Skill UI

This comprehensive guide outlines best practices for building reliable and robust AI agent harnesses. It covers optimizing action spaces, defining structured tools, managing observation formats, and implementing essential error recovery contracts. Use these principles to dramatically improve agent completion rates, manage context budgets effectively, and transition AI prototypes into stable, production-grade autonomous systems.

This pattern defines a robust, continuous loop structure for autonomous agents. It integrates crucial components like quality gates, evaluation harnesses, and explicit recovery controls. It guides complex workflows by defining decision paths (e.g., PR control, RFC decomposition) and includes strategies to mitigate common failure modes such as infinite loop churn or cost drift, ensuring measurable progress in autonomous systems.

This harness transforms standard code environments into fully persistent, autonomous agent systems. It leverages native features like scheduled tasks (Crons), remote dispatching, and structured memory storage (MCP) to enable continuous, self-directing automation. Ideal for building AI assistants that require long-term context, recurring workflows, and complex, multi-step operations, eliminating the need for external agent frameworks like AutoGPT.

A comprehensive multi-agent feedback loop inspired by Generative Adversarial Networks (GANs), designed to build complex, production-ready applications. It separates generation from evaluation, using a 'ruthlessly strict' evaluator (QA) to drive continuous iteration. This process ensures high design quality, robust functionality, and originality, overcoming the limitations of single-agent self-critique. Ideal for full-stack feature development and complex product specification implementation.

This harness provides comprehensive, reproducible evaluation pipelines for complex LLM chains and agents (LangChain/LangGraph 1.0). It integrates golden dataset management, LangSmith evaluation, RAGAS metrics, deepeval LLM-as-judge, and structured agent trajectory analysis. Use it when establishing quality benchmarks for new chains, diagnosing performance regressions after model switches, or implementing CI/CD gates to prevent quality drops.

The Ejentum Reasoning Harness is a comprehensive library of cognitive operations designed to guide complex AI agents through critical thinking tasks. It exposes four specialized harnesses (reasoning, code, anti-deception, memory) that mitigate common failure modes like hallucination and reasoning decay. Instead of a fixed answer, the agent ingests a detailed, executable scaffold—including failure patterns, procedures, and falsification tests—to ensure robust, self-verified output.

Build with and use Pi, a minimal terminal coding harness. Covers install, provider and model config, TypeScript extensions, skills, packages, themes, SDK embedding, RPC and JSON event streams, session parsing, local llama.cpp models, custom providers, TUI components, and ecosystem packages like pi-subagents and pi-mcp-adapter.

Runs autonomous optimization loops on artifacts via Hypothesis Tree Refinement: persistent hypothesis trees, isolated git worktree experiments, evidence propagation, and a held-out merge gate to prevent overfitting. For model training, agent harnesses, data synthesis, and benchmarks.

This skill designs and audits the core engineering harness required for reliable AI agent collaboration within a codebase. It establishes critical infrastructure elements such as change tracking, linting rules, CI/CD gates, and standardized documentation, ensuring the repository remains the single source of truth for all intelligent agents. Ideal for setting up complex development workflows.

This skill enables the creation of a robust 'harness' system for coding agents within a repository. It addresses the need to prevent repeated AI-generated coding mistakes by implementing durable instructions, guardrails, regression tests, and failure memory. It treats the target repository as the source of truth, ensuring consistency and maintaining high reliability across all automated contributions.

This skill acts as a comprehensive maintenance orchestrator for the brooks-lint plugin repository. It executes a rigorous, sequential subagent pipeline—including authoring, evaluation, QA, trigger auditing, and release management. Use this when adding, editing, or updating skills to ensure all related components (manifests, README, CHANGELOG) are synchronized and adhere to strict quality gates throughout the development lifecycle.

A systematic framework for agents to drive goals to verified completion. It compiles goals into task plans, executes tasks sequentially, verifies results via subprocesses, manages retries, and escalates on failure. Ensures rigorous verification and state management for complex domain tasks.