開發

Debugging techniques for Python, JavaScript, and distributed systems. Activate for troubleshooting, error analysis, log investigation, and performance debugging. Includes extended thinking integration for complex debugging scenarios.

Classifies information into PACER categories (Procedural, Analogous, Conceptual, Evidence, Reference) and recommends appropriate digestion protocols. Use when learning new material, studying, reading educational content, processing information for retention, or when user asks about how to study or remember something.

This skill should be used for independent code review with fresh perspective. Use when the orchestrator invokes phase 4 (review) or when performing final quality check before completion.

Review code for style, performance, and maintainability. Use before merging changes.

Automates GitHub workflows including batch issue creation from JSON/CSV, PR creation with issue linking, pre-PR testing, and WordPress-specific validation (PHP linting, WPCS). Use when creating multiple issues, automating PR workflows, or validating WordPress code before commits.

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.

Use when reviewing GitHub pull requests with gh CLI - creates pending reviews with code suggestions, batches comments, and chooses appropriate event types (COMMENT/APPROVE/REQUEST_CHANGES)

Analyze routes and recommend whether to use Server Actions or API routes based on use case patterns including authentication, revalidation, external API calls, and client requirements. Use this skill when deciding between Server Actions and API routes, optimizing Next.js data fetching, refactoring routes, analyzing route architecture, or choosing the right data mutation pattern. Trigger terms include Server Actions, API routes, route handler, data mutation, revalidation, authentication flow, external API, client-side fetch, route optimization, Next.js patterns.

Create and manage Jupyter notebooks for testing Adobe Edge Delivery Services (EDS) blocks interactively in the browser using the ipynb-viewer block. Interactive JavaScript execution, overlay previews with backdrop, direct ES6 imports. Use when creating notebooks, testing blocks with ipynb files in browser, generating overlay previews, or creating executable documentation.

Troubleshoot dev server reachability and HMR for WebF apps on real devices (Vite/Webpack): LAN IP vs localhost, 0.0.0.0/--host binding, firewall/ports, and websocket/HMR (ws://) issues. Use when the user mentions HMR, websocket, ws://, --host, 0.0.0.0, LAN IP, firewall, or a device that can load HTML but not assets/HMR.

This skill should be used when the user asks to "provision a VPS", "create a Hetzner server", "spin up a cloud server", "launch a Hetzner instance", "set up a cloud server for Claude Code", "deploy Claude Code to a server", "create a VPS for Claude", or mentions Hetzner Cloud provisioning. Automates VPS creation with Claude Code pre-installed.

Comprehensive research, analysis, and content extraction system. Multi-source parallel research using available researcher agents. Deep content analysis with extended thinking. Intelligent retrieval for difficult sites. Fabric pattern selection for 242+ specialized prompts. USE WHEN user says 'do research', 'extract wisdom', 'analyze content', 'find information about', or requests web/content research.

Asks Claude Code CLI for coding assistance. Use for getting a second opinion, code generation, debugging, or delegating coding tasks.

Generate hardware setup and wiring instructions for IC10 code. Use when user wants to know how to physically connect devices to use their IC10 scripts.

Guide for creating hooks that trigger actions in response to Claude Code events

Modern type-safe Rust CLI patterns with Clap derive macros, Parser trait, Subcommand enums, validation, and value parsers. Use when building CLI applications, creating Clap commands, implementing type-safe Rust CLIs, or when user mentions Clap, CLI patterns, Rust command-line, derive macros, Parser trait, Subcommands, or command-line interfaces.

知的障害・精神障害のある方の支援情報を一元管理し、視覚的なエコマップとして表示するスキル。計画相談支援の担当者がケース会議や利用計画作成時に使用。北九州市および隣接市町村対応。

Review and triage Trufflehog secret detection scan results to identify real credential exposures. Use when analyzing trufflehog output, triaging secret findings, reviewing credential leaks, or when the user has trufflehog results to review. Can also run scans for an organization. Filters out test/demo secrets and prioritizes verified findings with source code context analysis.

Instrument safety checks, content filters, and guardrails for agent outputs

NatSpec documentation standards and best practices for Solidity contracts. Use when documenting code or reviewing documentation quality.