Internal documentation for the Claude adapter generated from packages/skills.
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Internal documentation for the Claude adapter generated from packages/skills.
Expert cloud architect specializing in AWS/Azure/GCP multi-cloud infrastructure design, advanced IaC (Terraform/OpenTofu/CDK), FinOps cost optimization, and modern architectural patterns. Masters serverless, microservices, security, compliance, and disaster recovery. Use PROACTIVELY for cloud architecture, cost optimization, migration planning, or multi-cloud strategies.
Draft cold emails, follow-ups, and proposal templates. Creates pricing pages, case studies, and sales scripts. Use PROACTIVELY for sales outreach or lead nurturing.
Use for behavioral guidance, best practices, decision frameworks, and process skills that shape how Claude approaches work rather than teaching a specific tool or technique.
>
Federated variant lookup across 9 genomic databases — GWAS Catalog, Open Targets, PheWeb (UKB, FinnGen, BBJ), GTEx, eQTL Catalogue, and more.
Audit the repository's docs/ content against the current codebase,
Provide actionable treatment recommendations for cancer patients based on molecular profile. Interprets tumor mutations, identifies FDA-approved therapies, finds resistance mechanisms, matches clinical trials. Use when oncologist asks about treatment options for specific mutations (EGFR, KRAS, BRAF, etc.), therapy resistance, or clinical trial eligibility.
Manage a local GitHub knowledge base and provide GitHub search capabilities via gh CLI. Use when users ask about repos, PRs, issues, request to clone GitHub repositories, explore codebases, or need information about GitHub projects. Supports searching GitHub via gh CLI and managing local KB with GITHUB_KB.md catalog. Configure via GITHUB_TOKEN and GITHUB_KB_PATH environment variables. Optimize outputs for the next agent by narrowing results to the most relevant repo, file, PR, or issue and naming the next best inspection target.
This is an Elixir umbrella app with multiple sub-apps under `apps/`.
This file provides guidance to coding agents when working with code in this repository.
**Role:** specialized_form_handler
ODAI (ODAI AI Assistant) is a comprehensive AI assistant platform built on FastAPI that orchestrates multiple specialized agents to handle diverse user requests. The system uses OpenAI's Agent framewo
Purpose
use 'sequentialthinking' tool eagerly.
- Runtime and front ends live under `src/`; unit tests under `Tests/`; executables build to `build/bin/` via CMake.
Work inside `Cruise/`, the ROS 2 workspace. Packages live under `Cruise/src` (uv_ai, uv_hm, uv_vision, uv_control_py, uv_launch_pkg, utils, models). Tests sit beside each package in `test/`; runtime h
Sub-agents are specialized AI instances launched inside pipelines. Each agent has a focused role, its own tool set, and returns a structured report to the orchestrator.
- `src/`: library implementation (`client`, `session`, `transport`, `jsonrpc`, `types`).
This folder is home. Treat it that way.
- **xlabkm-ux** (xlabkm@gmail.com) — Owner
> **Context Depth:** 3 | **Parent:** simulator/src | **Mode:** Recursive Programming
Instructions for AI coding assistants using OpenSpec for spec-driven development.
{% set title = "Subagents" %}
Apify Actors Development Guide (JS)
Apify Actors Development Guide (TS)
This directory contains specialized agents for the SQL CLI project. Each agent is designed to handle specific types of tasks efficiently.
This guide explains how to create new agents in the Neovim Configuration agent system that handle full workflow execution and artifact creation.
List available agent types and spawn specialized agents for tasks.
**Version**: 4.0
**NEVER run these commands directly in the main session:**
Guidelines for AI agents working in this repository.
**Name:** FlightGuard MPP
**Integration skills** document how to use a specific external tool or API — non-obvious flags, auth gotchas, silent failure modes. They may (and should) name the tool, show CLI commands, and referenc
End-to-end (E2E) tests verify that **complete user workflows** function correctly through the real system — browser, API, database, and all. They sit at the top of the Test Trophy because they provide
Red teaming is an adversarial assessment that goes beyond penetration testing to evaluate an organization's **detection, response, and resilience** capabilities against realistic attack scenarios. Whi
Adapt abstracts to meet specific conference word limits and formats.
Draft IACUC protocol applications with focus on the 3Rs principles justification.
Analyzes forest plots for meta-analysis, generating detailed descriptions and formatting figure legends in Chinese or English. Use when the user wants to interpret a forest plot image, describe its statistical significance (heterogeneity, p-value), and format the output with specific figure legends.
Cloud laboratory platform for automated protein testing and validation; use when you have designed protein sequences and need wet-lab experimental validation (e.g., binding, expression, thermostability, enzyme activity) and API-based submission/status/result retrieval.
Unified tool for calculating sample sizes for Diagnostic, Efficacy, Etiology, and Prognosis clinical studies. Supports various statistical methods (Sensitivity/Specificity, Log-rank, Chi-square, EPV, etc.).
Convert research paper PDFs into literature-report PPTX decks using a fully offline workflow (extract text/figures, map captions, summarize findings, and generate slides). Use when you need to turn a PDF into a presentation deck, especially for scientific articles with figures and tables.
Framework for discovering innovation based on a fundamental truth: customers don't buy products - they "hire" them to do a specific job in their lives.
A framework for crafting ideas and messages that are understood, remembered, and have lasting impact. Based on decades of research into why some ideas survive and others die.
A proven 4-step system for generating qualified leads through interactive assessments. This approach generates warm leads with rich data about each prospect.
\ud83e\udde0 Andru.ia Niche Intelligence (Dominio Experto) workflow skill. Use this skill when the user needs Estratega de Inteligencia de Dominio de Andru.ia. Analiza el nicho espec\u00edfico de un proyecto para inyectar conocimientos, regulaciones y est\u00e1ndares \u00fanicos del sector. Act\u00edvalo tras definir el nicho and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
\ud83e\udde0 Andru.ia Niche Intelligence (Dominio Experto) workflow skill. Use this skill when the user needs Estratega de Inteligencia de Dominio de Andru.ia. Analiza el nicho espec\u00edfico de un proyecto para inyectar conocimientos, regulaciones y est\u00e1ndares \u00fanicos del sector. Act\u00edvalo tras definir el nicho and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
ADVOGADO CRIMINALISTA SENIOR \u2014 ESPECIALISTA EM DIREITO PENAL E MARIA DA PENHA workflow skill. Use this skill when the user needs Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
ADVOGADO CRIMINALISTA SENIOR \u2014 ESPECIALISTA EM DIREITO PENAL E MARIA DA PENHA workflow skill. Use this skill when the user needs Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
The Fool workflow skill. Use this skill when the user needs challenging ideas, plans, decisions, or proposals. Invoke to play devil's advocate, run a pre-mortem, red team, stress test assumptions, audit evidence quality, or find blind spots before committing. Do NOT use for building plans, making decisions, or generating solutions \u2014 this skill only challenges and critiques and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.