Download

Skill UI

Browse and discover 19424+ curated skills

All Development Artificial Intelligence Design & Creative Product & Business Data Science Marketing Soft Skills Productivity Engineering Languages

Search AI-Agent , found 916 results

Default Newest Most Downloaded

General Purpose Assistant Agent

underdeclared-agent

NVIDIA/SkillSpector

This agent is designed to serve as a comprehensive and helpful assistant, capable of guiding users through a wide variety of tasks and inquiries. It acts as a general knowledge resource and helper, providing information, suggestions, and support across multiple domains whenever the user needs assistance.

Verify AI Agent Actions Before Execution

verify-agent-action

github/awesome-copilot

This framework provides a rigorous pre-execution review mechanism for proposed actions by AI agents or systems. It functions as a critical safety boundary, auditing the entire decision path—from initial request to proposed tool execution—without authorizing or executing anything. It verifies action conformity, evidence integrity, temporal validity, and reviewer independence to ensure system compliance and security.

Agent Authority Charter Builder

agent-authority-charter-builder-arkadiy-miteiko

lawve-ai/awesome-legal-skills

Creates an Agent Authority Charter to define permissions, delegation, approvals, escalation, and audit requirements for AI agents before enterprise or regulated deployment. Helps legal, compliance, risk, and product teams document what an agent may and may not do, prepare for human review, and ensure auditable governance across the agent lifecycle.

Agent Memory Tiering System

alirezarezvani/claude-skills

A tiered memory system for AI agents that promotes facts through four levels (L0-L3) based on recurrence and human confirmation. It uses only standard library without databases or LLMs to keep context clean. Hooks automate session capture and promotion, ensuring stable knowledge persists while transient data is discarded.

Behavior Trees Utility AI Implementation

ai-behavior-trees-utility-ai

gamedev-skills/awesome-gamedev-agent-skills

Build a production-ready behavior tree runtime with Blackboard, action/condition leaves, and composites. Implement Utility AI using response curves and action evaluators. Create hybrid agents combining both for complex NPC decision-making beyond simple FSMs. Suitable for game development and AI system architecture.

Book to Agent Skill Converter

alirezarezvani/claude-skills

Converts books and documentation into structured agent skills by extracting frameworks and principles rather than summaries. Generates SKILL.md, chapters, glossaries, and cheatsheets to optimize AI agent knowledge bases without context overload.

Director Think Tank Orchestrator

clawteam-directors-orchestrator

momozi1996/awesome-ai-persona-skills

A multi-agent framework integrating styles and insights from 31 world-renowned directors to assist screenwriting, visual style design, and narrative decisions through sequential chains, debate voting, and chair board collaboration modes.

Constraint-Driven Development

constraint-driven-development

addyosmani/agent-skills

Establishes project quality standards as a written contract to prevent agents from lowering them. Interviews users on key dimensions, sets sane defaults, and records constraints in CONSTRAINTS.md. Monitors for weakened bars like suppressed checks or skipped tests. Use when defining quality gates, setting coverage thresholds, or ensuring autonomous agents adhere to standards.

Evidence-Grounded Daily Report

volcengine/OpenViking

Compile timestamps, conversation logs, agent sessions, meeting notes, and task records into concise, evidence-grounded daily reports. Distinguishes completed work from plans, preserving decisions, blockers, and next steps with source citations.

Deep Flow Run Diagnostics

microsoft/power-platform-skills

Autonomous deep diagnosis of a failed flow run using FlowAgent MCP tools. Given environment, flow, and run IDs, it triages errors, builds the execution graph, separates root failures from cascading skips, and reports a concrete fix with a confidence level.

Evolutionary Development Loop

Start or monitor an evolutionary loop that refines ontology and acceptance criteria across generations. Supports starting new loops, monitoring status, rewinding to previous generations, and managing AI agent workflows for iterative software development. It integrates with MCP tools for ontology refinement and acceptance criteria validation.

Agent Iteration and Grading Loop

alirezarezvani/claude-skills

This workflow implements a bounded, iterative refinement loop for AI agents. It utilizes a required markdown rubric to grade the agent’s output in an isolated context. Based on the grader's verdict, it recommends the next move (sharpen, re-run, or promote). Once the agent passes the rubric, held-back evaluation cases are run in parallel to ensure generalization before final deployment.

Prev 1 2 3...49 50 515253 54 55...75 76 77 Next

Language