All Skills

Runs evidence-first research workflows by combining search, synthesis, and recommendation skills for current facts, comparisons, or enrichment.

Write reliable, maintainable Rust tests using unit tests, integration tests, async testing, property-based testing, mocking, and coverage following TDD methodology.

Prevents destructive operations on production systems and restricts file edits to a specific directory when running agents autonomously.

Uses two independent review agents to verify output quality, requiring both to pass before shipping.

Research existing tools, libraries, and patterns before writing custom code by invoking a researcher agent.

Automatically measures whether coding agents follow skills, rules, or agent definitions by generating scenarios at multiple prompt strictness levels, running agents, classifying tool calls, and reporting compliance rates with full timelines.

Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests for new features, bug fixes, or refactoring.

Browse available agent personas and compose ad-hoc teams of up to 5 agents to work in parallel on a task, then synthesize their results.

Executes commands, inspects git state, debugs CI or builds, makes narrow fixes, and reports exactly what changed and what was verified.

Provides Vue.js 3 Composition API patterns, component architecture, reactivity best practices, Pinia state management, Vue Router navigation, and Nuxt SSR patterns for Vue, Nuxt, Vite, or Pinia projects.

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA standards, with guidance for Web, iOS, and Android platforms.

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

Guides users through selecting and installing skills and rules from the Everything Claude Code project, verifying paths and optionally optimizing installed files.

Analyze Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log. Provides summaries, breakdowns by model, session, or date, and CSV export.

Conduct multi-source deep research using firecrawl and exa MCPs, synthesize findings, and deliver cited reports with source attribution.

Generate or audit design systems, check visual consistency, and review PRs that touch styling.

Configure Celery with Django for background task processing, including task design, scheduling, retries, canvas workflows, monitoring, and testing.

Provides practical accessibility patterns for React and Next.js, covering form labeling, semantic HTML, ARIA attributes, keyboard navigation, focus management, and screen reader support.

Create and manage Hookify rules that define patterns to watch for and messages to display when those patterns match.

Manage a multi-layered knowledge system for ingesting, organizing, syncing, and retrieving knowledge across local files, MCP memory, vector stores, and Git repos.

Operate and extend NanoClaw v2, a zero-dependency session-aware REPL built on Claude's -p mode.

Defines a gated Research-Plan-TDD-Review-Commit pipeline for orchestrating feature development, defect fixes, and refactoring tasks through composable phases and human approval gates.

Write modern Perl 5.36+ code using idioms, best practices, and conventions for robust, maintainable applications.

Provides comprehensive security patterns for Perl applications covering taint mode, input validation, safe file operations, SQL injection prevention, and web security.

Write behavior-focused React component tests with React Testing Library, Vitest/Jest, MSW for network mocking, and accessibility assertions using axe, while deciding when to use component tests versus Playwright/Cypress end-to-end tests.

Scan installed skills to extract cross-cutting principles and distill them into rules files.

Enforce idiomatic Rust patterns for ownership, error handling, enums, traits, concurrency, and best practices to build safe, performant applications.

Audit Claude Code configuration files for security vulnerabilities, misconfigurations, and injection risks using AgentShield.

Edit real video footage using a pipeline of FFmpeg, Remotion, ElevenLabs, fal.ai, and traditional editors for cutting, structuring, and augmenting raw captures.

Configure and optimize Vite build tool projects with patterns for config, plugins, HMR, environment variables, proxy setup, SSR, library mode, dependency pre-bundling, and production builds.

Provides real-time structural code health scores via CodeScene MCP to review code quality before edits, verify score deltas after changes, and gate commits and PRs.

Create platform-native content for X, LinkedIn, TikTok, YouTube, and newsletters by repurposing source material while preserving the author's authentic voice.

Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.

Provides C# and .NET testing patterns using xUnit, FluentAssertions, mocking, integration tests, and test organization best practices.

Orchestrate parallel AI agent sessions using dmux, a tmux pane manager for agent harnesses like Claude Code and Codex.

Provides patterns for robust error handling across TypeScript, Python, and Go, including typed errors, error boundaries, retries, circuit breakers, and user-facing error messages.