Design, validate, and plan a startup from scratch. Covers market research, competitive analysis, business model, brand identity, product definition, financial projections, and validation experiments. Trigger when the user has a startup idea to explore, wants to validate a business concept, needs a business plan or lean canvas, asks for market sizing or competitive landscape, wants brand positioning or go-to-market strategy, or says anything like "I have an idea for..." or "is this idea worth pursuing". Also handles resuming from a previous checkpoint.

Loads coding rules from Qodo most relevant to the current coding task by generating a semantic search query from the assignment. Use when Qodo is configured and the user asks to write, edit, refactor, or review code, or when starting implementation planning. Skip if rules are already loaded.

Orchestrator context window discipline enforcement. Prevents the orchestrator from reading source files it will not edit, running diagnostic commands that waste context, and rationalizing delegation bypasses. Use when setting up orchestrator guardrails, reviewing delegation discipline, or diagnosing context window waste in multi-agent workflows. Activates PreToolUse hooks that surface decision points before source file reads and diagnostic command execution.

Execute Ideogram production deployment checklist and rollback procedures. Use when deploying Ideogram integrations to production, preparing for launch, or implementing go-live procedures. Trigger with phrases like "ideogram production", "deploy ideogram", "ideogram go-live", "ideogram launch checklist", "ideogram production ready".

Optimize Ideogram API performance with caching, model selection, and parallel generation. Use when experiencing slow generation, implementing caching strategies, or optimizing throughput for Ideogram integrations. Trigger with phrases like "ideogram performance", "optimize ideogram", "ideogram latency", "ideogram caching", "ideogram slow", "ideogram speed".

Deploy Fireflies.ai webhook receivers and GraphQL clients to Vercel, Docker, and Cloud Run. Use when deploying Fireflies.ai-powered applications to production, configuring platform-specific secrets, or hosting webhook endpoints. Trigger with phrases like "deploy fireflies", "fireflies Vercel", "fireflies production deploy", "fireflies Cloud Run", "fireflies Docker".

Process JSON with jq and YAML/TOML with yq. Filter, transform, query structured data efficiently. Triggers on: parse JSON, extract from YAML, query config, Docker Compose, K8s manifests, GitHub Actions workflows, package.json, filter data.

GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available), bulk operations across many repos (script with gh api), or when gh auth is not configured.

Optimize CodeRabbit review speed, relevance, and signal-to-noise ratio. Use when reviews take too long, contain too many irrelevant comments, or when teams are experiencing review fatigue. Trigger with phrases like "coderabbit performance", "optimize coderabbit", "coderabbit slow", "coderabbit noise", "coderabbit too many comments", "coderabbit relevance".

Configure CodeRabbit CLI for local pre-commit code reviews and fast iteration. Use when setting up local development with CodeRabbit CLI reviews, integrating AI review into your commit workflow, or testing config changes. Trigger with phrases like "coderabbit dev setup", "coderabbit local development", "coderabbit CLI workflow", "coderabbit pre-commit review".

Database schema design for PostgreSQL/MySQL with normalization, relationships, constraints. Use for new databases, schema reviews, migrations, or encountering missing PKs/FKs, wrong data types, premature denormalization, EAV anti-pattern.

Reverse-engineering specialist that extracts specifications from existing codebases. Use when working with legacy or undocumented systems, inherited projects, or old codebases with no documentation. Invoke to map code dependencies, generate API documentation from source, identify undocumented business logic, figure out what code does, or create architecture documentation from implementation. Trigger phrases: reverse engineer, old codebase, no docs, no documentation, figure out how this works, inherited project, legacy analysis, code archaeology, undocumented features.

Use when building React 18+ applications in .jsx or .tsx files, Next.js App Router projects, or create-react-app setups. Creates components, implements custom hooks, debugs rendering issues, migrates class components to functional, and implements state management. Invoke for Server Components, Suspense boundaries, useActionState forms, performance optimization, or React 19 features.

Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training datasets, setting hyperparameters for fine-tuning runs, adapter training, transfer learning, finetuning with Hugging Face PEFT, OpenAI fine-tuning, instruction tuning, RLHF, DPO, or quantizing and deploying fine-tuned models. Trigger terms include: LoRA, QLoRA, PEFT, finetuning, fine-tuning, adapter tuning, LLM training, model training, custom model.

Use when building .NET 8 applications with minimal APIs, clean architecture, or cloud-native microservices. Invoke for Entity Framework Core, CQRS with MediatR, JWT authentication, AOT compilation.

Compresses images to WebP (default) or PNG with automatic tool selection. Use when user asks to "compress image", "optimize image", "convert to webp", or reduce image file size.

AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream, Replicate and Agnes APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.

Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training datasets, setting hyperparameters for fine-tuning runs, adapter training, transfer learning, finetuning with Hugging Face PEFT, OpenAI fine-tuning, instruction tuning, RLHF, DPO, or quantizing and deploying fine-tuned models. Trigger terms include: LoRA, QLoRA, PEFT, finetuning, fine-tuning, adapter tuning, LLM training, model training, custom model.

Microsoft/Bing Ads deep analysis covering search, Performance Max, Audience Network, and Copilot integration. Evaluates 24 checks with focus on Google Ads import validation, unique Microsoft features (LinkedIn audience targeting, in-market audiences), and cost advantage assessment. Use when user says Microsoft Ads, Bing Ads, Bing PPC, Bing search ads, Copilot ads, Microsoft search ads, Google import audit, or Microsoft campaign.

Set up Gamma API v1.0 authentication and first request. Use when configuring API keys, setting up X-API-KEY header, or initializing Gamma REST API access in a project. Trigger: "install gamma", "setup gamma API", "gamma auth", "gamma API key", "configure gamma".