better_claude_skillz

Scan project, then generate or reconcile .primeignore patterns for smarter /prime loading

Run WCAG accessibility audits on frontend projects. Checks HTML semantics, ARIA usage, color contrast, and keyboard navigation patterns.

Generate OpenAPI specs from code, validate API contracts, and check for breaking changes between versions.

Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.

Incrementally fix TypeScript and build errors one at a time with verification. Invokes the build-error-resolver agent.

Create or verify a checkpoint in your workflow

ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.

Comprehensive security and quality review of uncommitted changes

Technical code review for quality and bugs that runs pre-commit

Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.

Evaluate the full Claude Code configuration stack for duplication, security, staleness, consistency, coverage gaps, optimization, and innovation opportunities.

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.

Create a Product Requirements Document from conversation

Scan one or more projects for dependency vulnerabilities, outdated packages, and cross-project version conflicts.

Generate and run end-to-end tests with Playwright. Creates test journeys, runs tests, captures screenshots/videos/traces, and uploads artifacts.

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles

Manage eval-driven development workflow with define, check, report, and list operations

Cluster related instincts into skills, commands, or agents

Execute an implementation plan

Document what was implemented vs planned

Identify cross-project code duplication and generate candidates for a shared utility package.

Web scraping, search, and crawling via the Firecrawl CLI. Use when asked to scrape a URL, fetch a page, read an article, research a topic online, look something up, search the web, find information about a website, check a competitor, pull documentation, extract data from a site, get the content of a URL, web search, or fetch any webpage. Handles JS-heavy pages, bot-protected sites (Cloudflare), PDFs, and multi-page crawls. Trigger words: scrape, fetch, search the web, read this URL, get this page, crawl, research online, competitor research, pricing page, docs page, download a site, find articles about, web research, browse, extract from this URL.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics. Has a library of 9 curated design examples (including one multi-page SaaS site) that can be referenced, blended, or adapted to any brand or context. Trigger words include design, build, style, beautify, UI, frontend, landing page, dashboard, website, component, mockup, prototype.

Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.

Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.

Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices.

Implement bug fix based on RCA

Initialize new project with standard structure

Export instincts for sharing with teammates or other projects

Import instincts from teammates, Skill Creator, or other sources

Show all learned instincts with their confidence levels

Pattern for progressively refining context retrieval to solve the subagent context problem

Enforce minimal-code discipline — write the least code that fully works. Applies a YAGNI/stdlib-first decision ladder before generating code. Use when writing or revising code, reviewing a diff for over-engineering, or auditing a repo for needless complexity. Trigger words include lazy, minimize, simplify, YAGNI, over-engineered, "least code", "do we need this".

Analyze the current session and extract reusable patterns worth saving as skills

Sequential agent workflow for complex tasks

Profile Python and Node.js application performance. Identify slow endpoints, memory leaks, and CPU bottlenecks.

Restate requirements, assess risks, and create step-by-step implementation plan. WAIT for user CONFIRM before touching any code.

Create comprehensive feature plan with deep codebase analysis and research

PostgreSQL database patterns for query optimization, schema design, indexing, and security.

Load project context. Use at the start of every session. Supports quick (default) and full modes.