Scripting

Detects and safely removes unused code (imports, functions, classes) across multiple languages. Use after refactoring, when removing features, or before production deployment. Includes safety checks and validation.

Use this skill when creating or refining Claude Code sub-agent definitions. Helps design specialized AI assistants with proper YAML frontmatter, system prompts, tool access, and example-driven descriptions. Automatically invoked when user requests "create an agent", "design a sub-agent", "make a specialist", or mentions agent development. Ensures agents follow Anthropic best practices with focused responsibilities, discovery-optimized descriptions, and proper tool restrictions.

Migrates codex configuration files from v2.0 push-based sync to v3.0 pull-based retrieval format with automatic backups

Python scripting with uv and PEP 723 inline dependencies. Use when creating standalone Python scripts with automatic dependency management.

This skill should be used when the user asks to "add fields to PocketBase collection", "modify PocketBase schema", "add new collection fields", "update PocketBase collection", "PocketBase JavaScript SDK API", "programmatically add PocketBase fields", or mentions modifying PocketBase collection schemas via API. Provides comprehensive guidance for adding fields to existing PocketBase collections using the JavaScript SDK API.

Use when creating or refining Claude Code skills to validate that skill descriptions trigger correctly - provides systematic testing methodology for skill activation patterns using test cases and automated evaluation

Comprehensive testing strategies including TDD, unit, integration, E2E, and property-based testing. Ensures code quality and prevents regressions. Use when writing tests, implementing features test-first, or improving coverage.

Debug DOPPLER WebGPU inference issues. Use when investigating model output problems, kernel bugs, hidden state explosions, or decode failures in the browser-based LLM inference engine.

Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.

Access AI-generated documentation and insights for GitHub repositories via DeepWiki. This skill should be used when exploring unfamiliar codebases, understanding repository architecture, finding implementation patterns, or asking questions about how a GitHub project works. Supports any public GitHub repository.

This skill should be used when reading documentation from multiple Claude Code projectsto extract knowledge, detect duplicates, unify best practices, and consolidate experience.AUTO-ACTIVATES for: knowledge sync, consolidate learning, unify knowledge, read multi-project,extract knowledge, detect duplicates, best practices, cross-project experience.PROVIDES: Multi-project documentation reading (AI_PRODUCT_DECISIONS.md, AI_BUGS_KNOWLEDGE.md, specs/),knowledge extraction (decisions, bugs, patterns, anti-patterns), duplicate detection(same problem in 3+ projects → unify), best practice validation (3+ confirmations → validated),experience consolidation (unified knowledge base), automatic propagation (to new projects).READS: AI_PRODUCT_DECISIONS.md, AI_BUGS_KNOWLEDGE.md, AI_PROGRESS_TRACKER.md, specs/,CLAUDE.md from multiple projects. Extracts architectural decisions, resolved bugs,discovered patterns, anti-patterns avoided.UNIFIES: Same bug found in 3 projects → single anti-pattern document.Same pa

コード品質チェック専門スキル。TypeScript/JavaScript ファイルの ESLint、型チェック、コーディング規約を検証する。

Expert guidance for Feishu (飞书) / Lark OpenAPI Python development. Build Feishu applications, robots, handle event subscriptions, card callbacks, and API integrations. Use when working with Feishu SDK, lark-oapi, building Feishu bots, or mentioning 飞书 development.

Master asynchronous JavaScript patterns including callbacks, promises, async/await, event loop mechanics, and real-world async patterns.

Engineering standards and code governance enforcement. Triggers during code review discussions, PR descriptions, commit preparation, and when discussing code quality. Ensures compliance with standards.md and runs audit checks. Trigger phrases include "code review", "review this", "commit", "standards", "compliance", "code quality", "best practices", "before I merge".

Automatically activated when user asks to "find patterns in...", "identify repeated code...", "analyze the architecture...", "what design patterns are used...", or needs to understand code organization, recurring structures, or architectural decisions

Advanced testing - Testcontainers, contract testing, mutation testing, property-based

Spawn a new terminal window to run CLI commands (ffmpeg, curl, python, etc.). Use for non-AI command execution.

This skill generates type-safe data validation schemas for APIs and forms.Supports Python (Pydantic), TypeScript (Zod), JavaScript (Joi, Yup), Go (validator).Creates request/response schemas, form validation, environment variable validation, and config validation.Activate when user says "validate data", "create schema", "input validation", "type-safe", or building APIs/forms.Output: Complete validation schemas with types, error messages, examples, and tests.

This skill should be used when handling domain cards and magical abilities in Daggerheart, including looking up domain card effects, understanding Recall costs, making Spellcast Rolls, selecting domain cards during character creation or advancement, or when players want to use domain-based abilities. Covers all 9 SRD domains (Arcana, Blade, Bone, Codex, Grace, Midnight, Sage, Splendor, Valor) and their associated cards.