Skill System Overview
Learn how the new skill model decouples orchestration, execution, and evaluation while remaining LLM-friendly.
Select a guide to explore Achilles Agents Library from architecture to hands-on tutorials.
Use the links below to explore the major skill guides. Each page provides conceptual background, public API documentation, and practical guidance.
Learn how the new skill model decouples orchestration, execution, and evaluation while remaining LLM-friendly.
Manage backlog files, task lifecycles, approvals, and history moves with the BacklogManager API.
Understand how LLMAgent and RecursiveSkilledAgent collaborate to supervise multi-step plans.
Deep dive into LoopAgentSession and SOPAgenticSession for stateful, multi-turn agent workflows.
See how orchestration skills build loop/SOP agentic sessions, apply intent taxonomies, and monitor downstream execution.
Detailed syntax, semantics, and command mapping rules for the scripting language that powers agent plans.
Understand default execution limits, monitoring hooks, and how to build custom observability for scripts.
See how table descriptors become CRUD workflows that plan operations, collect fields, and persist records.
Step-by-step guides showing how to define skills, configure orchestration sessions, and integrate MCP tools.
Discover how MCP-hosted toolchains are planned, scripted, and executed through the Agent runtime.
Dive into sandboxed code evaluation, safety filters, and developer productivity patterns.
Generate executable code from detailed specifications and execute it safely.
Understand regeneration rules, test generation, and repair workflows for spec-driven code.
Review static descriptors that surface skill summaries and bodies without running LLM actions.
import/export only).npm test before committing.SKILLEDAGENT-ARCHITECTURE.md to align with existing patterns.