Consiliency

Working with tree-sitter requires understanding AST navigation, query patterns, and visitor implementations. This skill provides ready-to-use patterns for parsing any programming language.

JSON wastes tokens in LLM prompts. TOON reduces token usage by 30-60% while keeping data human-readable. Transform tabular data into a compact format optimized for AI consumption.

Writing test files from scratch slows down test-driven development. This skill analyzes your source code and generates test scaffolds with TODO stubs in your preferred framework, so you can focus on implementing tests instead of setting them up.

Supabase projects often have security vulnerabilities from missing or incorrect RLS policies. This skill provides proven patterns for user ownership, team access, role-based security, and proper policy testing.

New contributors often guess coding conventions instead of following established project standards. This skill parses CONTRIBUTING.md, linter configs, and editor settings to return a complete standards summary for consistent contributions.

Stop manually configuring AI development skills for each project. Stack-analyzer automatically detects your technology stack and recommends the perfect skills for AI-assisted development.

Finding and tracking requirements across large codebases is time-consuming and error-prone. This skill automatically locates specification files, extracts requirement IDs like REQ-NOTIFY-001, and generates a traceable manifest with content hashes for downstream validation.

AI assistants cannot directly execute terminal commands. This skill enables running CLI tools like ffmpeg, curl, npm, and python in a separate terminal window for development workflows.

Managing multiple AI coding agents requires switching between different CLI tools. This skill launches Claude Code, Codex, Gemini, Cursor, OpenCode, or Copilot in a fresh terminal window. Developers can offload complex coding tasks to specialized agents while continuing their main workflow.

Launch AI coding agents and CLI commands in new terminal windows with cross-platform support for macOS, Windows, and WSL.

Security vulnerabilities like SQL injection and shell commands put applications at risk. This skill identifies OWASP patterns and provides specific remediation steps to fix issues before deployment.

Database schemas often drift from code definitions bugs and deployment causing failures. This skill detects misalignment between database schemas and ORM models across SQLAlchemy, Django, Prisma, and TypeORM frameworks.

Finding accurate information takes too long when checking multiple sources manually. This skill launches parallel research agents that search web, docs, and code simultaneously, then synthesize findings with confidence scores.

Testing code without proper patterns leads to flaky tests and maintenance nightmares. This skill provides battle-tested patterns for unit, integration, and E2E tests with proper fixtures and naming conventions.

Stop manually coordinating research tasks across multiple sources. This skill provides structured templates for AI agents to conduct systematic research with proper source management and synthesis.

Inconsistent terminology creates confusion in codebases. This skill establishes a shared vocabulary and entity relationships for your project domain. Teams can document entities, map relationships, and enforce naming conventions.

Documentation often falls out of sync with code changes. This skill automatically updates README, CHANGELOG, docs folder, and inline docstrings to reflect implemented changes.

Users need guidance on invoking external AI coding tools. This skill provides documented patterns and workflows for using Claude Code Task agents to call Codex, Gemini, and Cursor with proper authentication and read-only controls.

Managing multiple AI coding providers requires understanding their unique capabilities and command patterns. This skill provides documentation and workflows for delegating tasks to Claude, Codex, Gemini, and Cursor with proper authentication, read-only safeguards, and fallback strategies.

Managing multiple AI providers is complex with different capabilities and costs. This skill provides a decision framework and routing logic to automatically delegate tasks to the optimal provider based on requirements like context length, multimodal needs, sandboxed execution, or privacy constraints.

AI model names change frequently. This skill fetches current model lists from Anthropic, OpenAI, Gemini, and Ollama, then classifies them by performance tier for optimal model selection.

Complex tasks benefit from multiple perspectives. This skill enables you to fan out work to different AI providers simultaneously, then intelligently consolidate the results into a single high-quality output.

This skill identifies the technology stack of any project by scanning package manifests and configuration files. It helps developers quickly understand project dependencies, frameworks, and build tools without manual investigation.

This skill provides knowledge about 20+ documentation platforms and their fetch strategies. It helps you detect documentation frameworks, select the right fetching approach, and configure registry entries for new documentation sources.