Create, optimize, and evaluate reusable AgentEvolver HTML Workflows. Use when a repeated successful multi-agent orchestration should be retained, when an evolvable Workflow has recurring orchestration-level defects, or when a live version needs evidence for keep, improve, or rollback decisions.
Create new skills, improve/optimize existing skills, and evaluate skill quality — the full skill lifecycle. Use this whenever the task involves authoring a skill from scratch, editing or improving an existing skill, evaluating/scoring a skill, running test cases to measure whether a skill helps, or tuning a skill's description for better triggering. MetaAgent uses it to orchestrate the create→evaluate→improve loop across sub-agents.
Create new agents, improve/optimize existing agents (both Python class and HTML prompt), and evaluate agent quality — the full agent lifecycle in this framework. Use whenever the task involves authoring a new agent, editing/improving an existing agent or its prompt, or evaluating/scoring an agent. MetaAgent uses it to orchestrate the create→evaluate→improve loop across sub-agents.
Create new connectors (CONNECTOR.md configs that connect the framework to an MCP server), improve/optimize existing connectors, evaluate connector quality, and — when needed — build a new MCP server to connect to. Use this whenever the task involves adding a connector for an MCP server, writing/editing a CONNECTOR.md, evaluating whether a connector's actions let an agent accomplish tasks, or building an MCP server from scratch (Python FastMCP or Node/TS). MetaAgent uses it to orchestrate the create→evaluate→improve loop across sub-agents.
Create new environments, improve/optimize existing environments, and evaluate environment quality — the full environment lifecycle in this framework. Use whenever the task involves authoring a new environment (a stateful Python class exposing actions, plus an ENVIRONMENT.md), editing/improving an existing environment, or evaluating/scoring one. MetaAgent uses it to orchestrate the create→evaluate→improve loop across sub-agents.
Create new tools, improve/optimize existing tools, and evaluate tool quality — the full tool lifecycle in this framework. Use whenever the task involves authoring a new tool (a Python class the agents can call), editing/improving an existing tool, or evaluating/scoring a tool. MetaAgent uses it to orchestrate the create→evaluate→improve loop across sub-agents.
Predict genome-wide functional tracks (RNA-seq, CAGE, DNase, ChIP) from DNA sequence with Borzoi. Use this skill when: (1) Scoring the regulatory effect of a variant on expression/accessibility, (2) Generating predicted coverage tracks for a locus, (3) Prioritising non-coding variants by predicted track delta.
Embed proteins with Meta AI's ESM-2 (`fair-esm` package). Use this skill when: (1) Extracting per-residue or per-sequence embeddings for downstream ML, (2) Masked-LM likelihood / mutation effect scoring, (3) Contact prediction from a sequence.