yangsi7

Intelligence-first code analysis for bugs, architecture, performance, and security. Use proactively when investigating code issues, tracing dependencies, or understanding system behavior. MUST query project-intel.mjs before reading files.

Identify and resolve ambiguities in specifications through structured questioning. Use when specification has [NEEDS CLARIFICATION] markers, when user mentions unclear or ambiguous requirements, before creating implementation plans, or when planning reveals specification gaps.

Create technical implementation plans from specifications with intelligence-backed architectural decisions. Use when specification exists and user mentions tech stack, architecture, implementation approach, or asks "how to implement" or "how to build" the feature.

Create detailed implementation plans from feature specs or bug reports with testable acceptance criteria. Use proactively when planning features, refactors, or fixes. Every task MUST have minimum 2 testable ACs and map to requirements.

Debug bugs and errors using intel-first approach with systematic root cause analysis. Use proactively when errors occur, tests fail, or unexpected behavior appears. MUST trace from symptom to root cause with CoD^Σ reasoning.

Create user-centric product definitions by analyzing the repository, inferring product goals and user needs, clarifying ambiguities through structured questioning, and generating comprehensive product.md documentation. Use when the user mentions "product definition", "define product", "product strategy", or needs to document user personas, pain points, and user journeys.

Derive technical development principles FROM user needs in product.md using evidence-based reasoning. Creates constitution.md with architecture decisions, tech stack choices, and development constraints - all traced back to specific user needs. Use when user mentions "technical principles", "constitution", "architecture decisions", or after creating product.md.

Generate user-story-organized task lists from implementation plans. Use when plan exists and user is ready for implementation, mentions "create tasks", "break down work", or asks "what tasks are needed" to implement the feature.

Intelligence-first code analysis for bugs, architecture, performance, and security. Use proactively when investigating code issues, tracing dependencies, or understanding system behavior. MUST query project-intel.mjs before reading files.

Identify and resolve ambiguities in specifications through structured questioning. Use when specification has [NEEDS CLARIFICATION] markers, when user mentions unclear or ambiguous requirements, before creating implementation plans, or when planning reveals specification gaps.

Create technical implementation plans from specifications with intelligence-backed architectural decisions. Use when specification exists and user mentions tech stack, architecture, implementation approach, or asks "how to implement" or "how to build" the feature.

Create detailed implementation plans from feature specs or bug reports with testable acceptance criteria. Use proactively when planning features, refactors, or fixes. Every task MUST have minimum 2 testable ACs and map to requirements.

Debug bugs and errors using intel-first approach with systematic root cause analysis. Use proactively when errors occur, tests fail, or unexpected behavior appears. MUST trace from symptom to root cause with CoD^Σ reasoning.

Create user-centric product definitions by analyzing the repository, inferring product goals and user needs, clarifying ambiguities through structured questioning, and generating comprehensive product.md documentation. Use when the user mentions "product definition", "define product", "product strategy", or needs to document user personas, pain points, and user journeys.

Derive technical development principles FROM user needs in product.md using evidence-based reasoning. Creates constitution.md with architecture decisions, tech stack choices, and development constraints - all traced back to specific user needs. Use when user mentions "technical principles", "constitution", "architecture decisions", or after creating product.md.

Generate user-story-organized task lists from implementation plans. Use when plan exists and user is ready for implementation, mentions "create tasks", "break down work", or asks "what tasks are needed" to implement the feature.

Best-practice prompt engineering using research-backed patterns. Handles: transforming rough prompts into production-ready, debugging prompt issues, creating new prompts from scratch. ALWAYS researches via subagents (keeps main context clean). Triggers on: "improve prompt", "fix prompt", "create prompt", "prompt not working", "write a prompt for", "optimize prompt", "/prompt".

Rigorous TDD workflow enforcement with Red-Green-Refactor cycle, deployment verification, and log monitoring. Use when fixing bugs, implementing features, or verifying deployments.

Complete user journey simulation for the Nikita AI girlfriend game. Simulates a real player (Simon) playing through all 5 chapters — registration, onboarding, text gameplay, boss encounters, decay, engagement states, vice personalization, voice calls, portal monitoring, terminal states, and adversarial scenarios. Assesses behavioral realism (does Nikita feel human?), game balance (are thresholds achievable?), and classifies all findings by severity and category. Use this skill whenever the user says "e2e", "end to end test", "full journey test", "test nikita", "regression test", "verify deployment", "test the bot", "test onboarding", "simulate a game", "run the test suite", "play through the game", "test the experience", "check if nikita feels real", "behavioral test", "game balance check", or after any deployment to production. This is THE authoritative E2E testing method — replaces the archived e2e-test-automation and e2e-journey skills. Always use /e2e, never the old commands.

Execute end-to-end tests for Nikita using Telegram MCP, Gmail MCP, Supabase MCP, Chrome DevTools MCP, and gcloud CLI. Use when verifying implementations, testing user journeys, validating integrations, performing regression testing, or after completing any feature implementation. MANDATORY after /implement completes.

Generate tailored CV and cover letter for job applications. Use when user says /apply, asks to write a cover letter, wants to apply to a job posting, needs help with job applications, or provides a job URL. Orchestrates job analysis, company research, and document generation following Swiss formal style rules.

Create technology-agnostic feature specifications using intelligence-first queries. Use when user describes what they want to build, mentions requirements, discusses user needs, or says "I want to create/build/implement" something. This skill enforces Article IV Specification-First Development.

Intelligence-first code analysis for bugs, architecture, performance, and security. Use proactively when investigating code issues, tracing dependencies, or understanding system behavior. MUST query project-intel.mjs before reading files.

Comprehensive Next.js project setup from scratch following industry best practices. Use when creating new Next.js projects, requiring template selection, design system ideation, specifications, wireframes, implementation with TDD, QA validation, and complete documentation. Handles both simple quick-start and complex multi-phase projects with sub-agent orchestration.

Rotate a leaked or expired API-key env variable across every .env and .mcp.json file in a project, safely and without ever printing the secret. Use when a key was committed/leaked/exposed (e.g. an agent pasted it into config files) and needs replacing everywhere at once, or on scheduled credential rotation.

Unified frontend development for production-grade Next.js applications with shadcn/ui + Tailwind CSS. Use when building web apps, creating UI components, implementing design systems, styling with Tailwind, setting up Next.js projects, running visual QA tests, or coordinating frontend implementation teams.

Systematic project health audit with categorized read-only checks. Auto-detects project type (Python/FastAPI, Next.js, Flutter, Node) and runs relevant checks across: state files, test coverage, dependency health, CI/CD status, documentation freshness, deployment safety, repository hygiene. Produces scored report (PASS/WARN/FAIL/SKIP) with remediation suggestions. Triggers: "health check", "project health", "how healthy is this project", "/health", "run health audit", "quick health check", "pre-deploy check". NOT for: security audits (use /security-audit), deep spec audits (use /deep-audit), code quality reviews (use /qa-review), toolkit integrity (use /system-integrity).

Team-powered SDD workflow using Claude Code Agent Teams. Creates 3-teammate teams for parallel validation (GATE 2), implementation (Phase 8), and existing specs audit. Triggers: /sdd-team, /sdd-team audit, /sdd-team validate, /sdd-team implement.

Use when [specific triggering conditions and symptoms] - [what the skill does and how it helps, written in third person]