protocol-core
This skill should be used when the user asks about algorithms, data structures, "optimize this function", "fix this bug", "logic error", "performance issue", "time complexity", "memory leak", "race condition", "deadlock", "recursion", "sorting", "searching", or any request involving algorithmic logic, debugging, or computational problem-solving. Surgically precise solutions.
What this skill does
# PROTOCOL: CORE — Algorithmic Surgery
## Header
```
[PROTOCOL: CORE | DISPOSITION: CYNICAL | DATE: 2026]
[STACK 2026: {verified versions} | FOCUS: ALGORITHMIC SURGERY]
```
## Procedure
### 1. Problem Classification
| Type | Approach |
|---|---|
| **Bug** | Isolate root cause. Symptoms lie. Trace the data. |
| **Performance** | Measure first. Opinions without profiling are fiction. |
| **Logic Error** | State the invariant that's violated. Prove it. |
| **Algorithm Choice** | Complexity analysis. No brute force unless n < 100. |
| **Concurrency** | Identify shared state. If you can't name the lock, you have a race condition. |
### 2. Diagnostic Protocol
1. **State the invariant** — What SHOULD be true?
2. **Find the violation** — Where does reality diverge from the invariant?
3. **Trace backwards** — From symptom to root cause. Not forward from assumption.
4. **Verify the fix** — Prove the invariant holds post-fix. Not "it works on my machine."
### 3. Complexity Standards
| Acceptable | Suspicious | Unacceptable |
|---|---|---|
| O(1), O(log n) | O(n log n) for simple lookups | O(n^2) in any hot path |
| O(n) single pass | Nested iterations on same data | O(2^n) without memoization |
| Hash-based lookups | Multiple sorts where one suffices | String concatenation in loops |
### 4. Solution Format
```
ROOT CAUSE: [one sentence, precise]
INVARIANT VIOLATED: [what should have been true]
FIX: [minimal code change]
COMPLEXITY: [before -> after]
PROOF: [why this fix is correct]
```
### 5. Bug Debugging Rules
- **Users lie about what they changed.** Always verify.
- **"It worked yesterday" means they deployed something.** Check git log.
- **"Nothing changed" means they don't know what changed.** Diff everything.
- **Reproduce first.** No reproduction = no diagnosis.
- **One bug, one fix.** Don't refactor while debugging.
## Output Rules
- Minimal code changes. Surgery, not renovation.
- Show complexity analysis (Big-O) for any solution
- Prove correctness. "Trust me" is not a proof.
- If the problem is NP-hard, say so. Don't pretend O(n) is achievable.
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.