Research

Fetch current model names from AI providers (Anthropic, OpenAI, Gemini, Ollama), classify them into tiers (fast/default/heavy), and detect new models. Use when needing up-to-date model IDs for API calls or when other skills reference model names.

Pre-implementation confidence assessment (≥90% required). Use before starting any implementation to verify readiness with duplicate check, architecture compliance, official docs verification, OSS references, and root cause identification.

Get comprehensive factory status - research progress, drill status, inventory, production overview. Use when checking progress or deciding what to do next.

Documents HOW code works with surgical precision - traces data flow, explains implementation details, provides file:line references. Purely documentarian, no critiques or suggestions for improvement.

Build document Q&A and searchable knowledge bases with Google Gemini File Search - fully managed RAG with automatic chunking, embeddings, and citations. Upload 100+ file formats (PDF, Word, Excel, code), configure semantic search, and query with natural language.Use when: building document Q&A systems, creating searchable knowledge bases, implementing semantic search without managing embeddings, indexing large document collections (100+ formats), or troubleshooting document immutability errors (delete+re-upload required), storage quota issues (3x input size for embeddings), chunking configuration (500 tokens/chunk recommended), metadata limits (20 key-value pairs max), indexing cost surprises ($0.15/1M tokens one-time), operation polling timeouts (wait for done: true), force delete errors, or model compatibility (Gemini 2.5 Pro/Flash only).

Research and identify target companies matching ICP observable characteristics using web search, score against ICP criteria, output prioritized prospect list. Use when you need to find and qualify potential customers.

Web research skill for augmenting agent context with current information. Used when outdated information could lead to broken implementations or wasted effort.

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.1-Codex by default for state-of-the-art software engineering.

Context-aware task execution with Serena MCP backend. First time: Explores project, saves to Serena,runs spec if complex, executes waves. Returning: Loads from Serena (<1s), detects changes, executeswith cached context. Intelligently decides when to research, when to spec, when to prime. One catch-allintelligent execution command. Use when: User wants task executed in any project (new or existing).

Validate claims against sources and score confidence; use when asked to verify research output accuracy.

Preferences and tricks for working with SQLite databases

Work with Resource datasets (mutable state tracking) using OPAL temporal joins. Use when you need to enrich Events/Intervals with contextual state information, track resource state changes over time, or navigate between datasets using temporal relationships. Covers temporal join mechanics (lookup, join, follow), automatic field matching, and when to use Resources vs Reference Tables.

Systematic marketing experimentation process - discover concepts, generate hypotheses, coordinate multiple experiments, synthesize results, generate next-iteration ideas through rigorous validation cycles

Executes Exa AI search queries via unified Python CLI. Use when searching the web for current information, finding code examples, researching APIs, SDKs, or retrieving programming context for any library or framework.

Identify unifying concepts and common threads that run through multiple observations or ideas, useful for making sense of diverse feedback, understanding what really matters, or finding the signal in noise. Use when: (1) explicit request to identify patterns or themes that unify diverse observations, (2) numerous qualitative observations need analysis for what recurs across them, (3) deciding priorities requires understanding what concerns keep appearing across stakeholders, (4) multiple sources describe situations using different terms but may share underlying patterns.

Use when user wants to assess progress toward an open-ended goal by reading and summarizing all iteration journals

Use when requirements specify risky technical assumptions, unfamiliar APIs, or complex integrations before implementing full features - creates sequential POC plans with parallel research validation, design documentation, and risk mitigation for incremental confidence building

When designing layouts, navigation, forms, or feedback components. Reference for consistent UI decisions.

Generate conversion-optimized page copy using VOC research, competitor insights, and proven structures. Use when creating or revising landing pages, service pages, or marketing content.

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.