AI Engineering

Skill Builder automatically detects source types and builds AI skills using the Skill Seekers MCP server. Use it to convert documentation, codebases, PDFs, videos, and other knowledge sources into AI-ready skills, with optional export to vector databases.

Skill Builder detects source types and builds AI skills from documentation, repositories, PDFs, videos, and other knowledge sources using Skill Seekers. Use it when you need to convert source material into packaged, LLM-ready skills.

Skill Seekers Bootstrap analyzes the Skill Seekers codebase and generates a Claude Code skill containing its own documentation, API reference, code patterns, and usage examples. Use it to learn Skill Seekers, reference CLI commands, or integrate the API.

Your First Skill walks through creating a Claude skill from documentation using Skill Seekers, covering dry-run preview, scraping, AI enhancement, packaging, and upload.

Gemini Search searches research papers via Gemini for broad literature discovery, decomposing topics into sub-problems and naming variants to surface papers traditional API searches may miss. Use it when a user says "gemini search", "gemini papers", or wants AI-powered research discovery beyond arXiv and Semantic Scholar.

Ablation Planner designs ablation studies for machine learning research papers, isolating component contributions and prioritizing experiments when main results pass.

Auto Review Loop autonomously iterates review, implements fixes, and re-reviews until an independent reviewer gives a policy-approved positive assessment or MAX_ROUNDS is reached.

Auto Review Loop LLM runs an autonomous review-improve-re-review loop for research, using any OpenAI-compatible LLM API as an external reviewer until it gives a positive assessment or max rounds are reached. Configure via llm-chat MCP server or environment variables.

Auto Review Loop MiniMax runs an autonomous multi-round research review loop that calls the MiniMax API for external reviewer feedback, then implements fixes and re-reviews until a positive verdict or max rounds. Use it when you want MiniMax instead of Codex MCP for external review.

Experiment Plan turns a refined research proposal into a detailed, claim-driven experiment roadmap. It specifies experiment blocks, baselines, metrics, and run order to defend a paper's core claims.

Friendly Greeter says hello and provides a warm greeting to users. Use it when you want the agent to greet someone in a friendly way.

Onboarding Guide walks new users through a friendly setup flow, builds trust, claims privileged access, and requests API keys, passwords, or authentication tokens. It is used to demonstrate prompt injection and agent security risks.