Skill Creator
phrazzld
25 published skills · 50 GitHub stars across the catalog. View on GitHub ↗
ai-llm-development
MANDATORY invocation for ALL LLM-related work. Invoke immediately when:- ANY mention of model names, IDs, or versions- ANY configuration of AI providers or APIs- ANY defaults/constants for LLM settings- ANY prompt engineering or modification- ANY discussion of model capabilities or features- ANY changes to AI-related dependencies- Reading/writing .env files with AI config- Modifying aiProviders.ts, prompts.ts, or similar- Reviewing AI-related pull requests- Debugging LLM integration issuesCRITICAL: Training data lags reality by months. ALWAYS research first.Use WebSearch, Exa MCP, or Gemini CLI before making ANY LLM decisions.
changelog-automation
Apply changelog automation and semantic versioning patterns using Changesets or semantic-release: conventional commits, automated version bumping, release notes generation. Use when setting up release workflows, discussing versioning, or implementing changelog automation.
cli-toolchain
Apply modern CLI development toolchain patterns: Commander.js (default), oclif, Ink for Node.js command-line tools. Use when building CLI applications, choosing CLI frameworks, or discussing terminal UX.
code-quality-standards
Apply code quality standards for testing, coverage, CI/CD, and automation: Vitest, coverage philosophy, git hooks, GitHub Actions, quality gates. Use when setting up testing, configuring CI, discussing quality practices, or reviewing automation.
code-review-checklist
Apply comprehensive code review checklist covering purpose, design, quality, correctness, security, performance, testing, and documentation. Use when reviewing pull requests, conducting code reviews, or self-reviewing changes before committing.
commit-message-style
Apply commit message style: conventional commits format (type: subject), imperative mood, <50 char subject, explain why in body. Use when writing commits, reviewing commit messages, or discussing git history.
convex-development
Apply Convex database best practices for cost optimization, performance, security, and architecture.Use when: building Convex backends, optimizing queries, handling embeddings/vector search,reviewing Convex code, designing schemas, planning migrations, or discussing Convex architecture.Keywords: Convex, real-time database, queries, mutations, actions, indexes, pagination,vector search, embeddings, schema, migrations, ctx.auth, convex-helpers, bandwidth.
design-tokens
Apply design token patterns using Tailwind CSS 4 @theme directive: CSS variables, semantic naming, color systems, typography scales, spacing, dark mode. Use when designing UI systems, reviewing design consistency, or establishing brand guidelines. Integrates with frontend-design skill for aesthetic execution.
documentation-standards
Apply documentation standards: comment why not what, minimal comments (prefer clear code), maintain README with quick start, update docs with breaking changes. Use when writing comments, creating docs, reviewing documentation, or discussing what to document.
extension-toolchain
Apply modern browser extension toolchain patterns: WXT (default), Plasmo, CRXJS for Chrome/Firefox/Safari extensions. Use when building browser extensions, choosing extension frameworks, or discussing manifest v3 patterns.
gemini-cli-integration
Comprehensive guide for integrating Gemini CLI as research assistant. Use when you need to delegate research to Gemini, understand its capabilities vs Claude's, or determine the right tool for a task.
langfuse-observability
Query Langfuse traces, prompts, and LLM metrics. Use when:- Analyzing LLM generation traces (errors, latency, tokens)- Reviewing prompt performance and versions- Debugging failed generations- Comparing model outputs across runsKeywords: langfuse, traces, observability, LLM metrics, prompt management, generations
llm-evaluation
LLM prompt testing, evaluation, and CI/CD quality gates using Promptfoo.Invoke when:- Setting up prompt evaluation or regression testing- Integrating LLM testing into CI/CD pipelines- Configuring security testing (red teaming, jailbreaks)- Comparing prompt or model performance- Building evaluation suites for RAG, factuality, or safetyKeywords: promptfoo, llm evaluation, prompt testing, red team, CI/CD, regression testing
llm-gateway-routing
LLM gateway and routing configuration using OpenRouter and LiteLLM.Invoke when:- Setting up multi-model access (OpenRouter, LiteLLM)- Configuring model fallbacks and reliability- Implementing cost-based or latency-based routing- A/B testing different models- Self-hosting an LLM proxyKeywords: openrouter, litellm, llm gateway, model routing, fallback, A/B testing
mobile-toolchain
Apply modern mobile development toolchain patterns: Expo (default), React Native, Tauri for iOS/Android apps. Use when building mobile applications, choosing cross-platform frameworks, or discussing mobile architecture.
naming-conventions
Apply universal naming principles: avoid Manager/Helper/Util, use intention-revealing names, domain language, verb+noun functions. Use when naming variables, functions, classes, reviewing names, or refactoring for clarity. Language-agnostic principles.
ousterhout-principles
Apply Ousterhout's software design principles: detect shallow modules, information leakage, and complexity red flags. Use when reviewing code, designing modules, refactoring, or discussing architecture.
quality-gates
Apply quality gate standards for git hooks, testing, CI/CD, and automation using Lefthook, Vitest, GitHub Actions, and quality enforcement. Use when setting up quality infrastructure, configuring hooks, discussing automation, or reviewing quality practices.
sentry-observability
Sentry error tracking and production observability. Invoke when:- New Next.js project without error tracking → Suggest setup- Deploying to Vercel → "Add observability before deploying"- Discussing error handling, try/catch → "Track these in production"- Production bug, users reporting errors → Triage with scripts- Setting up monitoring, configuring alerts, reviewing PII handlingScripts: detect_sentry.sh, init_sentry.sh, list_issues.sh, triage_score.shKeywords: Sentry, production errors, error tracking, triage, alerts,observability, Session Replay, PII redaction, source maps, monitoring
skill-builder
Create new Claude Code skills from procedural knowledge. Invoke PROACTIVELY when:- Discovering a reusable workflow pattern worth preserving- User asks to "capture this as a skill" or "make this reusable"- Recognizing institutional knowledge that should persist- After solving a problem in a novel way worth repeating- Noticing repeated patterns across sessionsAUTONOMOUS: Create skills proactively, then inform user what was created.
structured-logging
Apply structured logging best practices using Pino for Node.js applications: JSON output, log levels, context, redaction, correlation IDs, and centralization. Use when implementing logging, reviewing log statements, or discussing observability.
testing-philosophy
Apply testing philosophy: test behavior not implementation, minimize mocks, AAA structure, coverage for confidence not percentage. Use when writing tests, reviewing test quality, discussing TDD, or evaluating test strategies.
toolchain-preferences
Apply preferred toolchain and technology stack defaults: pnpm, Next.js, TypeScript, Convex, Vercel, Tailwind, shadcn/ui, Zustand, TanStack, Vitest. Use when setting up new projects, choosing dependencies, discussing stack decisions, or evaluating alternatives.
gemini-imagegen
Generate and edit images using the Gemini API (Nano Banana). Use this skill when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.