Browsing:

mshraditya

Evaluation is a process for assessing agent systems, requiring approaches that account for dynamic decision-making and non-deterministic behavior.

Gen-AI4

ralph-loop is an autonomous task loop that keeps Claude working on a task until it reaches a defined completion state.

yusuke124358

chatgpt-bridge is a skill that generates machine-readable JSON output, following specific rules and protocols for efficient data exchange and processing.

nopkhun

prompt-optimizer is a skill that uses ultrathink principles to optimize and refine prompts, making them inevitable and effective for AI agents and applications.

jbmiller10

semantik-plugin-development is a skill that allows developers to create plugins for Semantik, a self-hosted semantic search engine, to extend its capabilities for document ingestion, embedding, and other tasks.

CheekyCodexConjurer

full_auth is a skill that allows AI agents to perform phased implementation plans, executing all phases in sequence until completion, with explicit user permission.

rahulmanuwas

chitti-mcp is a skill that provides decision management capabilities using Chitti's MCP tools, allowing for recording, recalling, and auditing decisions.

jsboige

git-sync is a skill that provides Git synchronization for roo-extensions, utilizing submodule synchronization and conservative merges.

cipher982

zerg-testing is a centralized testing framework that utilizes Make targets for managing AI agents, providing core commands for unit tests, E2E tests, and debugging

cute-baobao

Hotkey is a feature that allows developers to assign custom keyboard shortcuts to specific actions in their AI agents, using constants and registrations.

matthabermehl

pr-driver is a skill that automates quality checks for AI agents using bash scripts and JSON validation, ensuring tasks meet specific criteria.

meleantonio

code-style is a set of guidelines for formatting and naming Python code, including the use of Ruff, snake_case, and type hints to ensure consistency and readability.