master
IncludedThis skill should be used when the user asks to "generate interview questions", "prepare for interview", "optimize resume", "conduct mock interview", "analyze git commits for resume", "generate resume from code", "review my resume", or mentions interview preparation, career assistance, or extracting project experience from git history. Provides comprehensive interview and career development guidance for both job seekers and interviewers.
fix-issue
IncludedFixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to avoid recurrence. Use when debugging errors, resolving regressions, fixing bugs, or triaging issues.
sf-apex
IncludedGenerates and reviews Salesforce Apex code with 150-point scoring. TRIGGER when: user writes, reviews, or fixes Apex classes, triggers, test classes, batch/queueable/schedulable jobs, or touches .cls/.trigger files. DO NOT TRIGGER when: LWC JavaScript (use sf-lwc), Flow XML (use sf-flow), SOQL-only queries (use sf-soql), or non-Salesforce code.
swift-development
IncludedComprehensive Swift development for building, testing, and deploying iOS/macOS applications. Use when Claude needs to: (1) Build Swift packages or Xcode projects from command line, (2) Run tests with XCTest or Swift Testing framework, (3) Manage iOS simulators with simctl, (4) Handle code signing, provisioning profiles, and app distribution, (5) Format or lint Swift code with SwiftFormat/SwiftLint, (6) Work with Swift Package Manager (SPM), (7) Implement Swift 6 concurrency patterns (async/await, actors, Sendable), (8) Create SwiftUI views with MVVM architecture, (9) Set up Core Data or SwiftData persistence, or any other Swift/iOS/macOS development tasks.