Build an early sales team and operating cadence (readiness gate, hiring plan, role scorecards, interview loop, onboarding/ramp). Use for first AE/SDR hires, seed→Series A sales team build, and...
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
>
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with...
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate...
複雑なタスク（Epic）を15分以内のAtomic Stepに分解するワークフローガイド。進捗管理、脱線防止、適切なタイミングでのコミット提案。迷わず登頂するための山岳ガイド役。複雑タスク分解が必要な時に使用。
Use this skill when users are stuck on a decision, overthinking, experiencing analysis paralysis, or need to ship faster. Activates for "should I wait," "I can't decide," "I'm overthinking," or...
E2Eテスト専門。Playwright/Cypress設定、Page Object設計、認証フロー、並列実行、視覚回帰、CI統合。ユーザージャーニー全体を検証。RadarのE2E専門版。E2Eテスト作成が必要な時に使用。
Dispatches one subagent per independent domain to parallelize investigation/fixes. Use when you have 2+ unrelated failures (e.g., separate failing test files, subsystems, bugs) with no shared...
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
Validate n8n expression syntax and fix common errors. Use when writing n8n expressions, using {{}} syntax, accessing $json/$node variables, troubleshooting expression errors, or working with...
Use this skill when users need to create irresistible offers, design value stacks, optimize product/service positioning, or build "grand slam offers." Activates for offer creation, value...
Comprehensive code review for PRs or recent changes. Checks correctness, security, performance, maintainability, and tests.
Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when...
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse...
Use this skill when users need to develop brand strategy, choose a company name, define brand positioning, create brand voice, or build brand identity from day one. Activates for "what should I...
Plan, run, and synthesize usability tests and produce a Usability Test Pack (test plan, tasks/script, logistics, notes template, issue log, findings + recommendations). Use for usability test,...
Disciplined plan execution for implementation tasks. Use when executing a saved implementation plan, following step-by-step instructions from a plan document.
Use this skill when users need to validate a launch plan, assess MVP scope, or determine if they're ready to execute. Activates for "validate my plan," "am I ready to launch," "is my scope too...
When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup," "structured data," "JSON-LD," "rich snippets,"...