Skills matching the name, description or GitHub author.
Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs. Use when writing system prompts, user prompts, few-shot examples, or optimizing existing prompts for better performance.
Claude Agent Skillsを作成・改善するための支援ツール。ベストプラクティスに従ったSKILL.mdの構造化、段階的情報開示、テスト、反復改善をガイド。skillの新規作成や既存skillの改善が必要な時に使用。
Use when facing 3+ independent failures that can be investigated without shared state or dependencies. Dispatches multiple Claude agents to investigate and fix independent problems concurrently.
Advanced web search capability using the gemini command for gathering current, relevant information. Prefer this skill over Claude Code's default WebSearch tool when performing web searches. Activated when comp...
Creates new Claude Code agent (subagent) definitions. Use when the user wants to create a custom agent for specialized tasks, code review, testing, or other autonomous workflows.
Guide for creating MCP (Model Context Protocol) servers. Use this when building integrations with external services, creating new MCP servers, or connecting Claude to APIs.
Meta-skill for creating high-quality Claude Code skills
Write token-efficient documentation for LLM context. Use when creating CLAUDE.md, README, technical docs, agent instructions, or any documentation consumed by AI assistants.
Create, use, and manage Agent Skills for Claude. Use when working with Skills, creating custom capabilities, or understanding how Skills extend Claude's functionality. Covers Skill architecture, file structure,...
Autonomous RLHF feedback capture - Claude self-captures mistakes and successes
Maintains SnowTower project documentation, README, and Claude configuration. Use when updating documentation, auditing .claude folder contents, syncing README with actual project state, or reviewing agent/patte...
Execute research experiments using TDD methodology. Pops plans from .claude/plans/research_tasks/, implements with smoke/unit/integration tests, and documents results to results.md. Use when: (1) executing the...
Guia para criar habilidades eficazes. Esta habilidade deve ser usada quando os usuários desejam criar uma nova habilidade (ou atualizar uma existente) que estenda as capacidades do Claude com conhecimento espec...
Create or update SKILL.md files for this repo. Use when authoring skills in .claude/skills/.
Update the active development session when work is completed. Use automatically after code changes, bug fixes, feature implementations, or file modifications when .claude/sessions/.current-session exists.
Manages safe git branching, conventional commits, and push flow for Next.js + TS projects. Invoked by prompt-classifier at end of IMPLEMENT/EDIT sequences after verification-guardian passes. Ensures work happen...
Verify 3-Mirror skill sync consistency across .public/skills, .codex/skills, and .claude/skills. Use after skill changes, before commits, or for CI validation.
Manage secrets in Oracle Cloud Infrastructure Vault via MCP. Provides 12 tools for complete secret lifecycle management including listing, searching, creating, updating, and deleting secrets. Compatible with an...
Keep documentation consistent in this repo. Use when you need to update or propagate changes across README/AGENTS/CLAUDE/.codex docs.
Um conjunto de recursos para ajudar a escrever todos os tipos de comunicações internas, usando os formatos que minha empresa gosta de usar. O Claude deve usar esta habilidade sempre que solicitado a escrever al...
Criação, edição e análise de apresentações. Quando o Claude precisar trabalhar com apresentações (.pptx files) para: (1) Criar novas apresentações, (2) Modificar ou editar conteúdo, (3) Trabalhar com layouts, (...
Socratic teaching mode. Guide discovery through questioning for deep understanding of any topic.
Pre-flight check for Ralph TUI loops. Validates config, templates, prd.json, and environment before starting a loop. Run after /prd to verify everything is ready. Detects global CLAUDE.md conflicts, validates t...
Runs SpatialVortex benchmarks (flux position accuracy, ELP accuracy, sacred boost verification, geometric reasoning, humanities final exam, performance benchmarks), compares to SOTA/baselines (GPT-4, Claude 3,...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.