claude-config

Scaffold repo-local Ralph autonomous harness under scripts/ralph/. Use when user runs /flow-next:ralph-init.

Collect, deduplicate, enrich, triage, and convert code comments (TODO/FIXME/HACK/NOTE/OPTIMIZE/SECURITY/DEBT) into structured, dependency-ordered task lists ready for autonomous agents. Use when processing technical debt, converting code notes into tracked work, preparing task backlogs, or generating executable task graphs. Triggers: TODO triage, fixme list, tech debt scan, task extraction, comment analysis.

Converts any MCP server into a standalone skill package with zero runtime dependencies (no MCP process required). Trigger when user says: "convert this MCP to a skill", "I don't want to use MCP anymore", "wrap MCP X as a skill", "MCP is too heavy", "turn MCP capabilities into a skill". Does: connects to MCP server to extract tool schemas, analyzes source code to infer equivalent Bash commands, generates a ready-to-use skill package and registers it with the agent, optionally asks user to remove the original MCP. Does NOT: execute MCP tool calls to complete tasks (that's using MCP, not converting it); wrap existing Bash scripts as skills (use skill-creator); execute MCP business logic. Optional dependency: skill-creator (improves generated SKILL.md quality).

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Creates high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services. Use when building MCP servers to integrate APIs, designing tool schemas, or implementing Python (FastMCP) or TypeScript (MCP SDK) servers. Triggers include "MCP server", "tool schema", "model context protocol", or "FastMCP".

Builds and refactors production-ready Python CLI tools and packages with modern pyproject layouts, uv workflows, and robust testing.

Packages repositories into AI-friendly bundles with Repomix and can reconstruct files from existing Repomix outputs. Use when packaging codebases for LLM analysis, creating repository snapshots, reversing bundles, or preparing security audits. Triggers include "repomix", "package codebase", "repomix-unmix", "extract-bundle", "AI-friendly", or "LLM context".

Analyzes bash scripts for performance bottlenecks, coding standards, and modern tool replacements. Use when optimizing shell scripts, consolidating scripts, or preparing for production. Triggers include "optimize bash", "shellcheck", "script performance", or "consolidate scripts".

Claude Code hooks configuration and development. Covers hook lifecycle events, configuration patterns, input/output schemas, and common automation use cases. Use when user mentions hooks, automation, PreToolUse, PostToolUse, SessionStart, SubagentStart, or needs to enforce consistent behavior in Claude Code workflows.

Use the `json_repair` Python library to fix invalid/malformed JSON, especially output from LLMs. Trigger this skill whenever you encounter broken JSON strings, need to parse unreliable JSON from model outputs, want a drop-in replacement for json.loads() that auto-repairs, or are building pipelines that consume LLM-generated JSON. Also use when the user mentions "json repair", "fix json", "malformed json", "invalid json from LLM", or needs to robustly parse JSON that may have missing quotes, trailing commas, unescaped characters, or other common LLM output defects.

Compress images to reduce file size while preserving quality. Use when images are slowing down builds, uploads, or page loads.

Use Cloudflare Browser Rendering REST APIs to extract rendered webpage content as Markdown or crawl whole sites asynchronously. Use when normal web_fetch is insufficient because pages are JavaScript-heavy, require render-time extraction, or you need multi-page site crawling for docs, research, monitoring, or RAG preparation. Prefer this skill for: (1) converting a rendered page to Markdown with /markdown, (2) crawling a documentation site or knowledge base with /crawl, (3) controlling render/load behavior via gotoOptions, cookies, auth, userAgent, or request filtering. Do not use it for interactive login/button-click workflows; use browser for those.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends the agent's capabilities with specialized knowledge, workflows, or tool integrations.

Compress and format structured data with TOON to cut prompt size without losing shape. Use for JSON, tables, logs, API responses, or repeated records when token budget matters.

Persist and retrieve repository-specific knowledge using AGENTS.md files. Use when you want to save important information about a codebase (build commands, code style, workflows) for future sessions.

Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 230 rules.

Performs structural code search and safe rewrite planning with ast-grep. Use when pattern matching must follow AST structure instead of plain text.

Connect to Cloudflare API for DNS management, tunnels, and zone administration. Use when user needs to manage domains, DNS records, or create tunnels.

Manage Cloudflare domains, DNS records, SSL settings, zone configuration, firewall rules, tunnels, and analytics via the Cloudflare API. Use when the user asks to set up a domain, add/edit/delete DNS records, configure SSL, check zone settings, manage Cloudflare Tunnels, view analytics, or any Cloudflare account management task.

Analyze codebases for anti-patterns, code smells, and quality issues using ast-grep structural pattern matching. Use when reviewing code quality, identifying technical debt, or performing comprehensive code analysis across JavaScript, TypeScript, Python, Vue, React, or other supported languages.

Execute Python code locally with marketplace API access for 90%+ token savings on bulk operations. Activates when user requests bulk operations (10+ files), complex multi-step workflows, iterative processing, or mentions efficiency/performance.

Generate an interactive collapsible tree visualization of your codebase. Use when exploring a new repo, understanding project structure, or identifying large files.

Data format specialist covering TOON encoding, JSON/YAML optimization, serialization patterns, and data validation for modern applications. Use when optimizing data for LLM transmission, implementing high-performance serialization, validating data schemas, or converting between data formats.

Run Docker commands within a container environment, including starting the Docker daemon and managing containers. Use when building, running, or managing Docker containers and images.

Google Calendar CLI for listing calendars, viewing/creating/updating events, and checking availability.

Google Drive CLI for listing, searching, uploading, downloading, and sharing files and folders.

Comprehensive GitHub operations using the gh CLI tool. Supports pull requests, issues, workflows/actions, releases, repositories, gists, and local git operations with deterministic porcelain output. Use when working with GitHub PRs, issues, actions, releases, repos, or agentic git workflows. Triggers: gh, GitHub, pull request, PR, issue, workflow, actions, release, gist, git status, git diff, git log.

Gmail CLI for searching emails, reading threads, sending messages, managing drafts, and handling labels/attachments.

JavaScript specialist for Node.js, Bun, and Deno with modern async patterns, API development, testing, and lint/format workflows. Use when building or refactoring JavaScript applications.

Distill code review feedback from GitHub PRs into reusable skills and guidelines. This skill should be used when users ask to "learn from code reviews", "distill PR feedback", "improve coding standards", "extract learnings from reviews", or want to generate skills/guidelines from historical review comments.

Cross-language linter autofix commands and common fix patterns for biome, ruff, clippy, shellcheck, and more.

Debug Linux kernel crashes using the crash utility. Use when users mention kernel crash, kernel panic, vmcore analysis, kernel dump debugging, crash utility, kernel oops debugging, analyzing kernel crash dump files, using crash commands, or locating root causes of kernel issues.

Operate Linux systems avoiding permission traps, silent failures, and common admin mistakes.

Optimize LLM-facing content: documentation c7score, llms.txt generation, Claude Code skill optimization, XML tag structuring for prompts, CLAUDE.md auditing, and LLM parameter tuning. Use when optimizing docs for AI assistants, creating llms.txt, improving c7score, optimizing skills for token efficiency, applying 500-line rule, implementing progressive disclosure, designing XML tag structures for prompts, auditing CLAUDE.md files, tuning LLM temperature and token settings, or compressing markdown for context efficiency.

Use when navigating code, understanding unfamiliar functions, finding definitions or references, tracing call hierarchies, preparing for refactoring, or analyzing code impact. Enforces LSP-first semantic code intelligence with mandatory pre-edit checks, impact analysis before refactoring, and post-edit diagnostics. Provides IDE-like precision for code operations in large codebases. Covers navigation (goToDefinition, findReferences), understanding (hover, documentSymbol), and call analysis (incomingCalls, outgoingCalls).

Run autofix maintenance commands to keep code clean and consistent.

Core Claude Code extension-authoring playbook for skills, agents, commands, plugins, hooks, and settings. Use when creating or reviewing Claude Code extensions and automation workflows.

Interactive onboarding workflow that interviews users to understand their coding goals and generates PR-ready implementation plans. Use when starting a new development task to ensure clear requirements and structured execution.

High-accuracy web search and research via Parallel.ai API. Optimized for AI agents with rich excerpts and citations. Supports agentic mode for token-efficient multi-step reasoning.

Raspberry Pi system administration. Monitor resources, manage services, perform updates and maintenance.