itallstartedwithaidea/agent-skills

parallel-agent-orchestration

Parallel Agent Orchestration is the discipline of dispatching, coordinating, and aggregating results from multiple concurrent subagents to dramatically accelerate complex tasks.

原文の言語: 英語

proactive-intelligence

Proactive Intelligence enables agents to autonomously seek out external information — web searches, API re-pulls, data freshness checks — during analysis without waiting for explicit user requests

原文の言語: 英語

context-engineering

Context Engineering is the discipline of maximizing agent output quality while minimizing token expenditure.

原文の言語: 英語

prompt-architecture

Prompt Architecture is the structural engineering of agent instructions.

原文の言語: 英語

verification-loops

Verification Loops are systematic evaluation pipelines that validate agent outputs at every stage of execution.

原文の言語: 英語

continuous-learning

Continuous Learning enables agents to automatically extract successful patterns from completed sessions and codify them into reusable skills, rules, and prompt refinements.

原文の言語: 英語

entity-memory-management

Entity Memory Management is the systematic extraction, persistence, and retrieval of named entities across agent sessions, enabling long-term contextual awareness that transforms transient conversations into persistent relationships.

原文の言語: 英語

knowledge-base-injection

Knowledge Base Injection is the technique of dynamically injecting domain expertise into an agent's context at the moment it is most relevant, using TF-IDF pattern matching and semantic scoring.

原文の言語: 英語

long-horizon-workflows

Long-Horizon Workflows enable AI agents to execute multi-hour, multi-phase autonomous pipelines that far exceed the scope of a single conversation turn.

原文の言語: 英語

mcp-server-creation

MCP Server Creation is the skill of building Model Context Protocol servers that expose tools, resources, and capabilities to AI agents through a standardized interface.

原文の言語: 英語

memory-persistence

Memory Persistence enables AI agents to maintain knowledge across sessions, transforming stateless inference calls into stateful, continuously improving systems.

原文の言語: 英語

multi-model-routing

Multi-Model Routing is the intelligent dispatch of agent tasks to the optimal model provider based on task characteristics, cost constraints, latency requirements, and availability.

原文の言語: 英語

token-optimization

Token Optimization is the systematic reduction of token expenditure across agent operations without sacrificing output quality.

原文の言語: 英語

adversarial-resilience

Adversarial Resilience is the practice of hardening AI agents against deliberate attacks — prompt injection, data exfiltration, sandbox escape, and unauthorized capability escalation.

原文の言語: 英語

agent-instinct-system

The Agent Instinct System implements pre-cognitive reflexes — automatic safety checks and validations that fire before every code change, tool call, or output generation.

原文の言語: 英語

anthropic-tool-mastery

Anthropic Tool Mastery is the definitive skill for leveraging Claude's native tool_use capability to its fullest potential.

原文の言語: 英語

cognitive-scaffolding

Cognitive Scaffolding structures an agent's context window using principles from cognitive science — primacy effects, recency bias, chunking, and attention allocation.

原文の言語: 英語

multi-harness-portability

Multi-Harness Portability is the engineering discipline of writing agent skills, prompts, and configurations that work across every major AI coding harness — Claude Code, Cursor, Codex, Gemini CLI, OpenCode, and beyond.

原文の言語: 英語

self-healing-agents

Self-Healing Agents are autonomous systems that detect their own failure modes and self-correct without human intervention.

原文の言語: 英語

session-archaeology

Session Archaeology is the systematic excavation and analysis of past agent sessions to extract reusable patterns, identify recurring failure modes, and derive new skills from operational history.

原文の言語: 英語

ad-copy-generation

The Ad Copy Generation skill produces high-performance responsive search ad (RSA) copy using AI-driven generation pipelines calibrated against millions of ad performance data points.

原文の言語: 英語

audience-targeting

The Audience Targeting skill orchestrates Google Ads' full audience ecosystem to reach the right users at every stage of the conversion funnel.

原文の言語: 英語

budget-optimization

The Budget Optimization skill applies AI-driven forecasting and portfolio theory to allocate advertising budgets across campaigns for maximum return.

原文の言語: 英語

competitor-analysis

The Competitor Analysis skill transforms Google Ads auction data into actionable competitive intelligence.

原文の言語: 英語

conversion-tracking

The Conversion Tracking skill provides end-to-end management of Google Ads conversion measurement infrastructure.

原文の言語: 英語

google-ads-audit

The Google Ads Account Audit skill executes a comprehensive, pattern-driven analysis of any Google Ads account using a proprietary 1,000-pattern knowledge base.

原文の言語: 英語

keyword-research

The Keyword Research skill delivers a systematic approach to keyword discovery, expansion, and optimization for Google Ads campaigns.

原文の言語: 英語

landing-page-audit

The Landing Page Audit skill performs comprehensive evaluations of post-click experiences, combining technical performance analysis with conversion rate optimization (CRO) assessment.

原文の言語: 英語

pmax-optimization

The Performance Max Optimization skill provides expert-level management of Google's most automated campaign type.

原文の言語: 英語

quality-score-optimization

The Quality Score Optimization skill provides a systematic framework for diagnosing, tracking, and improving Quality Score across every keyword in a Google Ads account.

原文の言語: 英語

remarketing-strategy

The Remarketing Strategy skill designs and implements cross-channel remarketing architectures that re-engage users at every stage of the conversion funnel.

原文の言語: 英語

shopping-ads

The Shopping Ads skill delivers end-to-end management of Google Shopping campaigns and Merchant Center product feeds.

原文の言語: 英語

ci-cd-pipelines

CI/CD Pipelines defines production-grade continuous integration and deployment workflows using GitHub Actions with wrangler deploy, link validation, HTML validation, and automated quality gates.

原文の言語: 英語

cloudflare-workers

Cloudflare Workers provides comprehensive guidance for building edge-first applications using Durable Objects, KV, R2, D1, AI bindings, and Vectorize.

原文の言語: 英語

configuration-management

Configuration Management implements dynamic configuration with hot-reload capability, inspired by Nacos configuration management patterns.

原文の言語: 英語

edge-rendering

Edge Rendering generates and serves dynamic pages at the network edge, eliminating origin round-trips for content that varies by city, service, or user segment.

原文の言語: 英語

observability

Observability implements structured logging, distributed tracing, and error monitoring for Cloudflare Workers and edge applications.

原文の言語: 英語

service-discovery

Service Discovery implements dynamic service registry, health check monitoring, and intelligent load balancing patterns inspired by Nacos for cloud-native applications.

原文の言語: 英語

ml-model-integration

ML Model Integration provides workflows for discovering, evaluating, and deploying machine learning models from HuggingFace Hub.

原文の言語: 英語

programmatic-video

Programmatic Video enables React-based video rendering with Remotion, where every frame is a React component and every animation is expressed in code.

原文の言語: 英語