AI Engineering

Action Converter turns open loops from memory, logs, topics, cron state, and PRs into five specific next actions. It is used when you need concrete, leverage-scored work items instead of vague planning.

Auto Research evolves an existing skill by generating variations, scoring them, and replacing the original with the best version. Use it when you want to improve a skill’s inputs, output, reliability, or overall approach.

Base MCP accesses a Base Account wallet for balances, portfolio data, sending, swapping, signing, x402 payments, batched contract calls, and transaction history. Use it when an agent needs to interact with Base through the MCP server.

Context Engineering curates the right project files, specs, and evidence before coding or debugging. Use it when starting a session, switching code areas, or reconciling external instructions with repository conventions.

Create Skill generates a complete new Claude Code skill from a one-line prompt and prepares it for review as a pull request. It is used when you want a new skill scaffolded with steps, research, and workflow notes.

Executor MCP runs one task through Executor Cloud’s connected tool catalog, including MCP servers, OpenAPI specs, and GraphQL APIs. Use it to discover available integrations and execute a task under allow, approval, or block policies.

Finance District MCP operates a non-custodial agent wallet to check balances, prices, yields, and move funds or pay x402 requests across supported chains. Use it when you need structured wallet actions with server-side limits and TEE-protected keys.

GitHub Trending curates trending GitHub repositories and Hugging Face assets into a smaller, filtered list with a short why-notable note and momentum tag. Use it to scan what is gaining attention without reading the full trending pages.

Harness Improvement turns session learnings into durable harness changes like skills, agents, commands, and instruction files. Use it when updating Claude Code or related harness guidance across platforms.

Interview Me clarifies the user’s intent before specs, plans, or code when an ask is underspecified. Use it to ask focused questions and surface assumptions before proceeding.

Planner Orchestration enforces Kandev's single-session workflow for planning, execution, delegation, and delivery. Use it to keep specs, task files, model checkpoints, and handoffs organized during feature, fix, debug, review, and verification work.

PR Walkthrough generates a single-file HTML summary of a pull request. Use it when you need a scrollable page that explains the problem, approach, code changes, data flow, and trade-offs for reviewers.