Claude Skills by marcmarti9

Red-teams an early idea, product, feature, business model, strategy, or go-to-market direction before commitment. Use whenever exploring or refining a non-trivial idea and the useful question is not only "could this work?" but "how would customers, competitors, operations, economics, adoption, support, or reality make this fail?" Pair with idea-refine before converging. Do not use as a substitute for code/artifact review after implementation; use doubt-driven-development or code-review-and-qu...

Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.

Adversarial pre-deploy security gate for web apps and APIs, especially AI/vibe-coded builds. Use after substantial implementation, before production release, or when asked whether an app is safe to ship. Composes security-and-hardening with evidence-driven attack-path checks, safe remediation, and mandatory retesting. Not for pure security theory or a single isolated hardening question.

JIT orchestration for material work. Help the primary AI choose useful topology, bounded workers, independent alternatives/review, and deterministic Loop/Graph execution without imposing a fixed hierarchy.

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.

Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.

Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-ignore or eslint-disable suppressions, skipped or deleted tests, assertions stripped out, unimplemented stubs, thresholds edited down. Use when no quality bar is written down, when the user says "se...

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

Research and select the best current creative-development tools, libraries, primitives, and implementation techniques for a chosen experience instead of defaulting to familiar stacks.

Invent distinctive interactive web concepts before implementation. Use for premium redesigns, experiential sites, campaign pages, portfolios, product launches, editorial stories, or any request to make a site memorable without forcing a specific interaction pattern.

Guides systematic root-cause debugging. Use when tests fail, builds break, something that worked yesterday broke, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need to figure out what broke and why — a systematic approach to finding and fixing the root cause rather than guessing.

Add a restrained set of memorable, brand-appropriate interaction details, easter eggs, micro-moments, and playful affordances without sacrificing usability or turning the product into a gimmick.

Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code.

Research current visual and interaction references before public greenfield or total-redesign art direction; extract design DNA, synthesize original directions, and keep provenance traceable.

Read, create, maintain and verify a project's durable DESIGN.md visual-identity contract when persistent design tokens and rationale would materially improve multi-session frontend/design consistency.

Research current design and creative-development trends, separating emerging patterns from mature conventions, saturated aesthetics, and speculative hype.

Records decisions and documentation. Use when you need to document an architecture decision (ADR) or the reasoning behind a design choice, when changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production auth, security-sensitive logic, a high-stakes migration, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.

This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

Prepare board and investor decisions, narratives, pre-reads and governance communications around material metrics, variance, risks and explicit asks without spin or fabricated confidence.

Triage company signals, maintain a decision/action queue, coordinate priorities and surface blockers with minimal noise while respecting authority and ownership.

Turn company financial data, unit economics, cash constraints and investment choices into explicit scenarios and executive decisions without pretending heuristics are universal rules.

Frame business legal and compliance decisions around issue, exposure, standard negotiating positions, jurisdiction and escalation without pretending AI advice is binding counsel.

Make executive go-to-market, positioning, channel, funnel, brand and retention decisions by connecting customer evidence and channel economics to revenue.

Diagnose operational constraints, process/vendor risk, execution capacity and automation opportunities, then turn them into measurable operating decisions.

Orchestrate company-level decisions through a single accountable executive voice, selecting only the specialist executive skills and evidence that materially improve the current decision.

Make executive people decisions about role design, hiring, compensation, performance, retention and organization structure while accounting for human and jurisdiction-specific risk.

Make executive product decisions about customer problems, roadmap, product-market fit, sequencing, make/buy and investment using evidence rather than feature voting.

Make company-level strategy decisions about positioning, markets, moats, priorities, partnerships and build/buy choices with explicit assumptions, evidence and trade-offs.

Use the official Figma MCP as design context and design-system authority for design-to-code, code-to-Figma, component mapping, variables, assets, and collaborative visual iteration.

Builds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces and pages, creating components, implementing layouts, meeting WCAG accessibility requirements, managing state, or when the output needs to look and feel production-quality rather than AI-generated.

Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, splitting uncommitted work in a messy working tree into clean atomic commits, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump, tagging, or writing a changelog.

Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.

Rewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, staged openers, forced triads, dashes everywhere, inflated claims, sales language, stock AI words, bold labels, or filler. Based on Wikipedia's "Signs of AI writing."

Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing,...

Delivers changes incrementally in thin, verifiable slices. Use when implementing any feature or change that touches more than one file, or when picking up the next task from a plan. Use when rolling a change out behind a feature flag, when you're about to write a large amount of code at once, or when a task feels too big to land in one step.

Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invokes ("interview me", "grill me", "are we sure?", "stress-test my thinking"), or when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists.

Assess an explicitly available local or remote model endpoint for a bounded role. Guidance only; no automatic model-routing implementation or capability parity is implied.

Keep substantial multi-session Agentit work resumable using private local state, compact checkpoints, and a fresh task decision when a new execution session resumes.

Growth engineering, conversion rate optimization (CRO), technical and local SEO, AI-search visibility, landing page copywriting, analytics, campaign/launch strategy, email, customer research, positioning, and content systems. Use for marketing, growth, launch strategy, SEO, local SEO, GEO/AEO, or funnel optimization.

Select the smallest useful MCP/tool set for the current Agentit task, based on repository facts, explicit capability needs, least privilege, and current availability.

Instruments code so production behavior is visible and diagnosable. Use when adding logging, metrics, tracing, or alerting. Use when shipping any feature that runs in production and you need evidence it works. Use when production issues are reported but you can't tell what happened from the available data.

Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.

Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.

Decide whether a task materially benefits from external references, then use the smallest domain-appropriate curated/live set. Distinguish authority, actually read material sources, distill useful knowledge into existing skills, and record durable provenance without making the user re-paste references.

Design and implement cinematic scroll-driven web narratives: pinned scenes, scrubbed timelines, product decomposition, image sequences, section transitions, spatial storytelling, and progressive 3D reveals. Use when scroll itself drives the story.

Hardens code against vulnerabilities. Use when auditing an input handler for vulnerabilities, when handling user input, authentication, data storage, or external integrations, or when checking a login flow is safe against the OWASP Top Ten. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services. Use when auditing dependencies for known vulnerabilities, triaging package-manager audit findings, or assessing supply-chain risk in a...